Search

Simple Summary: Head and neck cancer is a serious health concern that affects millions of people across the globe. Predicting how patients will respond to therapy is critical for providing optimal care. To make these predictions, one may first manually identify tumour boundaries on medical imaging in order to obtain the necessary information. Manually establishing tumour borders, however, is both costly and time-consuming, and prone to error and disagreement. Our AI-based research provides a unique method for predicting patient outcome that eliminates the need for manual delineation steps. Instead, we collect information from the patient's whole head and neck area on PET scans as "looked upon" from a variety of angles. Our technique is faster, more consistent, and more precise than existing methods, with the potential to help doctors deliver better care to patients. We introduce an innovative, simple, effective segmentation-free approach for survival analysis of head and neck cancer (HNC) patients from PET/CT images. By harnessing deep learning-based feature extraction techniques and multi-angle maximum intensity projections (MA-MIPs) applied to Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) images, our proposed method eliminates the need for manual segmentations of regions-of-interest (ROIs) such as primary tumors and involved lymph nodes. Instead, a state-of-the-art object detection model is trained utilizing the CT images to perform automatic cropping of the head and neck anatomical area, instead of only the lesions or involved lymph nodes on the PET volumes. A pre-trained deep convolutional neural network backbone is then utilized to extract deep features from MA-MIPs obtained from 72 multi-angel axial rotations of the cropped PET volumes. These deep features extracted from multiple projection views of the PET volumes are then aggregated and fused, and employed to perform recurrence-free survival analysis on a cohort of 489 HNC patients. The proposed approach outperforms the best performing method on the target dataset for the task of recurrence-free survival analysis. By circumventing the manual delineation of the malignancies on the FDG PET-CT images, our approach eliminates the dependency on subjective interpretations and highly enhances the reproducibility of the proposed survival analysis method. The code for this work is publicly released. [ABSTRACT FROM AUTHOR]

We introduce an innovative, simple, effective segmentation-free approach for survival analysis of head and neck cancer (HNC) patients from PET/CT images. By harnessing deep learning-based feature extraction techniques and multi-angle maximum intensity projections (MA-MIPs) applied to Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) images, our proposed method eliminates the need for manual segmentations of regions-of-interest (ROIs) such as primary tumors and involved lymph nodes. Instead, a state-of-the-art object detection model is trained utilizing the CT images to perform automatic cropping of the head and neck anatomical area, instead of only the lesions or involved lymph nodes on the PET volumes. A pre-trained deep convolutional neural network backbone is then utilized to extract deep features from MA-MIPs obtained from 72 multi-angel axial rotations of the cropped PET volumes. These deep features extracted from multiple projection views of the PET volumes are then aggregated and fused, and employed to perform recurrence-free survival analysis on a cohort of 489 HNC patients. The proposed approach outperforms the best performing method on the target dataset for the task of recurrence-free survival analysis. By circumventing the manual delineation of the malignancies on the FDG PET-CT images, our approach eliminates the dependency on subjective interpretations and highly enhances the reproducibility of the proposed survival analysis method. The code for this work is publicly released.

