Search

Simple Summary: Preoperative risk prediction prior to oncologic esophagectomy is crucial for assisting surgeons in accurate patient selection and patients in their informed decision making. A new risk stratification tool, the IESG prediction model, was recently introduced, categorizing patients into different risk levelsMachine learning is a subfield of artificial intelligence and may allow for a more accurate identification of patients at risk. Therefore, we evaluated the IESG risk model and compared its performance with ML models. We found that the IESG risk model provided an overall adequate risk estimation. However, ML showed better results in the accurate risk stratification of patients, demonstrating its potential as a novel and powerful approach for future patient assessment. Risk prediction prior to oncologic esophagectomy is crucial for assisting surgeons and patients in their joint informed decision making. Recently, a new risk prediction model for 90-day mortality after esophagectomy using the International Esodata Study Group (IESG) database was proposed, allowing for the preoperative assignment of patients into different risk categories. However, given the non-linear dependencies between patient- and tumor-related risk factors contributing to cumulative surgical risk, machine learning (ML) may evolve as a novel and more integrated approach for mortality prediction. We evaluated the IESG risk model and compared its performance to ML models. Multiple classifiers were trained and validated on 552 patients from two independent centers undergoing oncologic esophagectomies. The discrimination performance of each model was assessed utilizing the area under the receiver operating characteristics curve (AUROC), the area under the precision–recall curve (AUPRC), and the Matthews correlation coefficient (MCC). The 90-day mortality rate was 5.8%. We found that IESG categorization allowed for adequate group-based risk prediction. However, ML models provided better discrimination performance, reaching superior AUROCs (0.64 [0.63–0.65] vs. 0.44 [0.32–0.56]), AUPRCs (0.25 [0.24–0.27] vs. 0.11 [0.05–0.21]), and MCCs (0.27 ([0.25–0.28] vs. 0.15 [0.03–0.27]). Conclusively, ML shows promising potential to identify patients at risk prior to surgery, surpassing conventional statistics. Still, larger datasets are needed to achieve higher discrimination performances for large-scale clinical implementation in the future. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to predict the Length of hospital Stay (LoS) after laparoscopic right hemicolectomy for colon cancer using machine learning techniques. Accurately forecasting LoS is crucial for improving patient care and hospital resource management. The researchers utilized data from two large Italian studies, CoDIG 1 and CoDIG 2, to train and validate various machine learning models. The Random Forest (RF) algorithm demonstrated the best internal performance, while the Support Vector Machine (SVM) outperformed in external validation. Key factors influencing LoS included the use of fast-track protocols, type of anastomosis, and drainage. These findings could help tailor postoperative care and optimize hospital resources, ultimately enhancing patient outcomes and operational efficiency. The evolution of laparoscopic right hemicolectomy, particularly with complete mesocolic excision (CME) and central vascular ligation (CVL), represents a significant advancement in colon cancer surgery. The CoDIG 1 and CoDIG 2 studies highlighted Italy's progressive approach, providing useful findings for optimizing patient outcomes and procedural efficiency. Within this context, accurately predicting postoperative length of stay (LoS) is crucial for improving resource allocation and patient care, yet its determination through machine learning techniques (MLTs) remains underexplored. This study aimed to harness MLTs to forecast the LoS for patients undergoing right hemicolectomy for colon cancer, using data from the CoDIG 1 (1224 patients) and CoDIG 2 (788 patients) studies. Multiple MLT algorithms, including random forest (RF) and support vector machine (SVM), were trained to predict LoS, with CoDIG 1 data used for internal validation and CoDIG 2 data for external validation. The RF algorithm showed a strong internal validation performance, achieving the best performances and a 0.92 ROC in predicting long-term stays (more than 5 days). External validation using the SVM model demonstrated 75% ROC values. Factors such as fast-track protocols, anastomosis, and drainage emerged as key predictors of LoS. Integrating MLTs into predicting postoperative LOS in colon cancer surgery offers a promising avenue for personalized patient care and improved surgical management. Using intraoperative features in the algorithm enables the profiling of a patient's stay based on the planned intervention. This issue is important for tailoring postoperative care to individual patients and for hospitals to effectively plan and manage long-term stays for more critical procedures. [ABSTRACT FROM AUTHOR]

Simple Summary: Three-dimensional (3D) telomere analysis using TeloView v 2.2 has shown promise in quantifying genomic instability and predicting therapy response. In a study of 156 Classic Hodgkin's lymphoma (cHL), we identified significant 3D telomere parameters that predict patient outcomes. A predictive model using four 3D telomere parameters, including the proportion of t-stumps (very short telomeres), achieved an area under curve (AUC) of 0.83, with a sensitivity and specificity of 0.82 and 0.78, respectively. Classic Hodgkin's lymphoma (cHL) is a curable cancer with a disease-free survival rate of over 10 years. Over 80% of diagnosed patients respond favorably to first-line chemotherapy, but few biomarkers exist that can predict the 15–20% of patients who experience refractory or early relapsed disease. To date, the identification of patients who will not respond to first-line therapy based on disease staging and traditional clinical risk factor analysis is still not possible. Three-dimensional (3D) telomere analysis using the TeloView® software platform has been shown to be a reliable tool to quantify genomic instability and to inform on disease progression and patients' response to therapy in several cancers. It also demonstrated telomere dysfunction in cHL elucidating biological mechanisms related to disease progression. Here, we report 3D telomere analysis on a multicenter cohort of 156 cHL patients. We used the cohort data as a training data set and identified significant 3D telomere parameters suitable to predict individual patient outcomes at the point of diagnosis. Multivariate analysis using logistic regression procedures allowed for developing a predictive scoring model using four 3D telomere parameters as predictors, including the proportion of t-stumps (very short telomeres), which has been a prominent predictor for cHL patient outcome in a previously published study using TeloView® analysis. The percentage of t-stumps was by far the most prominent predictor to identify refractory/relapsing (RR) cHL prior to initiation of adriamycin, bleomycin, vinblastine, and dacarbazine (ABVD) therapy. The model characteristics include an AUC of 0.83 in ROC analysis and a sensitivity and specificity of 0.82 and 0.78 respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: The incidence of metastatic melanoma is rising, making it imperative to identify patients who do not benefit from immunotherapy. This study aimed to develop a radiomic biomarker, using segmentations from 146 baseline and 146 first follow-up CT scans, to predict best overall response, progression-free survival, and overall survival across various immunotherapies. We volumetrically segmented the total tumour load, excluding cerebral metastases. This study also examined whether reducing the number of segmented metastases per patient affects predictive accuracy. The findings suggest that delta radiomics could enhance the prediction of best overall response, progression-free survival, and overall survival in metastatic melanoma patients undergoing first-line immunotherapy. Although volumetric whole tumour load segmentation is complex, it may provide predictive benefits. Background: The prevalence of metastatic melanoma is increasing, necessitating the identification of patients who do not benefit from immunotherapy. This study aimed to develop a radiomic biomarker based on the segmentation of all metastases at baseline and the first follow-up CT for the endpoints best overall response (BOR), progression-free survival (PFS), and overall survival (OS), encompassing various immunotherapies. Additionally, this study investigated whether reducing the number of segmented metastases per patient affects predictive capacity. Methods: The total tumour load, excluding cerebral metastases, from 146 baseline and 146 first follow-up CTs of melanoma patients treated with first-line immunotherapy was volumetrically segmented. Twenty-one random forest models were trained and compared for the endpoints BOR; PFS at 6, 9, and 12 months; and OS at 6, 9, and 12 months, using as input either only clinical parameters, whole-tumour-load delta radiomics plus clinical parameters, or delta radiomics from the largest ten metastases plus clinical parameters. Results: The whole-tumour-load delta radiomics model performed best for BOR (AUC 0.81); PFS at 6, 9, and 12 months (AUC 0.82, 0.80, and 0.77); and OS at 6 months (AUC 0.74). The model using delta radiomics from the largest ten metastases performed best for OS at 9 and 12 months (AUC 0.71 and 0.75). Although the radiomic models were numerically superior to the clinical model, statistical significance was not reached. Conclusions: The findings indicate that delta radiomics may offer additional value for predicting BOR, PFS, and OS in metastatic melanoma patients undergoing first-line immunotherapy. Despite its complexity, volumetric whole-tumour-load segmentation could be advantageous. [ABSTRACT FROM AUTHOR]

Simple Summary: The identification of gliomas and the differentiation between different types is essential to evaluate patients' prognosis and guide optimal clinical management. The ideal multiparametric magnetic resonance imaging (MRI) protocol for the assessment of gliomas is a current topic of research. This study aimed to explore the performance of dynamic contrast-enhanced (DCE) MRI and diffusion kurtosis imaging (DKI) in differentiating molecular subtypes of adult-type diffuse gliomas. The results showed that a combined evaluation of DCE-MRI and DKI parameters reveals the best prediction of high-grade vs. low-grade gliomas, IDH1/2 wildtype vs. mutated gliomas, and astrocytomas/glioblastomas vs. oligodendrogliomas. The aim was to explore the performance of dynamic contrast-enhanced (DCE) MRI and diffusion kurtosis imaging (DKI) in differentiating the molecular subtypes of adult-type gliomas. A multicenter MRI study with standardized imaging protocols, including DCE-MRI and DKI data of 81 patients with WHO grade 2–4 gliomas, was performed at six centers. The DCE-MRI and DKI parameter values were quantitatively evaluated in ROIs in tumor tissue and contralateral normal-appearing white matter. Binary logistic regression analyses were performed to differentiate between high-grade (HGG) vs. low-grade gliomas (LGG), IDH1/2 wildtype vs. mutated gliomas, and high-grade astrocytic tumors vs. high-grade oligodendrogliomas. Receiver operating characteristic (ROC) curves were generated for each parameter and for the regression models to determine the area under the curve (AUC), sensitivity, and specificity. Significant differences between tumor groups were found in the DCE-MRI and DKI parameters. A combination of DCE-MRI and DKI parameters revealed the best prediction of HGG vs. LGG (AUC = 0.954 (0.900–1.000)), IDH1/2 wildtype vs. mutated gliomas (AUC = 0.802 (0.702–0.903)), and astrocytomas/glioblastomas vs. oligodendrogliomas (AUC = 0.806 (0.700–0.912)) with the lowest Akaike information criterion. The combination of DCE-MRI and DKI seems helpful in predicting glioma types according to the 2021 World Health Organization's (WHO) classification. [ABSTRACT FROM AUTHOR]

Simple Summary: A 90-day mortality predictive model for curative gastric cancer resection based on the Spanish EURECCA Esophagogastric Cancer database was externally validated using the GASTRODATA registry. The externally validated model showed a modestly worse performance compared to the original model, nevertheless maintaining its discriminating ability in clinical practice. Background: Radical gastrectomy remains the main treatment for gastric cancer, despite its high mortality. A clinical predictive model of 90-day mortality (90DM) risk after gastric cancer surgery based on the Spanish EURECCA registry database was developed using a matching learning algorithm. We performed an external validation of this model based on data from an international multicenter cohort of patients. Methods: A cohort of patients from the European GASTRODATA database was selected. Demographic, clinical, and treatment variables in the original and validation cohorts were compared. The performance of the model was evaluated using the area under the curve (AUC) for a random forest model. Results: The validation cohort included 2546 patients from 24 European hospitals. The advanced clinical T- and N-category, neoadjuvant therapy, open procedures, total gastrectomy rates, and mean volume of the centers were significantly higher in the validation cohort. The 90DM rate was also higher in the validation cohort (5.6%) vs. the original cohort (3.7%). The AUC in the validation model was 0.716. Conclusion: The externally validated model for predicting the 90DM risk in gastric cancer patients undergoing gastrectomy with curative intent continues to be as useful as the original model in clinical practice. [ABSTRACT FROM AUTHOR]