Simple Summary: The role of prostate cryoablation was still uncertain for patients with high-risk prostate cancer (PC). This study was designed to investigate the 10-year outcomes and establish a nomogram for high-risk PC patients. We found prostate cryoablation to be an effective treatment option for selected men with high-risk PC. A preoperative nomogram that predicts biochemical recurrence would be useful for both patients and physicians to make clinical decisions when considering prostate cryoablation among other treatment modalities. A peri-operative nomogram that includes diagnostic PSA, PSA nadir, Gleason sum, and the number of cryoprobes deployed helps inform increased risk of biochemical recurrence, which would then justify early salvage treatments. The role of prostate cryoablation was still uncertain for patients with high-risk prostate cancer (PC). This study was designed to investigate 10-year disease-free survival and establish a nomogram in localized high-risk PC patients. Between October 2008 and December 2020, 191 patients with high-risk PC who received primary total prostate cryoablation (PTPC) were enrolled. The primary endpoint was biochemical recurrence (BCR), defined using Phoenix criteria. The performance of pre-operative and peri-operative nomograms was determined using the Harrell concordance index (C-index). Among the cohort, the median age and PSA levels at diagnosis were 71 years and 12.3 ng/mL, respectively. Gleason sum 8–10, stage ≥ T3a, and PSA > 20 ng/mL were noted in 27.2%, 74.4%, and 26.2% of patients, respectively. During the median follow-up duration of 120.4 months, BCR-free rates at 1, 3, 5, and 10 years were 92.6%, 76.6%, 66.7%, and 50.8%, respectively. The metastasis-free, cancer-specific, and overall survival rates were 89.5%, 97.4%, and 90.5% at 10 years, respectively. The variables in the pre-operative nomogram for BCR contained PSA at diagnosis, clinical stage, and Gleason score (C-index: 0.73, 95% CI, 0.67–0.79). The variables in the peri-operative nomogram for BCR included PSA at diagnosis, Gleason score, number of cryoprobes used, and PSA nadir (C-index: 0.83, 95% CI, 0.78–0.88). In conclusion, total prostate cryoablation appears to be an effective treatment option for selected men with high-risk PC. A pre-operative nomogram can help select patients suitable for cryoablation. A peri-operative nomogram signifies the importance of the ample use of cryoprobes and helps identify patients who may need early salvage treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: The poor tumor characterization and the lack of prognostic biomarkers hinder the efficacy and the personalization of treatments for Sacral Chordomas (SC), for which Carbon Ion Radiotherapy (CIRT) is one of the most promising therapeutic options. The aim of this work is to apply, for the first time, a dosiomics approach to biological dose and dose-averaged Linear Energy Transfer (LETd) maps, towards the identification of possible prognostic factors and the future integration of decision supportive tools in CIRT workflows. We conducted a time-to-event analysis on a pool of 50 SC patients, investigating the performances of regularized Cox models (r-Cox) and survival Support Vector Machines (s-SVM) in predicting Local Recurrence (LR). LETd distributions confirmed their important role for patient stratification into high/low-risk groups for recurrencies in high-dose regions, showing a potential as a possible source of prognostic factors for CIRT applied to SC. Carbon Ion Radiotherapy (CIRT) is one of the most promising therapeutic options to reduce Local Recurrence (LR) in Sacral Chordomas (SC). The aim of this work is to compare the performances of survival models fed with dosiomics features and conventional DVH metrics extracted from relative biological effectiveness (RBE)-weighted dose (DRBE) and dose-averaged Linear Energy Transfer (LETd) maps, towards the identification of possible prognostic factors for LR in SC patients treated with CIRT. This retrospective study included 50 patients affected by SC with a focus on patients that presented a relapse in a high-dose region. Survival models were built to predict both LR and High-Dose Local Recurrencies (HD-LR). The models were evaluated through Harrell Concordance Index (C-index) and patients were stratified into high/low-risk groups. Local Recurrence-free Kaplan–Meier curves were estimated and evaluated through log-rank tests. The model with highest performance (median(interquartile-range) C-index of 0.86 (0.22)) was built on features extracted from LETd maps, with DRBE models showing promising but weaker results (C-index of 0.83 (0.21), 0.80 (0.21)). Although the study should be extended to a wider patient population, LETd maps show potential as a prognostic factor for SC HD-LR in CIRT, and dosiomics appears to be the most promising approach against more conventional methods (e.g., DVH-based). [ABSTRACT FROM AUTHOR]

Simple Summary: Lung cancer is the leading cause of cancer-related death worldwide. Nonsmall cell lung cancer (NSCLC) accounts for 80–85% of all cases. Immune checkpoint inhibitors (ICIs) have revolutionized the field of oncology by improving survival in cancer patients. However, given their limited response rate and high immunotoxicity, an accurate selection of NSCLC patients eligible for ICIs appears to be of great importance. We aimed to investigate the predictive value of baseline 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography (FDG-PET/CT) for a durable response to ICIs by linking the morphological and metabolic features of primary tumors in NSCLC patients. The baseline FDG-PET/CT could be used to predict the durable response to ICIs in NSCLC patients. Age, clinical stage IV, lymphangiosis features (on imaging), primary tumor (PT) volume (thus PT metabolic tumor volume MTV due to the demonstrated linear correlation), PT standardized uptake value maximum (SUVmax), and total lesion glycolysis (TLG) were very strong long-term outcome predictors. Our results highlight the importance of linking clinical data, as much as morphological features, to the metabolic parameters of primary tumors in a multivariate outcome-predicting model using baseline FDG-PET/CT. Objectives: We aimed to investigate the predictive value of baseline 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography (FDG-PET/CT) for durable responses to immune checkpoint inhibitors (ICIs) by linking the morphological and metabolic features of primary tumors (PTs) in nonsmall cell lung cancer (NSCLC) patients. Methods: For the purpose of this single-center study, the imaging data of the patients with a first diagnosis of NSCLC and an available baseline FDG-PET/CT between 2020 and 2021 were retrospectively assessed. The baseline characteristics were collected based on clinical reports and interdisciplinary tumor board documentation. The metabolic (such as standardized uptake value SUV maximum and mean (SUVmax, SUV mean), metabolic tumor volume (MTV), total lesion glycolysis (TLG)) and morphological (such as volume, morphology, margin, and presence of lymphangiosis through imaging) features of all the PTs were retrospectively assessed using FDG-PET/CT. Overall survival (OS), progression-free survival (PFS), clinical benefit (CB) and mortality rate were used as endpoints to define the long-term response to therapy. A backward, stepwise logistic regression analysis was performed in order to define the best model for predicting lasting responses to treatment. Statistical significance was assumed at p < 0.05. Results: A total of 125 patients (median age ± standard deviation (SD) 72.0 ± 9.5 years) were enrolled: 64 men (51.2%) and 61 women (48.8%). Adenocarcinoma was by far the most common histological subtype of NSCLC (47.2%). At the initial diagnosis, the vast majority of all the included patients showed either locally advanced disease (34.4%) or metastatic disease (36.8%). Fifty patients were treated with ICIs either as a first-line (20%) or second-line (20%) therapy, while 75 patients did not receive ICIs. The median values ± SD of PT SUVmax, mean, MTV, and TLG were respectively 10.1 ± 6.0, 6.1 ± 3.5, 13.5 ± 30.7, and 71.4 ± 247.7. The median volume of PT ± SD was 13.7 ± 30.7 cm3. The PTs were most frequently solid (86.4%) with irregular margins (76.8%). Furthermore, in one out of five cases, the morphological evidence of lymphangiosis was seen through imaging (n = 25). The median follow-up ± SD was 18.93 ± 6.98 months. The median values ± SD of OS and PFS were, respectively, 14.80 ± 8.68 months and 14.03 ± 9.02 months. Age, PT volume, SUVmax, TLG, the presence of lymphangiosis features through imaging, and clinical stage IV were very strong long-term outcome predictors of patients treated with ICIs, while no significant outcome predictors could be found for the cohort with no ICI treatment. The optimal cut-off values were determined for PT volume (26.94 cm3) and SUVmax (15.05). Finally, 58% of NSCLC patients treated with ICIs had a CB vs. 78.7% of patients in the cohort with no ICI treatment. However, almost all patients treated with ICIs and with disease progression over time died (mortality in the case of disease progression 95% vs. 62.5% in the cohort without ICIs). Conclusion: Baseline FDG-PET/CT could be used to predict a durable response to ICIs in NSCLC patients. Age, clinical stage IV, lymphangiosis features through imaging, PT volume (thus PT MTV due to a previously demonstrated linear correlation), PT SUVmax, and TLG were very strong long-term outcome predictors. Our results highlight the importance of linking clinical data, as much as morphological features, to the metabolic parameters of primary tumors in a multivariate outcome-predicting model using baseline FDG-PET/CT. [ABSTRACT FROM AUTHOR]

The role of prostate cryoablation was still uncertain for patients with high-risk prostate cancer (PC). This study was designed to investigate 10-year disease-free survival and establish a nomogram in localized high-risk PC patients. Between October 2008 and December 2020, 191 patients with high-risk PC who received primary total prostate cryoablation (PTPC) were enrolled. The primary endpoint was biochemical recurrence (BCR), defined using Phoenix criteria. The performance of pre-operative and peri-operative nomograms was determined using the Harrell concordance index (C-index). Among the cohort, the median age and PSA levels at diagnosis were 71 years and 12.3 ng/mL, respectively. Gleason sum 8–10, stage ≥ T3a, and PSA > 20 ng/mL were noted in 27.2%, 74.4%, and 26.2% of patients, respectively. During the median follow-up duration of 120.4 months, BCR-free rates at 1, 3, 5, and 10 years were 92.6%, 76.6%, 66.7%, and 50.8%, respectively. The metastasis-free, cancer-specific, and overall survival rates were 89.5%, 97.4%, and 90.5% at 10 years, respectively. The variables in the pre-operative nomogram for BCR contained PSA at diagnosis, clinical stage, and Gleason score (C-index: 0.73, 95% CI, 0.67–0.79). The variables in the peri-operative nomogram for BCR included PSA at diagnosis, Gleason score, number of cryoprobes used, and PSA nadir (C-index: 0.83, 95% CI, 0.78–0.88). In conclusion, total prostate cryoablation appears to be an effective treatment option for selected men with high-risk PC. A pre-operative nomogram can help select patients suitable for cryoablation. A peri-operative nomogram signifies the importance of the ample use of cryoprobes and helps identify patients who may need early salvage treatment.