Simple Summary: Predicting the survival of bladder cancer patients following cystectomy can offer valuable information for treatment planning, decision-making, patient counseling, and resource allocation. Our aim was to develop large language model (LLM)-aided multi-modal predictive models, based on clinical information and CT images. These models achieved performances comparable to those of multi-modal predictive models that rely on manually extracted clinical information. This study demonstrates the potential of employing LLMs to process medical data, and of integrating LLM-processed data into modeling for prognosis. Survival prediction post-cystectomy is essential for the follow-up care of bladder cancer patients. This study aimed to evaluate artificial intelligence (AI)-large language models (LLMs) for extracting clinical information and improving image analysis, with an initial application involving predicting five-year survival rates of patients after radical cystectomy for bladder cancer. Data were retrospectively collected from medical records and CT urograms (CTUs) of bladder cancer patients between 2001 and 2020. Of 781 patients, 163 underwent chemotherapy, had pre- and post-chemotherapy CTUs, underwent radical cystectomy, and had an available post-surgery five-year survival follow-up. Five AI-LLMs (Dolly-v2, Vicuna-13b, Llama-2.0-13b, GPT-3.5, and GPT-4.0) were used to extract clinical descriptors from each patient's medical records. As a reference standard, clinical descriptors were also extracted manually. Radiomics and deep learning descriptors were extracted from CTU images. The developed multi-modal predictive model, CRD, was based on the clinical (C), radiomics (R), and deep learning (D) descriptors. The LLM retrieval accuracy was assessed. The performances of the survival predictive models were evaluated using AUC and Kaplan–Meier analysis. For the 163 patients (mean age 64 ± 9 years; M:F 131:32), the LLMs achieved extraction accuracies of 74%~87% (Dolly), 76%~83% (Vicuna), 82%~93% (Llama), 85%~91% (GPT-3.5), and 94%~97% (GPT-4.0). For a test dataset of 64 patients, the CRD model achieved AUCs of 0.89 ± 0.04 (manually extracted information), 0.87 ± 0.05 (Dolly), 0.83 ± 0.06~0.84 ± 0.05 (Vicuna), 0.81 ± 0.06~0.86 ± 0.05 (Llama), 0.85 ± 0.05~0.88 ± 0.05 (GPT-3.5), and 0.87 ± 0.05~0.88 ± 0.05 (GPT-4.0). This study demonstrates the use of LLM model-extracted clinical information, in conjunction with imaging analysis, to improve the prediction of clinical outcomes, with bladder cancer as an initial example. [ABSTRACT FROM AUTHOR]

Simple Summary: Estimating the risk of postoperative complications is important for shared decision-making with the patient. This also helps multidisciplinary teams to plan preoperative management and postoperative care and predict duration of recovery. In this retrospective pilot study, we aim to evaluate the accuracy and reliability of the P-POSSUM and ACS-NSQIP surgical risk calculators in predicting postoperative complications in gynaecological–oncological (GO) robotic surgery (RS). We were able to demonstrate that the ACS-NSQIP risk tool showed 90% accuracy in prediction of five major complications and mortality. Purpose: In this retrospective pilot study, we aim to evaluate the accuracy and reliability of the P-POSSUM and ACS-NSQIP surgical risk calculators in predicting postoperative complications in gynaecological–oncological (GO) robotic surgery (RS). Methods: Retrospective data collection undertaken through a dedicated GO database and patient notes at a tertiary referral cancer centre. Following data lock with the actual post-op event/complication, the risk calculators were used to measure predictive scores for each patient. Baseline analysis of 153 patients, based on statistician advice, was undertaken to evaluate P-POSSUM and ACS-NSQIP validity and relevance in GO patients undergoing RS performed. Results: P-POSSUM reports on mortality and morbidity only; ACS-NSQIP reports some individual complications as well. ACS-NSQIP risk prediction was most accurate for venous thromboembolism (VTE) (area under the curve (AUC)-0.793) and pneumonia (AUC-0.657) and it showed 90% accuracy in prediction of five major complications (Brier score 0.01). Morbidity was much better predicted by ACS-NSQIP than by P-POSSUM (AUC-0.608 vs. AUC-0.551) with the same result in mortality prediction (Brier score 0.0000). Moreover, a statistically significant overestimation of morbidity has been shown by the P-POSSUM calculator (p = 0.018). Conclusions: Despite the limitations of this pilot study, the ACS-NSQIP risk calculator appears to be a better predictor of major complications and mortality, making it suitable for use by GO surgeons as an informed consent tool. Larger data collection and analyses are ongoing to validate this further. [ABSTRACT FROM AUTHOR]

Simple Summary: We investigated whether the baseline plasma cell-free DNA might help to differentiate malignant nodules from benign lesions observed in screening low-dose computed tomography (LDCT) examinations. Plasma cell-free DNA was determined before the first LDCT in 137 participants in the ITALUNG trial, including 29 with screen-detected malignant nodules (17 prevalent and 12 incident) and 108 with benign nodules. In subjects with prevalent lung cancers (LC), the radiological characteristics well differentiated the malignant nodule, and the cell-free DNA was markedly increased. A total of 75% of subjects with incident LC showed a baseline cell-free DNA ≥ 3.15 ng/mL, compared to 34% of subjects with benign nodules (p = 0.006). Moreover, the cell-free DNA correlated (p = 0.001) with the tumor growth measured with nodular volume doubling time. The baseline plasma cell-free DNA is an independent, potentially useful biomarker in the LC screening process and should be further investigated. The role of total plasma cell-free DNA (cfDNA) in lung cancer (LC) screening with low-dose computed tomography (LDCT) is uncertain. We hypothesized that cfDNA could support differentiation between malignant and benign nodules observed in LDCT. The baseline cfDNA was measured in 137 subjects of the ITALUNG trial, including 29 subjects with screen-detected LC (17 prevalent and 12 incident) and 108 subjects with benign nodules. The predictive capability of baseline cfDNA to differentiate malignant and benign nodules was compared to that of Lung-RADS classification and Brock score at initial LDCT (iLDCT). Subjects with prevalent LC showed both well-discriminating radiological characteristics of the malignant nodule (16 of 17 were classified as Lung-RADS 4) and markedly increased cfDNA (mean 18.8 ng/mL). The mean diameters and Brock scores of malignant nodules at iLDCT in subjects who were diagnosed with incident LC were not different from those of benign nodules. However, 75% (9/12) of subjects with incident LC showed a baseline cfDNA ≥ 3.15 ng/mL, compared to 34% (37/108) of subjects with benign nodules (p = 0.006). Moreover, baseline cfDNA was correlated (p = 0.001) with tumor growth, measured with volume doubling time. In conclusion, increased baseline cfDNA may help to differentiate subjects with malignant and benign nodules at LDCT. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurate pre-operative surgical risk predictions form the foundation of pre-operative counseling and informed consent. There are currently no validated risk calculators that are able to accurately predict post-operative complications for women undergoing gynecological cancer surgery in both high- and low-middle-income healthcare settings. Using the dataset from the international GO SOAR database, we present a novel artificial intelligence surgical risk calculator capable of accurately predicting the risk of complications associated with gynecological cancer surgery. The GO SOAR surgical risk calculator uses readily available pre-operative data available across all-income healthcare settings, ensuring benefits to women globally. The medical complexity of surgical patients is increasing, and surgical risk calculators are crucial in providing high-value, patient-centered surgical care. However, pre-existing models are not validated to accurately predict risk for major gynecological oncology surgeries, and many are not generalizable to low- and middle-income country settings (LMICs). The international GO SOAR database dataset was used to develop a novel predictive surgical risk calculator for post-operative morbidity and mortality following gynecological surgery. Fifteen candidate features readily available pre-operatively across both high-income countries (HICs) and LMICs were selected. Predictive modeling analyses using machine learning methods and linear regression were performed. The area-under-the-receiver-operating characteristic curve (AUROC) was calculated to assess overall discriminatory performance. Neural networks (AUROC 0.94) significantly outperformed other models (p < 0.001) for evaluating the accuracy of prediction across three groups, i.e., minor morbidity (Clavien–Dindo I-II), major morbidity (Clavien–Dindo III-V), and no morbidity. Logistic-regression modeling outperformed the clinically established SORT model in predicting mortality (AUROC 0.66 versus 0.61, p < 0.001). The GO SOAR surgical risk prediction model is the first that is validated for use in patients undergoing gynecological surgery. Accurate surgical risk predictions are vital within the context of major cytoreduction surgery, where surgery and its associated complications can diminish quality-of-life and affect long-term cancer survival. A model that requires readily available pre-operative data, irrespective of resource setting, is crucial to reducing global surgical disparities. [ABSTRACT FROM AUTHOR]

Simple Summary: This research aims to evaluate the effectiveness of a machine learning algorithm, XGBoost, in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). The study uses clinical and imaging data from patients discussed at a multidisciplinary tumor board. The findings suggest that the algorithm can accurately predict all eight treatment recommendations made by the board, potentially aiding clinical decision-making in settings lacking subspecialty expertise. This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise. [ABSTRACT FROM AUTHOR]

Simple Summary: We developed an attention-based whole slide image (WSI)-level classification deep learning model employing surgically and endoscopically resected specimens to predict LNM in T1 CRC. Our AI model with H&E-stained WSIs and without annotations showed good performance power with the validation of an independent cohort in a single center. The area under the curve of our model was 0.781–0.824, higher than that of previous artificial intelligence (AI) studies with only WSIs. Our AI model, which showed the highest sensitivity (92.9%), reduced unnecessary additional surgery by 14.2% more than using the current JSCCR guidelines (68.3% vs. 82.5%). This revealed the feasibility of using an AI model with only H&E-stained WSIs to predict LNM in T1 CRC. According to the current guidelines, additional surgery is performed for endoscopically resected specimens of early colorectal cancer (CRC) with a high risk of lymph node metastasis (LNM). However, the rate of LNM is 2.1–25.0% in cases treated endoscopically followed by surgery, indicating a high rate of unnecessary surgeries. Therefore, this study aimed to develop an artificial intelligence (AI) model using H&E-stained whole slide images (WSIs) without handcrafted features employing surgically and endoscopically resected specimens to predict LNM in T1 CRC. To validate with an independent cohort, we developed a model with four versions comprising various combinations of training and test sets using H&E-stained WSIs from endoscopically (400 patients) and surgically resected specimens (881 patients): Version 1, Train and Test: surgical specimens; Version 2, Train and Test: endoscopic and surgically resected specimens; Version 3, Train: endoscopic and surgical specimens and Test: surgical specimens; Version 4, Train: endoscopic and surgical specimens and Test: endoscopic specimens. The area under the curve (AUC) of the receiver operating characteristic curve was used to determine the accuracy of the AI model for predicting LNM with a 5-fold cross-validation in the training set. Our AI model with H&E-stained WSIs and without annotations showed good performance power with the validation of an independent cohort in a single center. The AUC of our model was 0.758–0.830 in the training set and 0.781–0.824 in the test set, higher than that of previous AI studies with only WSI. Moreover, the AI model with Version 4, which showed the highest sensitivity (92.9%), reduced unnecessary additional surgery by 14.2% more than using the current guidelines (68.3% vs. 82.5%). This revealed the feasibility of using an AI model with only H&E-stained WSIs to predict LNM in T1 CRC. [ABSTRACT FROM AUTHOR]

Simple Summary: In the context of endometrial cancer, molecular classification is becoming increasingly significant as the molecular class determines appropriate treatments and the prognosis. However, performing clinical testing for molecular classification in a large number of patients entails significant financial and time costs. Therefore, there is a need to develop a substantial molecular profile screening method for endometrial cancers. The objective of this study was to explore whether the molecular classification of endometrial cancer could be predicted from digital images of hematoxylin and eosin (H&E)-stained slides using deep learning as a screening tool. After making adjustments to the training data set and hyperparameters, we confirmed the feasibility of estimating the mismatch repair status from histological digital images of endometrial cancer. Deep learning was found to be effective for predicting one aspect of the molecular classification from H&E-stained histological digital images. The application of deep learning algorithms to predict the molecular profiles of various cancers from digital images of hematoxylin and eosin (H&E)-stained slides has been reported in recent years, mainly for gastric and colon cancers. In this study, we investigated the potential use of H&E-stained endometrial cancer slide images to predict the associated mismatch repair (MMR) status. H&E-stained slide images were collected from 127 cases of the primary lesion of endometrial cancer. After digitization using a Nanozoomer virtual slide scanner (Hamamatsu Photonics), we segmented the scanned images into 5397 tiles of 512 × 512 pixels. The MMR proteins (PMS2, MSH6) were immunohistochemically stained, classified into MMR proficient/deficient, and annotated for each case and tile. We trained several neural networks, including convolutional and attention-based networks, using tiles annotated with the MMR status. Among the tested networks, ResNet50 exhibited the highest area under the receiver operating characteristic curve (AUROC) of 0.91 for predicting the MMR status. The constructed prediction algorithm may be applicable to other molecular profiles and useful for pre-screening before implementing other, more costly genetic profiling tests. [ABSTRACT FROM AUTHOR]