Carbon Ion Radiotherapy (CIRT) is one of the most promising therapeutic options to reduce Local Recurrence (LR) in Sacral Chordomas (SC). The aim of this work is to compare the performances of survival models fed with dosiomics features and conventional DVH metrics extracted from relative biological effectiveness (RBE)-weighted dose (DRBE) and dose-averaged Linear Energy Transfer (LETd) maps, towards the identification of possible prognostic factors for LR in SC patients treated with CIRT. This retrospective study included 50 patients affected by SC with a focus on patients that presented a relapse in a high-dose region. Survival models were built to predict both LR and High-Dose Local Recurrencies (HD-LR). The models were evaluated through Harrell Concordance Index (C-index) and patients were stratified into high/low-risk groups. Local Recurrence-free Kaplan–Meier curves were estimated and evaluated through log-rank tests. The model with highest performance (median(interquartile-range) C-index of 0.86 (0.22)) was built on features extracted from LETd maps, with DRBE models showing promising but weaker results (C-index of 0.83 (0.21), 0.80 (0.21)). Although the study should be extended to a wider patient population, LETd maps show potential as a prognostic factor for SC HD-LR in CIRT, and dosiomics appears to be the most promising approach against more conventional methods (e.g., DVH-based).

(1) Background: To evaluate radiomics features as well as a combined model with clinical parameters for predicting overall survival in patients with bladder cancer (BCa). (2) Methods: This retrospective study included 301 BCa patients who received radical cystectomy (RC) and pelvic lymphadenectomy. Radiomics features were extracted from the regions of the primary tumor and pelvic lymph nodes as well as the peritumoral regions in preoperative CT scans. Cross-validation was performed in the training cohort, and a Cox regression model with an elastic net penalty was trained using radiomics features and clinical parameters. The models were evaluated with the time-dependent area under the ROC curve (AUC), Brier score and calibration curves. (3) Results: The median follow-up time was 56 months (95% CI: 48–74 months). In the follow-up period from 1 to 7 years after RC, radiomics models achieved comparable predictive performance to validated clinical parameters with an integrated AUC of 0.771 (95% CI: 0.657–0.869) compared to an integrated AUC of 0.761 (95% CI: 0.617–0.874) for the prediction of overall survival (p = 0.98). A combined clinical and radiomics model stratified patients into high-risk and low-risk groups with significantly different overall survival (p < 0.001). (4) Conclusions: Radiomics features based on preoperative CT scans have prognostic value in predicting overall survival before RC. Therefore, radiomics may guide early clinical decision-making.

Purpose: To assess radiomics features efficacy obtained by arterial and portal MRI phase in the prediction of clinical outcomes in the colorectal liver metastases patients, evaluating recurrence, mutational status, pathological characteristic (mucinous and tumor budding) and surgical resection margin. Methods: This retrospective analysis was approved by the local Ethical Committee board, and radiological databases were used to select patients with colorectal liver metastases with pathological proof and MRI study in a pre-surgical setting after neoadjuvant chemotherapy. The cohort of patients included a training set (51 patients with 61 years of median age and 121 liver metastases) and an external validation set (30 patients with single lesion with 60 years of median age). For each segmented volume of interest on MRI by two expert radiologists, 851 radiomics features were extracted as median values using the PyRadiomics tool. Non-parametric Kruskal-Wallis test, intraclass correlation, receiver operating characteristic (ROC) analysis, linear regression modelling and pattern recognition methods (support vector machine (SVM), k-nearest neighbors (KNN), artificial neural network (NNET), and decision tree (DT)) were considered. Results: The best predictor to discriminate expansive versus infiltrative tumor growth front was wavelet_LHH_glrlm_ShortRunLowGrayLevelEmphasis extracted on portal phase with accuracy of 82%, sensitivity of 84%, and specificity of 77%. The best predictor to discriminate tumor budding was wavelet_LLH_firstorder_10Percentile extracted on portal phase with accuracy of 92%, a sensitivity of 96%, and a specificity of 81%. The best predictor to differentiate the mucinous type of tumor was the wavelet_LLL_glcm_ClusterTendency extracted on portal phase with accuracy of 88%, a sensitivity of 38%, and a specificity of 100%. The best predictor to identify the recurrence was the wavelet_HLH_ngtdm_Complexity extracted on arterial phase with accuracy of 90%, a sensitivity of 71%, and a specificity of 95%. The best linear regression model was obtained in the identification of mucinous type considering the 13 textural significant metrics extracted by arterial phase (accuracy of 94%, sensitivity of 77% and a specificity of 99%). The best results were obtained in the identification of tumor budding with the eleven textural significant features extracted by arterial phase using a KNN (accuracy of 95%, sensitivity of 84%, and a specificity of 99%). Conclusions: Our results confirmed the capacity of radiomics to identify as biomarkers and several prognostic features that could affect the treatment choice in patients with liver metastases in order to obtain a more personalized approach.