Simple Summary: Early characterization of the isocitrate dehydrogenase (IDHIDH) gene mutation status of glioma is crucial for personalized decision making and prognosis in clinical neurooncological treatment. Based on the known differences in energy metabolism between IDHIDH-mutated and IDHIDH-wildtype gliomas, we assessed physio-metabolic magnetic resonance imaging-based measures along with machine learning for potential reliable presurgical characterization of IDHIDH gene status. Traditional machine learning algorithms and simple deep learning models trained in analyzing physio-metabolic parameters demonstrated the best performance in classifying the IDHIDH gene status of gliomas in independent internal testing. In contrast, external testing revealed that traditional machine learning models trained on clinical MRI data had higher accuracy compared to physio-metabolic algorithms, reflecting differences in data acquisition methodology between the two sites. Our results outline the necessity of independent internal and external testing, thus calling for standardized and robust protocols for clinical MRI-driven AI applications. The mutational status of the isocitrate dehydrogenase (IDH) gene plays a key role in the treatment of glioma patients because it is known to affect energy metabolism pathways relevant to glioma. Physio-metabolic magnetic resonance imaging (MRI) enables the non-invasive analysis of oxygen metabolism and tissue hypoxia as well as associated neovascularization and microvascular architecture. However, evaluating such complex neuroimaging data requires computational support. Traditional machine learning algorithms and simple deep learning models were trained with radiomic features from clinical MRI (cMRI) or physio-metabolic MRI data. A total of 215 patients (first center: 166 participants + 16 participants for independent internal testing of the algorithms versus second site: 33 participants for independent external testing) were enrolled using two different physio-metabolic MRI protocols. The algorithms trained with physio-metabolic data demonstrated the best classification performance in independent internal testing: precision, 91.7%; accuracy, 87.5%; area under the receiver operating curve (AUROC), 0.979. In external testing, traditional machine learning models trained with cMRI data exhibited the best IDH classification results: precision, 84.9%; accuracy, 81.8%; and AUROC, 0.879. The poor performance for the physio-metabolic MRI approach appears to be explainable by site-dependent differences in data acquisition methodologies. The physio-metabolic MRI approach potentially supports reliable classification of IDH gene status in the presurgical stage of glioma patients. However, non-standardized protocols limit the level of evidence and underlie the need for a reproducible framework of data acquisition techniques. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is the main cause of cancer-related deaths among women globally. It clearly shows it is essential to find a useful marker, which could have a beneficial influence on the prediction of cancer-related events and give more information about the possible outcomes in the early stage of the disease. This is the first study that presents advanced oxidation protein products as a potentially valuable biomarker for monitoring the course of breast cancer treatment and as a predictor of recurrence and cancer-related mortality. The study shows also the relationship between oxidative protein damage in breast cancer patients and excessive angiogenic processes. Breast cancer (BrC) is a highly prevalent tumour among women. The high incidence and mortality rate of BrC prompts researchers to search for new markers that will provide information on the possible impact of the therapy on the risk of cancer-related events. This study aimed to investigate whether the level of advanced oxidation protein products (AOPPs) may have a potential impact on disease-free (DFS) and overall survival (OS) in BrC patients with early-stage cancer. Additionally, we tried to assess the relationship between AOPPs and angiogenic parameters. In this study, the pre- and post-treatment AOPP levels were examined in the serum of 70 newly diagnosed BrC women. The receiver operating characteristic curve identified pre- and post-treatment AOPPs to be above 9.37 μM and 10.39 μM, respectively, as the best cut-off values to predict the risk of cancer relapse. Additionally, Kaplan–Meier survival analysis indicated that pre- and post-treatment AOPPs above 9.37 μM and 10.39 μM were associated with significantly poorer OS. The uni- and multivariate Cox regression analysis highlighted that lower levels of pre- and post-treatment AOPPs were associated with a longer duration without relapse or cancer-related death. A positive correlation between concentrations of pre-treatment AOPPs and vascular endothelial growth factor A, and negative correlations with levels of soluble forms of vascular endothelial growth factor receptor type 1 and 2, were found. In conclusion, AOPPs appear to have an important role in predicting cancer-related events and may potentially serve as a simple prognostic marker in clinical practice. [ABSTRACT FROM AUTHOR]

Simple Summary: An atypical teratoid/rhabdoid tumor (AT/RT) is an uncommon, yet aggressive, pediatric central nervous system neoplasm. Our prognostic study included 316 Surveillance, Epidemiology, and End Results (SEER) repository participants and 27 external validation patients. The incidence of AT/RT consistently increased between 2000 and 2020. Age, SEER stage, tumor size, surgery, chemotherapy, and radiotherapy are closely related to the prognosis of AT/RT. Triple therapy resulted in discernibly enhanced OS and CSS. The most common mutations in AT/RT identified using the COSMIC database were SMARCB1, BRAF, SMARCA4, NF2, and NRAS. Our study identified the clinical determinants of prognosis in patients with AT/RT and mapped the genetic mutation landscape. The prediction model that we devised may offer a valuable tool to address existing clinical challenges. Additionally, analysis based on mutational genomics will facilitate the research regarding molecular-targeted drugs. Background: An atypical teratoid/rhabdoid tumor (AT/RT) is an uncommon and aggressive pediatric central nervous system neoplasm. However, a universal clinical consensus or reliable prognostic evaluation system for this malignancy is lacking. Our study aimed to develop a risk model based on comprehensive clinical data to assist in clinical decision-making. Methods: We conducted a retrospective study by examining data from the Surveillance, Epidemiology, and End Results (SEER) repository, spanning 2000 to 2019. The external validation cohort was sourced from the Children's Hospital Affiliated to Chongqing Medical University, China. To discern independent factors affecting overall survival (OS) and cancer-specific survival (CSS), we applied Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest (RF) regression analyses. Based on these factors, we structured nomogram survival predictions and initiated a dynamic online risk-evaluation system. To contrast survival outcomes among diverse treatments, we used propensity score matching (PSM) methodology. Molecular data with the most common mutations in AT/RT were extracted from the Catalogue of Somatic Mutations in Cancer (COSMIC) database. Results: The annual incidence of AT/RT showed an increasing trend (APC, 2.86%; 95% CI:0.75–5.01). Our prognostic study included 316 SEER database participants and 27 external validation patients. The entire group had a median OS of 18 months (range 11.5 to 24 months) and median CSS of 21 months (range 11.7 to 29.2). Evaluations involving C-statistics, DCA, and ROC analysis underscored the distinctive capabilities of our prediction model. An analysis via PSM highlighted that individuals undergoing triple therapy (integrating surgery, radiotherapy, and chemotherapy) had discernibly enhanced OS and CSS. The most common mutations of AT/RT identified in the COSMIC database were SMARCB1, BRAF, SMARCA4, NF2, and NRAS. Conclusions: In this study, we devised a predictive model that effectively gauges the prognosis of AT/RT and briefly analyzed its genomic features, which might offer a valuable tool to address existing clinical challenges. [ABSTRACT FROM AUTHOR]

Simple Summary: In national hospital databases, certain prognostic factors cannot be taken into account. Our objective was to estimate the performance of two models based on the Epithor clinical database and the French hospital database. The performance of the models was assessed with the Brier score, the area under the receiver operating characteristic (AUC ROC) curve, and the calibration of the model. For the Epithor and hospital databases, the training dataset (70% of the initial data) included 10,516 patients (with, respectively, 227 (2.16%) and 283 (2.7%) deaths) and the validation dataset (30% of the initial data) included 4507 patients (with, respectively, 93 (2%) and 119 (2.64%) deaths). The Brier score values were similar in the models of the two databases. For validation data, the AUC ROC curve was 0.73 [0.68–0.78] for Epithor and 0.8 [0.76–0.84] for the hospital database. The slope of the calibration plot was less than 1 for the two databases. This work showed that the performance of a model developed from a national hospital database is nearly as good as a performance obtained with Epithor, but it lacks crucial clinical variables. In national hospital databases, certain prognostic factors cannot be taken into account. The main objective was to estimate the performance of two models based on two databases: the Epithor clinical database and the French hospital database. For each of the two databases, we randomly sampled a training dataset with 70% of the data and a validation dataset with 30%. The performance of the models was assessed with the Brier score, the area under the receiver operating characteristic (AUC ROC) curve and the calibration of the model. For Epithor and the hospital database, the training dataset included 10,516 patients (with resp. 227 (2.16%) and 283 (2.7%) deaths) and the validation dataset included 4507 patients (with resp. 93 (2%) and 119 (2.64%) deaths). A total of 15 predictors were selected in the models (including FEV1, body mass index, ASA score and TNM stage for Epithor). The Brier score values were similar in the models of the two databases. For validation data, the AUC ROC curve was 0.73 [0.68–0.78] for Epithor and 0.8 [0.76–0.84] for the hospital database. The slope of the calibration plot was less than 1 for the two databases. This work showed that the performance of a model developed from a national hospital database is nearly as good as a performance obtained with Epithor, but it lacks crucial clinical variables such as FEV1, ASA score, or TNM stage. [ABSTRACT FROM AUTHOR]

Simple Summary: The prognosis for patients with glioblastoma (GBM) remains dismal despite advances in tumor detection and treatment. The aim of our retrospective study was to develop a multiparametric model incorporating baseline MRI imaging, histopathological biomarkers, and demographic data to predict prognosis in patients with GBM. A training model was developed with 116 patients and validated with an external cohort of 40 patients. Three significant variables were identified as independent predictors of survival ≥ 18 months: radiomics, age, and MGMT status. Background: Clinical, histopathological, and imaging variables have been associated with prognosis in patients with glioblastoma (GBM). We aimed to develop a multiparametric radiogenomic model incorporating MRI texture features, demographic data, and histopathological tumor biomarkers to predict prognosis in patients with GBM. Methods: In this retrospective study, patients were included if they had confirmed diagnosis of GBM with histopathological biomarkers and pre-operative MRI. Tumor segmentation was performed, and texture features were extracted to develop a predictive radiomic model of survival (<18 months vs. ≥18 months) using multivariate analysis and Least Absolute Shrinkage and Selection Operator (LASSO) regularization to reduce the risk of overfitting. This radiomic model in combination with clinical and histopathological data was inserted into a backward stepwise logistic regression model to assess survival. The diagnostic performance of this model was reported for the training and external validation sets. Results: A total of 116 patients were included for model development and 40 patients for external testing validation. The diagnostic performance (AUC/sensitivity/specificity) of the radiomic model generated from seven texture features in determination of ≥18 months survival was 0.71/69.0/70.3. Three variables remained as independent predictors of survival, including radiomics (p = 0.004), age (p = 0.039), and MGMT status (p = 0.025). This model yielded diagnostic performance (AUC/sensitivity/specificity) of 0.77/81.0/66.0 (training) and 0.89/100/78.6 (testing) in determination of survival ≥ 18 months. Conclusions: Results show that our radiogenomic model generated from radiomic features at baseline MRI, age, and MGMT status can predict survival ≥ 18 months in patients with GBM. [ABSTRACT FROM AUTHOR]

Simple Summary: This study explored the predictive value of neutrophils and neutrophil-related biomarkers as auxiliary diagnosis biomarkers of NSCLC in an ongoing large cohort. IL-6 and IL-1RA were identified as independent risk factors for NSCLC. These findings can improve the predictive performance beyond epidemiological variables and classic neutrophil-related biomarkers in identifying NSCLC. Background: Recent studies have revealed that neutrophils play a crucial role in cancer progression. This study aimed to explore the diagnostic value of neutrophil-related biomarkers for non-small-cell lung cancer (NSCLC). Methods: We initially assessed the associations between classic neutrophil-related biomarkers (neutrophil-to-lymphocyte ratio (NLR), absolute neutrophil counts (NEU), absolute lymphocyte counts (LYM)) and NSCLC in 3942 cases and 6791 controls. Then, we measured 11 novel neutrophil-related biomarkers via Luminex Assays in 132 cases and 66 controls, individually matching on sex and age (±5 years), and evaluated their associations with NSCLC risk. We also developed the predictive models by sequentially adding variables of interest and assessed model improvement. Results: Interleukin-6 (IL-6) (odds ratio (OR) = 10.687, 95% confidence interval (CI): 3.875, 29.473) and Interleukin 1 Receptor Antagonist (IL-1RA) (OR = 8.113, 95% CI: 3.182, 20.689) shows strong associations with NSCLC risk after adjusting for body mass index, smoking status, NLR, and carcinoembryonic antigen. Adding the two identified biomarkers to the predictive model significantly elevated the model performance from an area under the receiver operating characteristic curve of 0.716 to 0.851 with a net reclassification improvement of 97.73%. Conclusions: IL-6 and IL-1RA were recognized as independent risk factors for NSCLC, improving the predictive performance of the model in identifying disease. [ABSTRACT FROM AUTHOR]

Simple Summary: Lymphovascular invasion (LVI) serves as a crucial predictor in gastric cancer, indicating an increased likelihood of lymph node spread and poorer patient outcomes. Detecting LVI(+) within gastric cancer histopathology presents challenges due to its elusive nature, leading to the proposal of a deep learning-based detection method using H&E-stained whole-slide images. Remarkably, both the classification and detection models demonstrated superior performance, and their ensemble exhibited outstanding predictive capabilities in identifying LVI areas. This innovative approach holds promise in precision medicine, potentially streamlining examinations and reducing discrepancies among pathologists. Lymphovascular invasion (LVI) is one of the most important prognostic factors in gastric cancer as it indicates a higher likelihood of lymph node metastasis and poorer overall outcome for the patient. Despite its importance, the detection of LVI(+) in histopathology specimens of gastric cancer can be a challenging task for pathologists as invasion can be subtle and difficult to discern. Herein, we propose a deep learning-based LVI(+) detection method using H&E-stained whole-slide images. The ConViT model showed the best performance in terms of both AUROC and AURPC among the classification models (AUROC: 0.9796; AUPRC: 0.9648). The AUROC and AUPRC of YOLOX computed based on the augmented patch-level confidence score were slightly lower (AUROC: −0.0094; AUPRC: −0.0225) than those of the ConViT classification model. With weighted averaging of the patch-level confidence scores, the ensemble model exhibited the best AUROC, AUPRC, and F1 scores of 0.9880, 0.9769, and 0.9280, respectively. The proposed model is expected to contribute to precision medicine by potentially saving examination-related time and labor and reducing disagreements among pathologists. [ABSTRACT FROM AUTHOR]

Simple Summary: Prostate cancer (PCa) is one of the leading causes of mortality for men worldwide. PCa aggressiveness affects the patient's prognosis, with less aggressive tumors, i.e., Grade Group (GG) 1 and 2, having lower mortality and better outcomes. For this reason, the aim of this study is to distinguish between GG ≤ 2 and ≥3 PCa using an automatic and noninvasive approach based on artificial intelligence methods. The results obtained are promising, as the system achieved robust results on a multicenter external dataset. If further validated, this approach, combined with the expert knowledge of urologists, could help identify PCa patients who have a better prognosis and may benefit from less invasive treatments. In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa. [ABSTRACT FROM AUTHOR]

Simple Summary: The rate of concurrent endometrial cancer (EC) in women with atypical endometrial hyperplasia (AEH) is not negligible. Furthermore, among women with EC, about 12% may have a high-risk disease requiring lymph node status assessment. Given that endometrial sampling cannot exclude EC in women with AEH, knowing variables that increase the risk of malignancy can be helpful in clinical practice. Some patient characteristics were associated with this occurrence, representing possible risk factors on which to adjust treatment planning. No prediction models with internal validation showed the impact of patient characteristics in predicting EC after a preoperative diagnosis of AEH. The present study, using regressions and artificial neural networks, found recurrent patient characteristics in women with EC. However, they likely do not contain good/optimal discriminating information. Future predictive models should include other individual factors (e.g., genotypic variables) to move toward more personalized medicine. Background: The rate of concurrent endometrial cancer (EC) in atypical endometrial hyperplasia (AEH) can be as high as 40%. Some patient characteristics showed associations with this occurrence. However, their real predictive power with related validation has yet to be discovered. The present study aimed to assess the performance of various models based on patient characteristics in predicting EC in women with AEH. Methods: This is a retrospective multi-institutional study including women with AEH undergoing definitive surgery. The women were divided according to the final histology (EC vs. no-EC). The available cases were divided into a training and validation set. Using k-fold cross-validation, we built many predictive models, including regressions and artificial neural networks (ANN). Results: A total of 193/629 women (30.7%) showed EC at hysterectomy. A total of 26/193 (13.4%) women showed high-risk EC. Regression and ANN models showed a prediction performance with a mean area under the curve of 0.65 and 0.75 on the validation set, respectively. Among the best prediction models, the most recurrent patient characteristics were age, body mass index, Lynch syndrome, diabetes, and previous breast cancer. None of these independent variables showed associations with high-risk diseases in women with EC. Conclusions: Patient characteristics did not show satisfactory performance in predicting EC in AEH. Risk stratification in AEH based mainly on patient characteristics may be clinically unsuitable. [ABSTRACT FROM AUTHOR]

Simple Summary: Head and neck cancer is the seventh-most prevalent cancer worldwide. Despite advances in treatment, many patients suffer from chemoradiation-induced oral mucositis and dysphagia, affecting both treatment outcome and quality of life. Accurate prediction of the severity of toxicities is important for optimizing management and improving patient outcomes. The aim of this scoping review was to provide recommendations for the improvement in predictive models for oral mucositis and dysphagia. This was achieved by comprehensively mapping the landscape of reported predictors and critically evaluating the performance, methodology, and reporting of predictive models for these conditions. Implementation of these improvements is desirable to enable the early detection of patients at high risk of severe toxicity, thereby offering opportunities for preemptive care, intensified support, and, ultimately, improved patient outcomes. Despite advances in head and neck cancer treatment, virtually all patients experience chemoradiation-induced toxicities. Oral mucositis (OM) and dysphagia are among the most prevalent and have a systemic impact on patients, hampering treatment outcome and harming quality of life. Accurate prediction of severe cases is crucial for improving management strategies and, ultimately, patient outcomes. This scoping review comprehensively maps the reported predictors and critically evaluates the performance, methodology, and reporting of predictive models for these conditions. A total of 174 studies were identified from database searches, with 73 reporting OM predictors, 97 reporting dysphagia predictors, and 4 reporting both OM and dysphagia predictors. These predictors included patient demographics, tumor classification, chemoradiotherapy regimen, radiation dose to organs-at-risk, genetic factors, and results of clinical laboratory tests. Notably, many studies only conducted univariate analysis or focused exclusively on certain predictor types. Among the included studies, numerous predictive models were reported: eight for acute OM, five for acute dysphagia, and nine for late dysphagia. The area under the receiver operating characteristic curve (AUC) ranged between 0.65 and 0.81, 0.60 and 0.82, and 0.70 and 0.85 for acute oral mucositis, acute dysphagia, and late dysphagia predictive models, respectively. Several areas for improvement were identified, including the need for external validation with sufficiently large sample sizes, further standardization of predictor and outcome definitions, and more comprehensive reporting to facilitate reproducibility. [ABSTRACT FROM AUTHOR]

Simple Summary: Two-dimensional shear wave elastography (2D-SWE) has demonstrated predictive value for symptomatic post-hepatectomy liver failure (PHLF) in hepatocellular carcinoma (HCC). Our aim was to develop and validate an interpretable radiomics model based on 2D-SWE for predicting symptomatic PHLF in patients undergoing liver resection for HCC. We proposed an interpretable clinical–radiomics model based on both multi-patch radiomics and clinical features, which showed an AUC of 0.822 in the test cohort, higher than the clinical model (AUC: 0.684, p = 0.007), radiomics model (AUC: 0.784, p = 0.415), end-stage liver disease (MELD) score (AUC: 0.529, p < 0.001), and albumin–bilirubin (ALBI) score (AUC: 0.644, p = 0.016). The SHAP analysis showed that first-order radiomics features were the most important features for PHLF prediction. The clinical–radiomics model is useful for predicting symptomatic PHLF in HCC with high model interpretability, which may serve as a useful tool for therapeutic decision making to improve perioperative management. Objective: The aim of this study was to develop and validate an interpretable radiomics model based on two-dimensional shear wave elastography (2D-SWE) for symptomatic post-hepatectomy liver failure (PHLF) prediction in patients undergoing liver resection for hepatocellular carcinoma (HCC). Methods: A total of 345 consecutive patients were enrolled. A five-fold cross-validation was performed during training, and the models were evaluated in the independent test cohort. A multi-patch radiomics model was established based on the 2D-SWE images for predicting symptomatic PHLF. Clinical features were incorporated into the models to train the clinical–radiomics model. The radiomics model and the clinical–radiomics model were compared with the clinical model comprising clinical variables and other clinical predictive indices, including the model for end-stage liver disease (MELD) score and albumin–bilirubin (ALBI) score. Shapley Additive exPlanations (SHAP) was used for post hoc interpretability of the radiomics model. Results: The clinical–radiomics model achieved an AUC of 0.867 (95% CI 0.787–0.947) in the five-fold cross-validation, and this score was higher than that of the clinical model (AUC: 0.809; 95% CI: 0.715–0.902) and the radiomics model (AUC: 0.746; 95% CI: 0.681–0.811). The clinical–radiomics model showed an AUC of 0.822 in the test cohort, higher than that of the clinical model (AUC: 0.684, p = 0.007), radiomics model (AUC: 0.784, p = 0.415), MELD score (AUC: 0.529, p < 0.001), and ALBI score (AUC: 0.644, p = 0.016). The SHAP analysis showed that the first-order radiomics features, including first-order maximum 64 × 64, first-order 90th percentile 64 × 64, and first-order 10th percentile 32 × 32, were the most important features for PHLF prediction. Conclusion: An interpretable clinical–radiomics model based on 2D-SWE and clinical variables can help in predicting symptomatic PHLF in HCC. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, we built clinical- and radiomics-based models to predict lesions/patients at low risk based on a combined clinical-genomic classification system. Eighty-three multi-parametric MRI exams from 78 men were analyzed. Several models for lesion classification were built using a minimal clinical variables subset and radiomic features from the lesion and normal tissues. The models were also evaluated for patient classification. In all cases, the radiomic features improved the performance. To the best of our knowledge, this is the first study to demonstrate that machine learning radiomics-based models can predict patients' risk using combined clinical-genomic classification. The utilization of multi-parametric MRI (mpMRI) in clinical decisions regarding prostate cancer patients' management has recently increased. After biopsy, clinicians can assess risk using National Comprehensive Cancer Network (NCCN) risk stratification schema and commercially available genomic classifiers, such as Decipher. We built radiomics-based models to predict lesions/patients at low risk prior to biopsy based on an established three-tier clinical-genomic classification system. Radiomic features were extracted from regions of positive biopsies and Normally Appearing Tissues (NAT) on T2-weighted and Diffusion-weighted Imaging. Using only clinical information available prior to biopsy, five models for predicting low-risk lesions/patients were evaluated, based on: 1: Clinical variables; 2: Lesion-based radiomic features; 3: Lesion and NAT radiomics; 4: Clinical and lesion-based radiomics; and 5: Clinical, lesion and NAT radiomic features. Eighty-three mpMRI exams from 78 men were analyzed. Models 1 and 2 performed similarly (Area under the receiver operating characteristic curve were 0.835 and 0.838, respectively), but radiomics significantly improved the lesion-based performance of the model in a subset analysis of patients with a negative Digital Rectal Exam (DRE). Adding normal tissue radiomics significantly improved the performance in all cases. Similar patterns were observed on patient-level models. To the best of our knowledge, this is the first study to demonstrate that machine learning radiomics-based models can predict patients' risk using combined clinical-genomic classification. [ABSTRACT FROM AUTHOR]