Genomic instability of circulating tumor DNA (ctDNA) as a prognostic biomarker has not been evaluated in pancreatic cancer. We investigated the role of the genomic instability index of ctDNA in pancreatic ductal adenocarcinoma (PDAC). We prospectively enrolled 315 patients newly diagnosed with resectable (n = 110), locally advanced (n = 78), and metastatic (n = 127) PDAC from March 2015 through January 2020. Low-depth whole-genome cell-free DNA sequencing identified genome-wide copy number alterations using instability score (I-score) to reflect genome-wide instability. Plasma cell-free and matched tumor tissue DNA from 15 patients with resectable pancreatic cancer was sequenced to assess the concordance of chromosomal copy number alteration profiles. Associations of I-score with clinical factors or survival were assessed. Seventy-six patients had high genomic instability with I-score > 7.3 in pre-treatment ctDNA; proportions of high I-score were 5.5%, 5.1%, and 52% in resectable, locally advanced, and metastatic stages, respectively. Correlation coefficients between Z-scores of plasma and tissue DNA at segment resolution were high (r2 = 0.82). Univariable analysis showed the association of I-score with progression-free survival in each stage. Multivariable analyses demonstrated that clinical stage-adjusted I-scores were significant factors for progression-free and overall survival. In these patients, ctDNA genomic I-scores provided prognostic information relevant to progression-free survival in each clinical stage.

The diagnosis of brain metastasis (BM) is commonly observed in non-small cell lung cancer (NSCLC) with poor outcomes. Accordingly, developing an approach to early predict BM response to Gamma Knife radiosurgery (GKRS) may benefit the patient treatment and monitoring. A total of 237 NSCLC patients with BMs (for survival prediction) and 256 patients with 976 BMs (for prediction of local tumor control) treated with GKRS were retrospectively analyzed. All the survival data were recorded without censoring, and the status of local tumor control was determined by comparing the last MRI follow-up in patients’ lives with the pre-GKRS MRI. Overall 1763 radiomic features were extracted from pre-radiosurgical magnetic resonance images. Three prediction models were constructed, using (1) clinical data, (2) radiomic features, and (3) clinical and radiomic features. Support vector machines with a 30% hold-out validation approach were constructed. For treatment outcome predictions, the models derived from both the clinical and radiomics data achieved the best results. For local tumor control, the combined model achieved an area under the curve (AUC) of 0.95, an accuracy of 90%, a sensitivity of 91%, and a specificity of 89%. For patient survival, the combined model achieved an AUC of 0.81, an accuracy of 77%, a sensitivity of 78%, and a specificity of 80%. The pre-radiosurgical radiomics data enhanced the performance of local tumor control and survival prediction models in NSCLC patients with BMs treated with GRKS. An outcome prediction model based on radiomics combined with clinical features may guide therapy in these patients.

We aimed to investigate, whether 18F-2-fluoro-2-desoxy-D-glucose positron emission tomography/computed tomography (FDG-PET/CT) scans performed at baseline (time point 0; TP 0) and three months after initiation of immunotherapy (time point 1; TP 1) can be used on a metastasis- and patient-level to predict the response to immune-checkpoint inhibition using FDG-PET/CT six months after treatment start (time point 2; TP 2) in metastatic melanoma patients. This single-center retrospective study considered metastatic melanoma patients treated with immune checkpoint inhibition from TP 0 to TP 2. An analysis on a metastasis- and patient-level was carried out. Tumor volume, standardized uptake values SUV (mean, maximum, and peak), metabolic tumor volume MTV and total lesion glycolysis TLG of each included metastasis were recorded at each time point, respectively TP 0, TP 1 and TP 2. Total tumor volume, total metabolic tumor volume and total lesion glycolysis per patient were also calculated at TP 0, TP 1 and TP 2. Treatment response was assessed at metastasis- and patient-level based on FDG-PET/CT scans at TP 2. 612 melanoma metastases in 111 patients were included. The analysis on a metastasis-level showed that metastatic SUVpeak at TP 1 and volume variation between TP 0 and TP 1 were the strongest negative predictive biomarkers for response. However, at TP 0, metastatic SUVmean and SUVpeak indicated a low negative prediction power, whereas initial metastatic volume was not a predictive biomarker. Also, melanoma metastases located in bone structures had a negative influence on the outcome at TP 2, particularly in women. The analysis on a patient-level showed, that total tumor volume, total metastatic tumor volume and total lesion glycolysis of all metastases three months after treatment initiation were strong negative predictive biomarkers for response to immunotherapy six months after initiation. Age and female sex were also found to be negative predictive biomarkers with lower predictive power. Interestingly, total tumor volume at TP 0 and number of metastases at TP 0 as well as the occurrence of early immune-related adverse events between TP 0 and TP 2 did not have any predictive value for early treatment response. FDG-PET/CT performed for treatment response assessment three months after initiation of immune checkpoint inhibition in metastatic melanoma patients can also be used to predict early response to treatment. On a metastasis-level SUV peak and volume variation of metastases are strong outcome predictive biomarkers. On a patient-level total tumor volume and semiquantitative parameters such as total metabolic tumor volume MTV and total lesion glycolysis TLG of all metastases are promising outcome predictive biomarkers. Also, early complete response on a metastasis- and patient-level seems to be predictive for lasting complete response.

Carbon Ion Radiotherapy (CIRT) is one of the most promising therapeutic options to reduce Local Recurrence (LR) in Sacral Chordomas (SC). The aim of this work is to compare the performances of survival models fed with dosiomics features and conventional DVH metrics extracted from relative biological effectiveness (RBE)-weighted dose (D RBE ) and dose-averaged Linear Energy Transfer (LET d ) maps, towards the identification of possible prognostic factors for LR in SC patients treated with CIRT. This retrospective study included 50 patients affected by SC with a focus on patients that presented a relapse in a high-dose region. Survival models were built to predict both LR and High-Dose Local Recurrencies (HD-LR). The models were evaluated through Harrell Concordance Index (C-index) and patients were stratified into high/low-risk groups. Local Recurrence-free Kaplan-Meier curves were estimated and evaluated through log-rank tests. The model with highest performance (median(interquartile-range) C-index of 0.86 (0.22)) was built on features extracted from LET d maps, with D RBE models showing promising but weaker results (C-index of 0.83 (0.21), 0.80 (0.21)). Although the study should be extended to a wider patient population, LET d maps show potential as a prognostic factor for SC HD-LR in CIRT, and dosiomics appears to be the most promising approach against more conventional methods (e.g., DVH-based).

Simple Summary: The objective of the study was to evaluate the radiomics features obtained by contrast MRI studies as prognostic biomarkers in colorectal liver metastases patients to predict clinical outcomes following liver resection. We demonstrated a good performance considering the single textural significant metric in the identification of front of tumor growth (expansive versus infiltrative) and tumor budding (high grade versus low grade or absent), in the recognition of mucinous type and in the detection of recurrences. Moreover, considering linear regression models or neural network classifiers in a multivariate approach was possible to increase the performance in terms of accuracy, sensitivity, and specificity. Purpose: To assess radiomics features efficacy obtained by arterial and portal MRI phase in the prediction of clinical outcomes in the colorectal liver metastases patients, evaluating recurrence, mutational status, pathological characteristic (mucinous and tumor budding) and surgical resection margin. Methods: This retrospective analysis was approved by the local Ethical Committee board, and radiological databases were used to select patients with colorectal liver metastases with pathological proof and MRI study in a pre-surgical setting after neoadjuvant chemotherapy. The cohort of patients included a training set (51 patients with 61 years of median age and 121 liver metastases) and an external validation set (30 patients with single lesion with 60 years of median age). For each segmented volume of interest on MRI by two expert radiologists, 851 radiomics features were extracted as median values using the PyRadiomics tool. Non-parametric Kruskal-Wallis test, intraclass correlation, receiver operating characteristic (ROC) analysis, linear regression modelling and pattern recognition methods (support vector machine (SVM), k-nearest neighbors (KNN), artificial neural network (NNET), and decision tree (DT)) were considered. Results: The best predictor to discriminate expansive versus infiltrative tumor growth front was wavelet_LHH_glrlm_ShortRunLowGrayLevelEmphasis extracted on portal phase with accuracy of 82%, sensitivity of 84%, and specificity of 77%. The best predictor to discriminate tumor budding was wavelet_LLH_firstorder_10Percentile extracted on portal phase with accuracy of 92%, a sensitivity of 96%, and a specificity of 81%. The best predictor to differentiate the mucinous type of tumor was the wavelet_LLL_glcm_ClusterTendency extracted on portal phase with accuracy of 88%, a sensitivity of 38%, and a specificity of 100%. The best predictor to identify the recurrence was the wavelet_HLH_ngtdm_Complexity extracted on arterial phase with accuracy of 90%, a sensitivity of 71%, and a specificity of 95%. The best linear regression model was obtained in the identification of mucinous type considering the 13 textural significant metrics extracted by arterial phase (accuracy of 94%, sensitivity of 77% and a specificity of 99%). The best results were obtained in the identification of tumor budding with the eleven textural significant features extracted by arterial phase using a KNN (accuracy of 95%, sensitivity of 84%, and a specificity of 99%). Conclusions: Our results confirmed the capacity of radiomics to identify as biomarkers and several prognostic features that could affect the treatment choice in patients with liver metastases in order to obtain a more personalized approach. [ABSTRACT FROM AUTHOR]