Simple Summary: The prediction model established based on preoperative MRI radiomics in this study can basically realize the prospective, non-invasive, and accurate diagnosis of diffuse astrocytic glioma, IDH wild-type, with molecular features of glioblastoma, WHO grade 4 (DAG-G), which is of great significance to help optimize the treatment plan for such patients, including expanding the extent of surgery and actively administering radiotherapy, targeted therapy, or other treatments after surgery, so as to fundamentally maximize the prognosis of patients. Purpose: In 2021, the WHO central nervous system (CNS) tumor classification criteria added the diagnosis of diffuse astrocytic glioma, IDH wild-type, with molecular features of glioblastoma, WHO grade 4 (DAG-G). DAG-G may exhibit the aggressiveness and malignancy of glioblastoma (GBM) despite the lower histological grade, and thus a precise preoperative diagnosis can help neurosurgeons develop more refined individualized treatment plans. This study aimed to establish a predictive model for the non-invasive identification of DAG-G based on preoperative MRI radiomics. Patients and Methods: Patients with pathologically confirmed glioma in Huashan Hospital, Fudan University, between September 2019 and July 2021 were retrospectively analyzed. Furthermore, two external validation datasets from Wuhan Union Hospital and Xuzhou Cancer Hospital were also utilized to verify the reliability and accuracy of the prediction model. Two regions of interest (ROI) were delineated on the preoperative MRI images of the patients using the semi-automatic tool ITK-SNAP (version 4.0.0), which were named the maximum anomaly region (ROI1) and the tumor region (ROI2), and Pyradiomics 3.0 was applied for feature extraction. Feature selection was performed using a least absolute shrinkage and selection operator (LASSO) filter and a Spearman correlation coefficient. Six classifiers, including Gauss naive Bayes (GNB), K-nearest neighbors (KNN), Random forest (RF), Adaptive boosting (AB), and Support vector machine (SVM) with linear kernel and multilayer perceptron (MLP), were used to build the prediction models, and the prediction performance of the six classifiers was evaluated by fivefold cross-validation. Moreover, the performance of prediction models was evaluated using area under the curve (AUC), precision (PRE), and other metrics. Results: According to the inclusion and exclusion criteria, 172 patients with grade 2–3 astrocytoma were finally included in the study, and a total of 44 patients met the diagnosis of DAG-G. In the prediction task of DAG-G, the average AUC of GNB classifier was 0.74 ± 0.07, that of KNN classifier was 0.89 ± 0.04, that of RF classifier was 0.96 ± 0.03, that of AB classifier was 0.97 ± 0.02, that of SVM classifier was 0.88 ± 0.05, and that of MLP classifier was 0.91 ± 0.03, among which, AB classifier achieved the best prediction performance. In addition, the AB classifier achieved AUCs of 0.91 and 0.89 in two external validation datasets obtained from Wuhan Union Hospital and Xuzhou Cancer Hospital, respectively. Conclusions: The prediction model constructed based on preoperative MRI radiomics established in this study can basically realize the prospective, non-invasive, and accurate diagnosis of DAG-G, which is of great significance to help further optimize treatment plans for such patients, including expanding the extent of surgery and actively administering radiotherapy, targeted therapy, or other treatments after surgery, to fundamentally maximize the prognosis of patients. [ABSTRACT FROM AUTHOR]

Simple Summary: Systemic inflammatory markers are useful methods to predict the prognosis of colorectal cancer patients after surgeries. The Naples prognostic score is a useful predictive scoring system that reflects a patient's inflammatory and nutritional status. In this study, the postoperative Naples prognostic score showed high accuracy in predicting survival after curative resection in stage II–III colorectal cancer patients compared with preoperative inflammatory markers. Background: The Naples prognostic score (NPS) is a scoring system that reflects a patient's systemic inflammatory and nutritional status. This study aimed to evaluate whether postoperative NPS is effective in assessing the prognosis of stage II–III colorectal cancer (CRC) patients compared with preoperative NPS. Methods: Between 2005 and 2012, a total of 164 patients diagnosed with stage II–III CRC, who underwent curative resection followed by adjuvant chemotherapy, were divided into two groups: Group 0–1 (NPS = 0–2) and Group 2 (NPS = 3 or 4). Preoperative NPS was calculated based on the results before surgeries, and postoperative NPS was assessed using the results obtained before adjuvant chemotherapy. Results: The overall survival of Group 0–1 was higher than that of Group 2 in both pre- and postoperative NPS assessments. According to the ROC curve analysis, the Area Under the Curve (AUC) ratio for postoperative NPS was 0.64, compared with 0.57 for preoperative NPS, 0.52 for the preoperative neutrophil–lymphocyte ratio (p = 0.032), and 0.51 for the preoperative platelet–lymphocyte ratio (p = 0.027). Conclusions: Postoperative NPS is effective in predicting the prognosis of stage II–III CRC patients who underwent curative resection followed by adjuvant chemotherapy. The use of NPS could be beneficial in evaluating the prognosis of CRC patients after surgeries. [ABSTRACT FROM AUTHOR]

Simple Summary: Given the variable aggressiveness of PCa, patients with indolent PCa do not require intervention, but rather require active surveillance and close lifelong follow-up, while those with invasive PCa require surgery, various types of radiation therapy, androgen-deprivation therapy (ADT), or multimodal treatment. Hence, it is critical to accurately distinguish indolent from invasive PCa for prognosis evaluation and treatment decision-making. The aim of the present study was to investigate the value of MR radiomics feature-based machine learning (ML) models in predicting the Ki67 index and Gleason grade group (GGG) of PCa. Biparametric magnetic resonance imaging (bpMRI) radiomics-based ML models to predict immuno-histochemically-determined Ki67 expression and the GGG demonstrated the ability to identify aggressive PCa. A preliminary exploration was performed in the conjoint analysis, laying the theoretical foundation for models predicting two or more variables; such models are expected to provide more comprehensive pathological information and provide valuable guidance for clinical decision-making in a noninvasive, synchronous, and objective manner. Purpose: The Ki67 index and the Gleason grade group (GGG) are vital prognostic indicators of prostate cancer (PCa). This study investigated the value of biparametric magnetic resonance imaging (bpMRI) radiomics feature-based machine learning (ML) models in predicting the Ki67 index and GGG of PCa. Methods: A total of 122 patients with pathologically proven PCa who had undergone preoperative MRI were retrospectively included. Radiomics features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. Then, recursive feature elimination (RFE) was applied to remove redundant features. ML models for predicting Ki67 expression and GGG were constructed based on bpMRI and different algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), and K-nearest neighbor (KNN). The performances of different models were evaluated with receiver operating characteristic (ROC) analysis. In addition, a joint analysis of Ki67 expression and GGG was performed by assessing their Spearman correlation and calculating the diagnostic accuracy for both indices. Results: The ML model based on LR and ADC + T2 (LR_ADC + T2, AUC = 0.8882) performed best in predicting Ki67 expression, and ADC_wavelet-LHH_firstorder_Maximum had the highest feature weighting. The SVM_DWI + T2 (AUC = 0.9248) performed best in predicting GGG, and DWI_wavelet HLL_glcm_SumAverage had the highest feature weighting. The Ki67 and GGG exhibited a weak positive correlation (r = 0.382, p < 0.001), and LR_ADC + DWI had the highest diagnostic accuracy in predicting both (0.6230). Conclusion: The proposed ML models are suitable for predicting both Ki67 expression and GGG in PCa. This algorithm could be used to identify indolent or invasive PCa with a noninvasive, repeatable, and accurate diagnostic method. [ABSTRACT FROM AUTHOR]

Simple Summary: The study aimed to develop and validate a prediction model that can be used to classify women for tailored breast cancer screening based on their individual risk. The model included data on age, mammographic density, family history of breast cancer, body mass index, age at menarche, alcohol consumption, exercise, pregnancy, hormone replacement therapy, and benign breast disease for 57,411 women screened in BreastScreen Norway 2007–2019. The 4-year predicted risk of breast cancer ranged between 0.2% and 7.3%, with 95% of the population having a risk of 0.6–2.3%. The differences in the predicted risk favor personalized screening for breast cancer. Background: We aimed to develop and validate a model predicting breast cancer risk for women targeted by breast cancer screening. Method: This retrospective cohort study included 57,411 women screened at least once in BreastScreen Norway during the period from 2007 to 2019. The prediction model included information about age, mammographic density, family history of breast cancer, body mass index, age at menarche, alcohol consumption, exercise, pregnancy, hormone replacement therapy, and benign breast disease. We calculated a 4-year absolute breast cancer risk estimates for women and in risk groups by quartiles. The Bootstrap resampling method was used for internal validation of the model (E/O ratio). The area under the curve (AUC) was estimated with a 95% confidence interval (CI). Results: The 4-year predicted risk of breast cancer ranged from 0.22–7.33%, while 95% of the population had a risk of 0.55–2.31%. The thresholds for the quartiles of the risk groups, with 25% of the population in each group, were 0.82%, 1.10%, and 1.47%. Overall, the model slightly overestimated the risk with an E/O ratio of 1.10 (95% CI: 1.09–1.11) and the AUC was 62.6% (95% CI: 60.5–65.0%). Conclusions: This 4-year risk prediction model showed differences in the risk of breast cancer, supporting personalized screening for breast cancer in women aged 50–69 years. [ABSTRACT FROM AUTHOR]

Simple Summary: There is sufficient evidence to confirm that early palliative care in advanced cancer patients improves symptom control, psychological distress, quality of life, patient and family satisfaction, futile use of cancer treatment at the end of life, use of healthcare resources and, in some cases, survival. In a patient-centred care model, referral to early palliative care depends on both prognosis and the complexity of care needs. Identifying the complexity of care needs is, therefore, key to appropriate referral to early palliative care teams. The PALCOM scale is a 5-domain multidimensional assessment tool developed to identify the level of complexity of the palliative needs of cancer patients. This validation study confirms the accuracy and predictive ability of the PALCOM scale to identify the level of complexity of palliative care needs in cancer patients. Higher levels of complexity are also associated with lower survival and higher in-hospital mortality. Background: In a patient-centred model of care, referral to early palliative care (EPC) depends on both the prognosis and the complexity of care needs. The PALCOM scale is a 5-domain multidimensional assessment tool developed to identify the level of complexity of palliative care needs of cancer patients. The aim of this study was to validate the PALCOM scale. Patient and methods: We conducted a prospective cohort study of cancer patients to compare the PALCOM scale and expert empirical assessment (EA) of the complexity of palliative care needs. The EA had to categorise patients according to their complexity, considering that medium to high levels required priority attention from specialist EPC teams, while those with low levels could be managed by non-specialist teams. Systematically collected multidimensional variables were recorded in an electronic report form and stratified by level of complexity and rating system (PALCOM scale versus EA). The correlation rank (Kendall's tau test) and accuracy test (F1-score) between the two rating systems were analysed. ROC curve analysis was used to determine the predictive power of the PALCOM scale. Results: A total of 283 advanced cancer patients were included. There were no significant differences in the frequency of the levels of complexity between the EA and the PALCOM scale (low 22.3–23.7%; medium 57.2–59.0%; high 20.5–17.3%). The prevalence of high symptom burden, severe pain, functional impairment, socio-familial risk, existential/spiritual problems, 6-month mortality and in-hospital death was significantly higher (p < 0.001) at the high complexity levels in both scoring systems. Comparative analysis showed a high correlation rank and accuracy between the two scoring systems (Kendall's tau test 0.81, F1 score 0.84). The predictive ability of the PALCOM scale was confirmed by an area under the curve in the ROC analysis of 0.907 for high and 0.902 for low complexity. Conclusions: In a patient-centred care model, the identification of complexity is a key point to appropriate referral and management of shared care with EPC teams. The PALCOM scale is a high precision tool for determining the level of complexity of palliative care needs. [ABSTRACT FROM AUTHOR]

Simple Summary: Ovarian cancer remains the leading cause of mortality from gynecologic cancer. In this study, we present a deep-learning artificial intelligence framework that uses pre-treatment histopathology images of high-grade ovarian cancers to predict the cancer's sensitivity or resistance to subsequent platinum-based chemotherapy. Analyses of this type could provide fast, inexpensive prediction of response to therapy at the time of initial pathological diagnosis. Background: Ovarian cancer remains the leading gynecological cause of cancer mortality. Predicting the sensitivity of ovarian cancer to chemotherapy at the time of pathological diagnosis is a goal of precision medicine research that we have addressed in this study using a novel deep-learning neural network framework to analyze the histopathological images. Methods: We have developed a method based on the Inception V3 deep learning algorithm that complements other methods for predicting response to standard platinum-based therapy of the disease. For the study, we used histopathological H&E images (pre-treatment) of high-grade serous carcinoma from The Cancer Genome Atlas (TCGA) Genomic Data Commons portal to train the Inception V3 convolutional neural network system to predict whether cancers had independently been labeled as sensitive or resistant to subsequent platinum-based chemotherapy. The trained model was then tested using data from patients left out of the training process. We used receiver operating characteristic (ROC) and confusion matrix analyses to evaluate model performance and Kaplan–Meier survival analysis to correlate the predicted probability of resistance with patient outcome. Finally, occlusion sensitivity analysis was piloted as a start toward correlating histopathological features with a response. Results: The study dataset consisted of 248 patients with stage 2 to 4 serous ovarian cancer. For a held-out test set of forty patients, the trained deep learning network model distinguished sensitive from resistant cancers with an area under the curve (AUC) of 0.846 ± 0.009 (SE). The probability of resistance calculated from the deep-learning network was also significantly correlated with patient survival and progression-free survival. In confusion matrix analysis, the network classifier achieved an overall predictive accuracy of 85% with a sensitivity of 73% and specificity of 90% for this cohort based on the Youden-J cut-off. Stage, grade, and patient age were not statistically significant for this cohort size. Occlusion sensitivity analysis suggested histopathological features learned by the network that may be associated with sensitivity or resistance to the chemotherapy, but multiple marker studies will be necessary to follow up on those preliminary results. Conclusions: This type of analysis has the potential, if further developed, to improve the prediction of response to therapy of high-grade serous ovarian cancer and perhaps be useful as a factor in deciding between platinum-based and other therapies. More broadly, it may increase our understanding of the histopathological variables that predict response and may be adaptable to other cancer types and imaging modalities. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer results from aberrant cellular signaling caused by somatic genomic alterations (SGAs). However, inferring how SGAs cause aberrations in cellular signaling and lead to cancer remains challenging. We designed an interpretable deep learning model to encode the impact of SGAs on cellular signaling systems (represented by hidden nodes in the model) and eventually on tumor gene expression. The transparent deep learning architecture enabled the model to discover drivers affecting common signaling pathways and partially resolve the causal structure of signaling proteins. This is an early attempt to use transparent deep learning model, in contrast to conventional "black box" approach, to learn interpretable insights into cancer cell signaling systems. A better representation of signaling system of a cancer cell sheds light on the disease mechanisms of the cancer and can guide precision medicine. Cancer is a disease of aberrant cellular signaling resulting from somatic genomic alterations (SGAs). Heterogeneous SGA events in tumors lead to tumor-specific signaling system aberrations. We interpret the cancer signaling system as a causal graphical model, where SGAs affect signaling proteins, propagate their effects through signal transduction, and ultimately change gene expression. To represent such a system, we developed a deep learning model called redundant-input neural network (RINN) with a transparent redundant-input architecture. Our findings demonstrate that by utilizing SGAs as inputs, the RINN can encode their impact on the signaling system and predict gene expression accurately when measured as the area under ROC curves. Moreover, the RINN can discover the shared functional impact (similar embeddings) of SGAs that perturb a common signaling pathway (e.g., PI3K, Nrf2, and TGF). Furthermore, the RINN exhibits the ability to discover known relationships in cellular signaling systems. [ABSTRACT FROM AUTHOR]

Simple Summary: The pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) is a surrogate endpoint for predicting long-term clinical benefit in breast cancer. Recently, the use of radiomic features extracted from 18F-FDG PET/CT has emerged as a promising tool for predicting treatment outcomes in various cancers. We developed and externally validated a predictive model using 18F-FDG PET-based radiomics with the least absolute shrinkage and selection operator (LASSO) logistic method for pCR following NAC in breast cancer. Our radiomic-score model demonstrated satisfactory discriminative performances in training, internal validation, and external validation cohorts. Furthermore, the integrated radiomic model incorporating human epidermal growth factor receptor 2 (HER2) status showed improved performance compared to the radiomic-score model alone in all cohorts. The newly developed radiomic-score model might enable a more accurate and personalized assessment of the tumor response to neoadjuvant chemotherapy in breast cancer. The aim of our retrospective study is to develop and externally validate an 18F-FDG PET-derived radiomics model for predicting pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer patients. A total of 87 breast cancer patients underwent curative surgery after NAC at Soonchunhyang University Seoul Hospital and were randomly assigned to a training cohort and an internal validation cohort. Radiomic features were extracted from pretreatment PET images. A radiomic-score model was generated using the LASSO method. A combination model incorporating significant clinical variables was constructed. These models were externally validated in a separate cohort of 28 patients from Soonchunhyang University Buscheon Hospital. The model performances were assessed using area under the receiver operating characteristic (AUC). Seven radiomic features were selected to calculate the radiomic-score. Among clinical variables, human epidermal growth factor receptor 2 status was an independent predictor of pCR. The radiomic-score model achieved good discriminability, with AUCs of 0.963, 0.731, and 0.729 for the training, internal validation, and external validation cohorts, respectively. The combination model showed improved predictive performance compared to the radiomic-score model alone, with AUCs of 0.993, 0.772, and 0.906 in three cohorts, respectively. The 18F-FDG PET-derived radiomic-based model is useful for predicting pCR after NAC in breast cancer. [ABSTRACT FROM AUTHOR]

Simple Summary: In our study, we aimed to create an accurate segmentation algorithm of blood vessels within histologically stained tumor tissue using deep learning. Blood vessels are crucial for supplying nutrients to tumor cells, and accurately identifying them is essential for understanding tumor development and designing effective treatments. We conducted a comprehensive investigation by comparing various deep learning architectural methods. Additionally, we reduced the time spent for data annotation and introduced a sparse labeling technique, by which only a limited amount of data was labeled for training the model. We showed that U-Net with a combination of attention gates and residual links yielded the highest precision and accuracy compared to other tested architectures. This demonstrates that our approach, even with sparse labeling, can effectively identify blood vessels and provide accurate segmentation within tumor tissue. These findings are promising for improving our understanding of tumor vasculature and potentially contributing to improved treatment strategies. Semantic segmentation is an important imaging analysis method enabling the identification of tissue structures. Histological image segmentation is particularly challenging, having large structural information while providing only limited training data. Additionally, labeling these structures to generate training data is time consuming. Here, we demonstrate the feasibility of a semantic segmentation using U-Net with a novel sparse labeling technique. The basic U-Net architecture was extended by attention gates, residual and recurrent links, and dropout regularization. To overcome the high class imbalance, which is intrinsic to histological data, under- and oversampling and data augmentation were used. In an ablation study, various architectures were evaluated, and the best performing model was identified. This model contains attention gates, residual links, and a dropout regularization of 0.125. The segmented images show accurate delineations of the vascular structures (with a precision of 0.9088 and an AUC-ROC score of 0.9717), and the segmentation algorithm is robust to images containing staining variations and damaged tissue. These results demonstrate the feasibility of sparse labeling in combination with the modified U-Net architecture. [ABSTRACT FROM AUTHOR]

Simple Summary: The information obtained in the CT and MRI allows adequate differentiation of adrenal adenomas and pheochromocytomas (PHEOs) with a high diagnostic accuracy. Our study confirms that our predictive model combining tumor size and lipid content has high re-liability for the prediction of PHEO when atypical adrenal lesions are excluded. However, for atypical adrenal lesions with >10 HU in an unenhanced CT scan, MRI information is necessary for a proper exclusion of the PHEO diagnosis. We observed that in the whole cohort (including atypical adenomas), when MRI information was included in the model, the diagnostic accuracy increased to up to 85% when the variables tumor size, high lipid content in an unenhanced CT scan, and hyperintensity in the T2 sequence in MRI were included. Purpose: to perform an external validation of our predictive model to rule out pheochromocytoma (PHEO) based on unenhanced CT in a cohort of patients with PHEOs and adenomas who underwent adrenalectomy. Methods: The predictive model was previously developed in a retrospective cohort of 1131 patients presenting with adrenal lesions. In the present study, we performed an external validation of the model in another cohort of 214 patients with available histopathological results. Results: For the external validation, 115 patients with PHEOs and 99 with adenomas were included. Our previously described predictive model combining the variables of high lipid content and tumor size in unenhanced CT (AUC-ROC: 0.961) had a lower diagnostic accuracy in our current study population for the prediction of PHEO (AUC: 0.750). However, when we excluded atypical adenomas (with Hounsfield units (HU) > 10, n = 39), the diagnostic accuracy increased to 87.4%. In addition, in the whole cohort (including atypical adenomas), when MRI information was included in the model, the diagnostic accuracy increased to up to 85% when the variables tumor size, high lipid content in an unenhanced CT scan, and hyperintensity in the T2 sequence in MRI were included. The probability of PHEO was <0.3% for adrenal lesions <20 mm with >10 HU and without hyperintensity in T2. Conclusion: Our study confirms that our predictive model combining tumor size and lipid content has high reliability for the prediction of PHEO when atypical adrenal lesions are excluded. However, for atypical adrenal lesions with >10 HU in an unenhanced CT scan, MRI information is necessary for a proper exclusion of the PHEO diagnosis. [ABSTRACT FROM AUTHOR]

Simple Summary: The standard protocol for distinguishing between benign and malignant lesions remains clinical judgment and histopathological confirmation by an experienced otolaryngologist. An additional tool is high-speed videoendoscopy (HSV), an accurate method for an objective assessment of vocal fold oscillations. The aim of the study was to utilize a quantitative assessment of the vibratory characteristics of vocal folds in diagnosing benign and malignant lesions of the glottis using HSV. The machine learning model identifying malignancy among organic lesions reached an AUC equal to 0.85 and presented with 80.6% accuracy, 100% sensitivity, and 71.1% specificity on the training set. Important predictive factors were frequency perturbation measures. The results suggested that advanced machine learning models based on HSV analysis could potentially indicate a heightened risk of cancerous mass. Therefore, this technology could, in future, aid in early cancer detection; however, further investigation and validation is needed. The aim of the study was to utilize a quantitative assessment of the vibratory characteristics of vocal folds in diagnosing benign and malignant lesions of the glottis using high-speed videolaryngoscopy (HSV). Methods: Case-control study including 100 patients with unilateral vocal fold lesions in comparison to 38 normophonic subjects. Quantitative assessment with the determination of vocal fold oscillation parameters was performed based on HSV kymography. Machine-learning predictive models were developed and validated. Results: All calculated parameters differed significantly between healthy subjects and patients with organic lesions. The first predictive model distinguishing any organic lesion patients from healthy subjects reached an area under the curve (AUC) equal to 0.983 and presented with 89.3% accuracy, 97.0% sensitivity, and 71.4% specificity on the testing set. The second model identifying malignancy among organic lesions reached an AUC equal to 0.85 and presented with 80.6% accuracy, 100% sensitivity, and 71.1% specificity on the training set. Important predictive factors for the models were frequency perturbation measures. Conclusions: The standard protocol for distinguishing between benign and malignant lesions continues to be clinical evaluation by an experienced ENT specialist and confirmed by histopathological examination. Our findings did suggest that advanced machine learning models, which consider the complex interactions present in HSV data, could potentially indicate a heightened risk of malignancy. Therefore, this technology could prove pivotal in aiding in early cancer detection, thereby emphasizing the need for further investigation and validation. [ABSTRACT FROM AUTHOR]

Simple Summary: Approximately 26.1% of patients diagnosed with lung adenocarcinoma harbour a KRAS mutation, which is associated with a poorer prognosis. Recent advances in targeted therapy, specifically with sotorasib and MRTX849, have shown promise in targeting KRAS mutations. This retrospective study aimed to develop a clinical prediction model that combines clinical–pathological variables and radiomics derived from PET scans to assess the KRAS mutation status in patients with lung adenocarcinoma. This study utilised two different databases and randomly divided into a training, a validation, and a testing dataset to build and evaluate the predictive performance of our model. Our retrospectively developed model demonstrates good predictive accuracy for determining the KRAS mutation status in lung adenocarcinoma patients. Objective: Considering the essential role of KRAS mutation in NSCLC and the limited experience of PET radiomic features in KRAS mutation, a prediction model was built in our current analysis. Our model aims to evaluate the status of KRAS mutants in lung adenocarcinoma by combining PET radiomics and machine learning. Method: Patients were retrospectively selected from our database and screened from the NSCLC radiogenomic dataset from TCIA. The dataset was randomly divided into three subgroups. Two open-source software programs, 3D Slicer and Python, were used to segment lung tumours and extract radiomic features from 18F-FDG-PET images. Feature selection was performed by the Mann–Whitney U test, Spearman's rank correlation coefficient, and RFE. Logistic regression was used to build the prediction models. AUCs from ROCs were used to compare the predictive abilities of the models. Calibration plots were obtained to examine the agreements of observed and predictive values in the validation and testing groups. DCA curves were performed to check the clinical impact of the best model. Finally, a nomogram was obtained to present the selected model. Results: One hundred and nineteen patients with lung adenocarcinoma were included in our study. The whole group was divided into three datasets: a training set (n = 96), a validation set (n = 11), and a testing set (n = 12). In total, 1781 radiomic features were extracted from PET images. One hundred sixty-three predictive models were established according to each original feature group and their combinations. After model comparison and selection, one model, including wHLH_fo_IR, wHLH_glrlm_SRHGLE, wHLH_glszm_SAHGLE, and smoking habits, was validated with the highest predictive value. The model obtained AUCs of 0.731 (95% CI: 0.619~0.843), 0.750 (95% CI: 0.248~1.000), and 0.750 (95% CI: 0.448~1.000) in the training set, the validation set and the testing set, respectively. Results from calibration plots in validation and testing groups indicated that there was no departure between observed and predictive values in the two datasets (p = 0.377 and 0.861, respectively). Conclusions: Our model combining 18F-FDG-PET radiomics and machine learning indicated a good predictive ability of KRAS status in lung adenocarcinoma. It may be a helpful non-invasive method to screen the KRAS mutation status of heterogenous lung adenocarcinoma before selected biopsy sampling. [ABSTRACT FROM AUTHOR]