Simple Summary: This prospective cohort study showed that circulating tumor DNA-genomic instability (ctDNA-GI) I-scores, which was defined as the natural logarithm of the sum of LOESS-normalized Z-scores of sequenced reads in 1 Mb bins, are prognostic of the outcome of either localized or metastatic pancreatic adenocarcinoma. At baseline, 24.1% of patients had high genomic instability with I-score. Multivariable analyses demonstrated I-score was a significant factor for progression-free survival and overall survival. Genomic instability of circulating tumor DNA (ctDNA) as a prognostic biomarker has not been evaluated in pancreatic cancer. We investigated the role of the genomic instability index of ctDNA in pancreatic ductal adenocarcinoma (PDAC). We prospectively enrolled 315 patients newly diagnosed with resectable (n = 110), locally advanced (n = 78), and metastatic (n = 127) PDAC from March 2015 through January 2020. Low-depth whole-genome cell-free DNA sequencing identified genome-wide copy number alterations using instability score (I-score) to reflect genome-wide instability. Plasma cell-free and matched tumor tissue DNA from 15 patients with resectable pancreatic cancer was sequenced to assess the concordance of chromosomal copy number alteration profiles. Associations of I-score with clinical factors or survival were assessed. Seventy-six patients had high genomic instability with I-score > 7.3 in pre-treatment ctDNA; proportions of high I-score were 5.5%, 5.1%, and 52% in resectable, locally advanced, and metastatic stages, respectively. Correlation coefficients between Z-scores of plasma and tissue DNA at segment resolution were high (r2 = 0.82). Univariable analysis showed the association of I-score with progression-free survival in each stage. Multivariable analyses demonstrated that clinical stage-adjusted I-scores were significant factors for progression-free and overall survival. In these patients, ctDNA genomic I-scores provided prognostic information relevant to progression-free survival in each clinical stage. [ABSTRACT FROM AUTHOR]