Simple Summary: This study developed a prediction model for late bladder toxicity in patients with uterine cervical cancer undergoing radiation therapy. A deep learning (DL) model was trained on data from 281 patients and compared its performance with a multivariable logistic regression model. The DL model outperformed the regression model, achieving higher accuracy, recall, F1-score, and area under the receiver operating characteristic curve. Specifically, based on the feature importance analysis, the DL model identified the doses for the most exposed 2 cc volume of the bladder (BD2cc), BD5cc, and ICRU bladder point as high-priority features. Finally, the lightweight DL model, which was designed to focus on the top five important features, demonstrated superior predictive capabilities, highlighting its potential in improving patient outcomes and minimizing treatment-related complications with secured reliability. (1) In this study, we developed a deep learning (DL) model that can be used to predict late bladder toxicity. (2) We collected data obtained from 281 uterine cervical cancer patients who underwent definitive radiation therapy. The DL model was trained using 16 features, including patient, tumor, treatment, and dose parameters, and its performance was compared with that of a multivariable logistic regression model using the following metrics: accuracy, prediction, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). In addition, permutation feature importance was calculated to interpret the DL model for each feature, and the lightweight DL model was designed to focus on the top five important features. (3) The DL model outperformed the multivariable logistic regression model on our dataset. It achieved an F1-score of 0.76 and an AUROC of 0.81, while the corresponding values for the multivariable logistic regression were 0.14 and 0.43, respectively. The DL model identified the doses for the most exposed 2 cc volume of the bladder (BD2cc) as the most important feature, followed by BD5cc and the ICRU bladder point. In the case of the lightweight DL model, the F-score and AUROC were 0.90 and 0.91, respectively. (4) The DL models exhibited superior performance in predicting late bladder toxicity compared with the statistical method. Through the interpretation of the model, it further emphasized its potential for improving patient outcomes and minimizing treatment-related complications with a high level of reliability. [ABSTRACT FROM AUTHOR]

Simple Summary: Multiparametric Magnetic Resonance Imaging (mpMRI) interpretation and reporting is based on the more recent version 2.1 of the Prostate Imaging-Reporting and Data System (PI-RADS), revised in 2019, indicating the probability of clinically significant Prostate Cancer (csPCa) on a 5-point scale, which should be confirmed through trans-rectal ultrasound (TRUS) fusion-targeted biopsy. Among PI-RADS categories, PI-RADS 3 lesions represent a highly "equivocal" result, with a non-negligible probability of PCa, or even csPCa. This study exploits machine learning methods in order to investigate the role of mpMRI as a stand-alone tool for early and non-invasive detection of PCa in a selected cohort of PI-RADS 3 lesions, by means of a radiomic analysis of Apparent Diffusion Coefficient sequences. Differently from what reported in the current literature, the methodology adopted has bounded the possibility of overoptimistic predictive performance, also improving the state-of-art by achieving a positive predictive value of 80%, with specificity = 76% and sensitivity = 78%. The Prostate Imaging and Reporting Data System (PI-RADS) has a key role in the management of prostate cancer (PCa). However, the clinical interpretation of PI-RADS 3 score lesions may be challenging and misleading, thus postponing PCa diagnosis to biopsy outcome. Multiparametric magnetic resonance imaging (mpMRI) radiomic analysis may represent a stand-alone noninvasive tool for PCa diagnosis. Hence, this study aims at developing a mpMRI-based radiomic PCa diagnostic model in a cohort of PI-RADS 3 lesions. We enrolled 133 patients with 155 PI-RADS 3 lesions, 84 of which had PCa confirmation by fusion biopsy. Local radiomic features were generated from apparent diffusion coefficient maps, and the four most informative were selected using LASSO, the Wilcoxon rank-sum test (p < 0.001), and support vector machines (SVMs). The selected features where augmented and used to train an SVM classifier, externally validated on a holdout subset. Linear and second-order polynomial kernels were exploited, and their predictive performance compared through receiver operating characteristics (ROC)-related metrics. On the test set, the highest performance, equally for both kernels, was specificity = 76%, sensitivity = 78%, positive predictive value = 80%, and negative predictive value = 74%. Our findings substantially improve radiologist interpretation of PI-RADS 3 lesions and let us advance towards an image-driven PCa diagnosis. [ABSTRACT FROM AUTHOR]

Simple Summary: Indeterminate pulmonary nodules detected by computer tomography are a common clinical finding, but the path to determine malignancy can cause harm to patients. We aimed to comprehensively assess other types of noninvasive information that could help clinicians diagnose lung cancer, including semantic imaging features, quantitative radiomic imaging features and proteomic, glycomic, and autoantibody–antigen complex blood-based biomarkers. Utilizing these data, we generated a malignancy risk prediction model called PSR (plasma, semantic, radiomic) comprising nine imaging and molecular biomarkers. The PSR model performed well in two cohorts and against a clinical risk prediction model. Adding known clinical risk factors for lung cancer further improved the PSR model, indicating that our discovered markers held independent clinical utility. Our study revealed novel biomarkers and a risk prediction model to help assess cancer risk in patients with indeterminate pulmonary nodules. The clinical management of patients with indeterminate pulmonary nodules is associated with unintended harm to patients and better methods are required to more precisely quantify lung cancer risk in this group. Here, we combine multiple noninvasive approaches to more accurately identify lung cancer in indeterminate pulmonary nodules. We analyzed 94 quantitative radiomic imaging features and 41 qualitative semantic imaging variables with molecular biomarkers from blood derived from an antibody-based microarray platform that determines protein, cancer-specific glycan, and autoantibody–antigen complex content with high sensitivity. From these datasets, we created a PSR (plasma, semantic, radiomic) risk prediction model comprising nine blood-based and imaging biomarkers with an area under the receiver operating curve (AUROC) of 0.964 that when tested in a second, independent cohort yielded an AUROC of 0.846. Incorporating known clinical risk factors (age, gender, and smoking pack years) for lung cancer into the PSR model improved the AUROC to 0.897 in the second cohort and was more accurate than a well-characterized clinical risk prediction model (AUROC = 0.802). Our findings support the use of a multi-omics approach to guide the clinical management of indeterminate pulmonary nodules. [ABSTRACT FROM AUTHOR]

Simple Summary: Highly aggressive cutaneous squamous-cell carcinomas (cSCCs) are the primary cause of death in patients with the rare skin disease recessive dystrophic epidermolysis bullosa (RDEB). Currently the detection of RDEB-SCCs requires invasive skin biopsies with a high burden for patients and limitations in surveying widespread areas. The aim of our study was to use machine learning as a tool to identify short RNA molecules that are capable of identifying tumors in RDEB patients. As there is only a limited number of RDEB-patients, we included data on patients with a different type of SCCs who, however, show similarity in RNA profiles. This finally facilitated us to nominate sets of short RNAs that can discriminate between tumor and healthy cells. Machine learning has been proven to be a powerful tool in the identification of diagnostic tumor biomarkers but is often impeded in rare cancers due to small patient numbers. In patients suffering from recessive dystrophic epidermolysis bullosa (RDEB), early-in-life development of particularly aggressive cutaneous squamous-cell carcinomas (cSCCs) represents a major threat and timely detection is crucial to facilitate prompt tumor excision. As miRNAs have been shown to hold great potential as liquid biopsy markers, we characterized miRNA signatures derived from cultured primary cells specific for the potential detection of tumors in RDEB patients. To address the limitation in RDEB-sample accessibility, we analyzed the similarity of RDEB miRNA profiles with other tumor entities derived from the Cancer Genome Atlas (TCGA) repository. Due to the similarity in miRNA expression with RDEB-SCC, we used HN-SCC data to train a tumor prediction model. Three models with varying complexity using 33, 10 and 3 miRNAs were derived from the elastic net logistic regression model. The predictive performance of all three models was determined on an independent HN-SCC test dataset (AUC-ROC: 100%, 83% and 96%), as well as on cell-based RDEB miRNA-Seq data (AUC-ROC: 100%, 100% and 91%). In addition, the ability of the models to predict tumor samples based on RDEB exosomes (AUC-ROC: 100%, 93% and 100%) demonstrated the potential feasibility in a clinical setting. Our results support the feasibility of this approach to identify a diagnostic miRNA signature, by exploiting publicly available data and will lay the base for an improvement of early RDEB-SCC detection. [ABSTRACT FROM AUTHOR]

Simple Summary: Early prediction of response to cancer therapies is critical for treatment personalisation. In patients with locally advanced rectal cancer (LARC) undergoing neoadjuvant chemoradiation therapy (nCRT), delta radiomics applied to mesorectal features could potentially lead to the development of predictive models of treatment response. Pre- and post-treatment MRIs of patients treated at a single institution were analysed. Radiomic features of the mesorectum and GTV were extracted and predictive models of pathological complete response (pCR) and two-year disease-free survival (2yDFS) were developed. In 203 patients with LARC, a total of 565 variables were evaluated; the best performing 2yDFS prediction model was based on one GTV and two mesorectal features with an AUC of 0.79 in the training set and 0.70 in the validation set. The mesorectum may contain important radiomics information for predicting response to nCRT treatment in LARC patients. Background: The aim of this study is to evaluate the delta radiomics approach based on mesorectal radiomic features to develop a model for predicting pathological complete response (pCR) and 2-year disease-free survival (2yDFS) in locally advanced rectal cancer (LARC) patients undergoing neoadjuvant chemoradiotherapy (nCRT). Methods: Pre- and post-nCRT MRIs of LARC patients treated at a single institution from May 2008 to November 2016 were retrospectively collected. Radiomic features were extracted from the GTV and mesorectum. The Wilcoxon–Mann–Whitney test and area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the features in predicting pCR and 2yDFS. Results: Out of 203 LARC patients, a total of 565 variables were evaluated. The best performing pCR prediction model was based on two GTV features with an AUC of 0.80 in the training set and 0.69 in the validation set. The best performing 2yDFS prediction model was based on one GTV and two mesorectal features with an AUC of 0.79 in the training set and 0.70 in the validation set. Conclusions: The results of this study suggest a possible role for delta radiomics based on mesorectal features in the prediction of 2yDFS in patients with LARC. [ABSTRACT FROM AUTHOR]

Simple Summary: After treatment, glioblastoma typically recurs. In some patients with recurrent glioblastoma, bevacizumab improves progression-free survival. The magnetic resonance texture analysis quantifies the macroscopic tissue heterogeneity that is indirectly linked to the microscopic tissue properties. In 33 patients with recurrent glioblastoma who were treated with bevacizumab, we evaluated the predictive value of magnetic resonance texture analysis for survival. Volumes of contrast-enhancing lesions segmented on postcontrast T1-weighted sequences were co-registered with apparent diffusion coefficient maps in order to extract 107 radiomic features. We found that some features derived from texture analysis accurately predicted survival. Identifying pretreatment imaging biomarkers that predict outcomes following bevacizumab therapy for recurrent glioblastoma can be beneficial for selecting patients most likely to benefit from this costly treatment. These promising preliminary results may be a small but significant step toward demonstrating the clinical relevance of radiomic profiles in the treatment of this disease. Purpose: Glioblastoma often recurs after treatment. Bevacizumab increases progression-free survival in some patients with recurrent glioblastoma. Identifying pretreatment predictors of survival can help clinical decision making. Magnetic resonance texture analysis (MRTA) quantifies macroscopic tissue heterogeneity indirectly linked to microscopic tissue properties. We investigated the usefulness of MRTA in predicting survival in patients with recurrent glioblastoma treated with bevacizumab. Methods: We evaluated retrospective longitudinal data from 33 patients (20 men; mean age 56 ± 13 years) who received bevacizumab on the first recurrence of glioblastoma. Volumes of contrast-enhancing lesions segmented on postcontrast T1-weighted sequences were co-registered on apparent diffusion coefficient maps to extract 107 radiomic features. To assess the performance of textural parameters in predicting progression-free survival and overall survival, we used receiver operating characteristic curves, univariate and multivariate regression analysis, and Kaplan–Meier plots. Results: Longer progression-free survival (>6 months) and overall survival (>1 year) were associated with lower values of major axis length (MAL), a lower maximum 2D diameter row (m2Ddr), and higher skewness values. Longer progression-free survival was also associated with higher kurtosis, and longer overall survival with higher elongation values. The model combining MAL, m2Ddr, and skewness best predicted progression-free survival at 6 months (AUC 0.886, 100% sensitivity, 77.8% specificity, 50% PPV, 100% NPV), and the model combining m2Ddr, elongation, and skewness best predicted overall survival (AUC 0.895, 83.3% sensitivity, 85.2% specificity, 55.6% PPV, 95.8% NPV). Conclusions: Our preliminary analyses suggest that in patients with recurrent glioblastoma pretreatment, MRTA helps to predict survival after bevacizumab treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. However, there are no reliable tools available for achieving this goal. Data-driven deep-learning techniques have been widely used in disease diagnosis, prognosis assessment, and treatment response prediction by identifying subtle patterns in digitized histopathological images. In this study, we developed a weakly-supervised model based on multiple instance learning and attention mechanism for predicting LNM status in MIBC patients, demonstrating decent performance in three independent cohorts. The visualization technique revealed that the stroma surrounding the tumor with lymphocytic inflammation seemed to be the critical feature for predicting LNM. This deep learning-based study provides a non-invasive and low-cost preoperative prediction tool for identifying MIBC patients with a high risk of LNM. Background: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC. Methods: We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets. Results: In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771–0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661–0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827–0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725–0.801) and 0.746 (95% CI, 0.687–0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence. Conclusions: Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation. [ABSTRACT FROM AUTHOR]

Simple Summary: In a retrospective study, researchers analyzed data from 909 patients with papillary thyroid carcinoma (PTC) who underwent thyroidectomy and neck dissection. The aim was to validate the relationship between lymph node ratio (LNR) and recurrence in patients with fewer than six lymph nodes examined after surgery. Over an average follow-up of 127.24 ± 33.6 months, recurrences occurred in 5.1% of the patients. The analysis identified an LNR ≥ 0.29 as an independent prognostic factor for recurrence. This means that patients with an LNR equal to or higher than 0.29 had a higher likelihood of recurrence compared to those with a lower LNR. These findings highlight the importance of considering LNR as a valuable prognostic marker for PTC patients with limited lymph node examination. Incorporating LNR into risk assessment can improve recurrence prediction and help guide treatment strategies. However, further prospective studies are needed to validate these results and determine their clinical implications in managing PTC patients. The American Thyroid Association risk stratification system suggests that having >5 metastatic lymph nodes (LNs) increase the recurrence risk in patients with papillary thyroid carcinoma (PTC). However, little is known about PTC with <5 harvested LNs. This study aimed to stratify patients with low-LN-yield (low-LNY) PTC based on lymph node ratios (LNRs). From 2007 to 2017, 6317 patients who underwent thyroidectomies were diagnosed with PTC at Seoul St. Mary's Hospital, and 909 patients with low LNYs were included in the study. Tumor recurrence was compared based on LNR. The LNR cutoff was determined using a receiver operating characteristic curve. Forty-six patients (5.1%) experienced recurrences over a mean follow-up period of 127.24 ± 33.6 months (range, 5–190 months). The cutoff for the low-LNR (n = 675) and high-LNR (n = 234) groups was 0.29 (AUC = 0.676, 95% CI = 0.591–0.761, p < 0.001). The recurrence rate was significantly higher in the high-LNR group compared to the rate in the low-LNR group (12.4% vs. 2.5%, p < 0.001). Multivariate analysis using Cox regression revealed that tumor size and LNR ≥ 0.29 were independent prognostic factors for recurrence. Therefore, LNR can be utilized to stratify the risk of recurrence in patients with low-LNY PTC. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, we developed a generic framework to analyze the Surveillance, Epidemiology, and End Results (SEER) database to generate reliable machine learning (ML) prediction models for cancer recurrence. As a proof-of-concept, using 130,979 oral tongue squamous cell carcinoma patients, we generated ML models to predict 5- and 10-year recurrence with high accuracy, recall, and precision. Thus, we demonstrate an effective framework for guiding future ML efforts in predicting cancer recurrence using the SEER database, with implications for the guidance of patient management and follow-up care. Despite diagnostic advancements, the development of reliable prognostic systems for assessing the risk of cancer recurrence still remains a challenge. In this study, we developed a novel framework to generate highly representative machine-learning prediction models for oral tongue squamous cell carcinoma (OTSCC) cancer recurrence. We identified cases of 5- and 10-year OTSCC recurrence from the SEER database. Four classification models were trained using the H2O ai platform, whose performances were assessed according to their accuracy, recall, precision, and the area under the curve (AUC) of their receiver operating characteristic (ROC) curves. By evaluating Shapley additive explanation contribution plots, feature importance was studied. Of the 130,979 patients studied, 36,042 (27.5%) were female, and the mean (SD) age was 58.2 (13.7) years. The Gradient Boosting Machine model performed the best, achieving 81.8% accuracy and 97.7% precision for 5-year prediction. Moreover, 10-year predictions demonstrated 80.0% accuracy and 94.0% precision. The number of prior tumors, patient age, the site of cancer recurrence, and tumor histology were the most significant predictors. The implementation of our novel SEER framework enabled the successful identification of patients with OTSCC recurrence, with which highly accurate and sensitive prediction models were generated. Thus, we demonstrate our framework's potential for application in various cancers to build generalizable screening tools to predict tumor recurrence. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is a heterogeneous disease characterized by different risks of relapse, which makes it challenging to predict progression and select the most appropriate follow-up strategies. With the ever-growing adoption of Electronic Health Records, there are great opportunities to leverage the amount of data collected routinely in electronic format for secondary purposes. Machine Learning algorithms offer the ability to analyze large amounts of data and reveal insights that might otherwise go undetected. In this study, we have applied several algorithms to predict 5-year breast cancer recurrence from health data. We compared whether taking advantage of both structured and unstructured data from health records yields better prediction results than using any of the sources separately. These algorithms are valuable tools to help clinicians effectively integrate large amounts of data into their decision-making and are key to improving risk stratification and providing personalized assistance to patients. Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort. [ABSTRACT FROM AUTHOR]

Simple Summary: We introduced a novel squamous cell carcinoma inflammatory index (SCI) derived by multiplying the serum squamous cell carcinoma antigen and neutrophil-to-lymphocyte ratio values for individuals with operable oral cavity squamous cell carcinomas (OSCCs). The prognostic value of SCI was explored by retrospectively analyzing data from 288 patients with a diagnosis of primary OSCC between January 2008 and December 2017. The current results demonstrated that patients with a high SCI (≥3.45) were associated with worse disease-free survival and overall survival than those with a low SCI (<3.45). An elevated preoperative SCI (≥3.45) predicted adverse overall survival (hazard ratio [HR] = 2.378; p < 0.002) and disease-free survival (HR = 2.219; p < 0.001) in a multivariable analysis. The constructed nomogram enables the clinical utility of the SCI and provides accurate OS predictions. Our findings indicate that SCI is a valuable and promising biomarker that is highly associated with patient survival outcomes in OSCC. We introduced a novel squamous cell carcinoma inflammatory index (SCI) and explored its prognostic utility for individuals with operable oral cavity squamous cell carcinomas (OSCCs). We retrospectively analyzed data from 288 patients who were given a diagnosis of primary OSCC from January 2008 to December 2017. The SCI value was derived by multiplying the serum squamous cell carcinoma antigen and neutrophil-to-lymphocyte ratio values. We appraised the associations of the SCI with survival outcomes by performing Cox proportional hazards and Kaplan–Meier analyses. We constructed a nomogram for survival predictions by incorporating independent prognostic factors in a multivariable analysis. By executing a receiver operating characteristic curve analysis, we identified the SCI cutoff to be 3.45, and 188 and 100 patients had SCI values of <3.45 and ≥3.45, respectively. The patients with a high SCI (≥3.45) were associated with worse disease-free survival and overall survival than those with a low SCI (<3.45). An elevated preoperative SCI (≥3.45) predicted adverse overall survival (hazard ratio [HR] = 2.378; p < 0.002) and disease-free survival (HR = 2.219; p < 0.001). The SCI-based nomogram accurately predicted overall survival (concordance index: 0.779). Our findings indicate that SCI is a valuable biomarker that is highly associated with patient survival outcomes in OSCC. [ABSTRACT FROM AUTHOR]

Simple Summary: A major prognosis factor for glioblastoma patients is the methylation status of the DNA repair enzyme MGMT. Obtaining this information using deep learning models trained on non-invasive MRI data is a major challenge with no scientific consensus to date. In this study, we provide a more rigorous and comprehensive answer to this question by using confidence metrics and relating them to the exact percentage of methylation obtained at biopsy. This systematic approach confirms that the deep learning algorithms developed until now are not suitable for clinical application. We also provide, to the best of our knowledge, the first fully reproducible source code and experiments on this issue. Glioblastoma is the most aggressive primary brain tumor, which almost systematically relapses despite surgery (when possible) followed by radio-chemotherapy temozolomide-based treatment. Upon relapse, one option for treatment is another chemotherapy, lomustine. The efficacy of these chemotherapy regimens depends on the methylation of a specific gene promoter known as MGMT, which is the main prognosis factor for glioblastoma. Knowing this biomarker is a key issue for the clinician to personalize and adapt treatment to the patient at primary diagnosis for elderly patients, in particular, and also upon relapse. The association between MRI-derived information and the prediction of MGMT promoter status has been discussed in many studies, and some, more recently, have proposed the use of deep learning algorithms on multimodal scans to extract this information, but they have failed to reach a consensus. Therefore, in this work, beyond the classical performance figures usually displayed, we seek to compute confidence scores to see if a clinical application of such methods can be seriously considered. The systematic approach carried out, using different input configurations and algorithms as well as the exact methylation percentage, led to the following conclusion: current deep learning methods are unable to determine MGMT promoter methylation from MRI data. [ABSTRACT FROM AUTHOR]

Simple Summary: Machine learning approaches, using both radiomic and deep-learning-based features, were performed for an analysis of the breast parenchyma to identify women at risk of future breast cancer. Results from this study demonstrate that the antecedent mammographic images can potentially discriminate between women with a future-biopsy-proven cancer versus those with a future-biopsy-proven benign lesion. The identification of women at risk for sporadic breast cancer remains a clinical challenge. We hypothesize that the temporal analysis of annual screening mammograms, using a long short-term memory (LSTM) network, could accurately identify women at risk of future breast cancer. Women with an imaging abnormality, which had been biopsy-confirmed to be cancer or benign, who also had antecedent imaging available were included in this case–control study. Sequences of antecedent mammograms were retrospectively collected under HIPAA-approved guidelines. Radiomic and deep-learning-based features were extracted on regions of interest placed posterior to the nipple in antecedent images. These features were input to LSTM recurrent networks to classify whether the future lesion would be malignant or benign. Classification performance was assessed using all available antecedent time-points and using a single antecedent time-point in the task of lesion classification. Classifiers incorporating multiple time-points with LSTM, based either on deep-learning-extracted features or on radiomic features, tended to perform statistically better than chance, whereas those using only a single time-point failed to show improved performance compared to chance, as judged by area under the receiver operating characteristic curves (AUC: 0.63 ± 0.05, 0.65 ± 0.05, 0.52 ± 0.06 and 0.54 ± 0.06, respectively). Lastly, similar classification performance was observed when using features extracted from the affected versus the contralateral breast in predicting future unilateral malignancy (AUC: 0.63 ± 0.05 vs. 0.59 ± 0.06 for deep-learning-extracted features; 0.65 ± 0.05 vs. 0.62 ± 0.06 for radiomic features). The results of this study suggest that the incorporation of temporal information into radiomic analyses may improve the overall classification performance through LSTM, as demonstrated by the improved discrimination of future lesions as malignant or benign. Further, our data suggest that a potential field effect, changes in the breast extending beyond the lesion itself, is present in both the affected and contralateral breasts in antecedent imaging, and, thus, the evaluation of either breast might inform on the future risk of breast cancer. [ABSTRACT FROM AUTHOR]