Simple Summary: Non-small cell lung cancer (NSCLC) is the most common cause of brain metastasis (BM). Approximately 50% of patients with metastatic NSCLC harbor BMs. Within the past decade, Gamma Knife radiosurgery (GKRS) has become one of the first-line treatments for BMs. Ability to predict treatment response after GKRS can therefore guide treatment strategy. This study aimed to determine whether pre-radiosurgical neuroimaging radiomics can predict survival and local tumor control after GKRS. Based on the collected magnetic resonance images and clinical characteristics of the 237 NSCLC BM patients with BMs (for survival prediction) and 256 NSCLC patients with 976 BMs (for prediction of local tumor control), we concluded that the identified radiomic features could provide valuable additional information to enhance the prediction of BM responses after GKRS. The proposed approach provided physicians with an intuitive way to predict the patient outcome based on pre-radiosurgical magnetic resonance images. The diagnosis of brain metastasis (BM) is commonly observed in non-small cell lung cancer (NSCLC) with poor outcomes. Accordingly, developing an approach to early predict BM response to Gamma Knife radiosurgery (GKRS) may benefit the patient treatment and monitoring. A total of 237 NSCLC patients with BMs (for survival prediction) and 256 patients with 976 BMs (for prediction of local tumor control) treated with GKRS were retrospectively analyzed. All the survival data were recorded without censoring, and the status of local tumor control was determined by comparing the last MRI follow-up in patients' lives with the pre-GKRS MRI. Overall 1763 radiomic features were extracted from pre-radiosurgical magnetic resonance images. Three prediction models were constructed, using (1) clinical data, (2) radiomic features, and (3) clinical and radiomic features. Support vector machines with a 30% hold-out validation approach were constructed. For treatment outcome predictions, the models derived from both the clinical and radiomics data achieved the best results. For local tumor control, the combined model achieved an area under the curve (AUC) of 0.95, an accuracy of 90%, a sensitivity of 91%, and a specificity of 89%. For patient survival, the combined model achieved an AUC of 0.81, an accuracy of 77%, a sensitivity of 78%, and a specificity of 80%. The pre-radiosurgical radiomics data enhanced the performance of local tumor control and survival prediction models in NSCLC patients with BMs treated with GRKS. An outcome prediction model based on radiomics combined with clinical features may guide therapy in these patients. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma has become the most rapidly increasing cancer in Caucasian populations, causing 90% of skin cancer mortality. FDG-PET/CT has been recommended by the European 2019 guidelines for melanoma for staging and treatment response assessment in advanced melanoma highlighting the need for new outcome predictive biomarkers. In the context of melanoma, the evidence on the predictive value of semiquantitative parameters derived from FDG-PET/CT is still very limited. We here provide evidence, in a large cohort of metastatic melanoma patients, that FDG-PET/CT can be used to predict the early response to immune checkpoint inhibition. On a patient-basis, total tumor volume and semiquantitative parameters, such as total metabolic tumor volume MTV and total lesion glycolysis TLG of all metastases three months after treatment start are promising predictive biomarkers for the outcome in metastatic melanoma patients. Also, early complete response on a metastasis- and patient-level seems to be predictive for lasting complete response. We aimed to investigate, whether 18F-2-fluoro-2-desoxy-D-glucose positron emission tomography/computed tomography (FDG-PET/CT) scans performed at baseline (time point 0; TP 0) and three months after initiation of immunotherapy (time point 1; TP 1) can be used on a metastasis- and patient-level to predict the response to immune-checkpoint inhibition using FDG-PET/CT six months after treatment start (time point 2; TP 2) in metastatic melanoma patients. This single-center retrospective study considered metastatic melanoma patients treated with immune checkpoint inhibition from TP 0 to TP 2. An analysis on a metastasis- and patient-level was carried out. Tumor volume, standardized uptake values SUV (mean, maximum, and peak), metabolic tumor volume MTV and total lesion glycolysis TLG of each included metastasis were recorded at each time point, respectively TP 0, TP 1 and TP 2. Total tumor volume, total metabolic tumor volume and total lesion glycolysis per patient were also calculated at TP 0, TP 1 and TP 2. Treatment response was assessed at metastasis- and patient-level based on FDG-PET/CT scans at TP 2. 612 melanoma metastases in 111 patients were included. The analysis on a metastasis-level showed that metastatic SUVpeak at TP 1 and volume variation between TP 0 and TP 1 were the strongest negative predictive biomarkers for response. However, at TP 0, metastatic SUVmean and SUVpeak indicated a low negative prediction power, whereas initial metastatic volume was not a predictive biomarker. Also, melanoma metastases located in bone structures had a negative influence on the outcome at TP 2, particularly in women. The analysis on a patient-level showed, that total tumor volume, total metastatic tumor volume and total lesion glycolysis of all metastases three months after treatment initiation were strong negative predictive biomarkers for response to immunotherapy six months after initiation. Age and female sex were also found to be negative predictive biomarkers with lower predictive power. Interestingly, total tumor volume at TP 0 and number of metastases at TP 0 as well as the occurrence of early immune-related adverse events between TP 0 and TP 2 did not have any predictive value for early treatment response. FDG-PET/CT performed for treatment response assessment three months after initiation of immune checkpoint inhibition in metastatic melanoma patients can also be used to predict early response to treatment. On a metastasis-level SUV peak and volume variation of metastases are strong outcome predictive biomarkers. On a patient-level total tumor volume and semiquantitative parameters such as total metabolic tumor volume MTV and total lesion glycolysis TLG of all metastases are promising outcome predictive biomarkers. Also, early complete response on a metastasis- and patient-level seems to be predictive for lasting complete response. [ABSTRACT FROM AUTHOR]