Search

Abstract Background Rectal cancer is a common cancer worldwide and lacks effective prognostic markers. The development of prognostic markers by computational pathology methods has attracted increasing attention. This paper aims to construct a prognostic signature from whole slide images for predicting progression-free survival (PFS) of rectal cancer through an unsupervised artificial intelligence algorithm. Methods A total of 238 patients with rectal cancer from two datasets were collected for the development and validation of the prognostic signature. A tumor detection model was built by transfer learning. Then, on the basis of the tumor patches recognized by the tumor detection model, a convolutional autoencoder model was built for decoding the tumor patches into deep latent features. Next, on the basis of the deep latent features, the tumor patches were divided into different clusters. The cluster number and other hyperparameters were optimized by a nested cross-validation method. The percentage of each cluster from the patient’s tumor patches, which is hereafter called PCF, was calculated for prognostic signature construction. The prognostic signature was constructed by Cox proportional hazard regression with L2 regularization. Finally, bioinformatic analysis was performed to explore the underlying biological mechanisms of the PCFs. Results The accuracy of the tumor detection model in distinguishing tumor patches from non-tumor patches achieved 99.3%. The optimal cluster number was determined to be 9. Therfore, 9 PCFs were calculated to construct the prognostic signature. The prognostic signature achieved a concordance index of 0.701 in the validation cohort. The Kaplan-Meier survival curves showed the prognostic signature had good risk stratification ability. Through the bioinformatic analysis, several PCF-associated genes were identified. These genes were enriched in various gene ontology terms. Conclusion The developed prognostic signature can effectively predict PFS in patients with rectal cancer and exploration of the underlying biological mechanisms may help to promote its clinical translation.

The current standard of care for anal squamous cell carcinoma (ASCC) is definitive concurrent chemoradiotherapy (CRT). However, about a third of patients may experience treatment failure. Recently, immunotherapy has emerged as a novel strategy for metastatic ASCC patients. We evaluated the efficacy and safety of surgery, CRT alone, and CRT with immunotherapy (CRT-I) in 100 nonmetastatic ASCC patients, treated from April 2012 through May 2023, by determining survival outcomes and acute adverse events. The median (range) follow-up was 30.7 (7.6 to 134.9) months. The study cohort 3-year overall survival (OS), progression-free survival (PFS), distant metastasis-free survival (DMFS), and locoregional recurrence-free survival (LRFS) rates were 80.7 %, 62.2 %, 71.1 %, and 67.6 %, respectively. The Surgery group had significantly lower rates than the CRT and CRT-I groups for 3-year PFS (33.1% vs. 65.2% vs. 92.9 %, P < 0.001), DMFS (46.7% vs. 74.6% vs. 92.9 %, P = 0.002) and LRFS (37.0% vs. 73.3% vs. 92.9 %, P < 0.001), respectively. All patients receiving CRT-I were alive at last follow-up. Of 100 patients, 26 (26.0 %) experienced severe (≥ grade 3) acute toxicity. Of 24 patients receiving CRT-I, 8 (33.3 %) had severe acute toxicity. Using immunohistochemistry, peritumoural stromal infiltration by CD8+ T cells was significantly higher after CRT-I compared to before CRT-I and to after CRT alone. The addition of immunotherapy to CRT may be an effective first-line treatment option with favourable survival outcomes and acceptable toxicity for patients with ASCC. A prospective, randomized trial assessing the efficacy of CRT combined with a PD-1 inhibitor in patients with locally advanced ASCC is in progress.

Abstract Liver cancer is one of the most common malignant tumors worldwide. Although some progress has been made in the diagnosis and treatment of Hepatocellular carcinoma (HCC), the diagnosis and treatment of HCC is still facing great challenges because of the high mortality rate and poor prognosis of HCC. The purpose of this study was to explore the relationship between adhesion-regulating molecule1 (ADRM1), and liver cancer, and the relationship between prognoses. ADRM1 is highly expressed in tumors and is closely associated with the prognosis of patients with liver cancer. In our previous study, we found that ADRM1 was highly expressed in HCC and was closely related to tumor immune and immune checkpoint levels in HCC. We validated the immune expression of ADRM1 in liver cancer cells using flow cytometry. In hepatocellular carcinoma tissues, miR-891a-5p regulates ADRM1. Upregulation of miR-891a-5p upregulates ADRM1, and downregulation of miR-891a-5p downregulates ADRM1. It is suggested that ADRM1 plays a key role in the occurrence and development of hepatocellular carcinoma. This study is expected to provide new ideas for the research and development of anti-HCC drugs targeting miR-891a-5p/ADRM1. However, further trials are needed to confirm these results and explore the actual results in patients with HCC.

Abstract Background Patients with DNA mismatch repair‐proficient/microsatellite stable (pMMR/MSS) colorectal cancer (CRC), which accounts for 85% of all CRC cases, display a poor respond to immune checkpoint inhibitors (i.e., anti‐PD‐1 antibodies). pMMR/MSS CRC patients with locally advanced cancers need effective combined therapies. Methods In this pilot study, we administered six preoperative doses of each 2‐week cycle of the anti‐PD‐1 antibody sintilimab (at a fixed dose of 200 mg), oxaliplatin, and 5‐FU/CF (mFOLFOX6) combined with five doses of bevacizumab (the number of doses was reduced to prevent surgical delays) to patients with cT4NxM0 colon or upper rectal cancers. And radical surgery was performed approximately 2 weeks after the last dose of neoadjuvant therapy. The primary endpoint was a pathologic complete response (pCR). We also evaluated major pathologic response (MPR, ≤10% residual viable tumor), radiological and pathological regression, safety, and tumor mutation burden (TMB), and tumor microenvironment (TME) characteristics. Results By the cutoff date (September 2023), 22 patients with cT4NxM0 pMMR/MSS colon or upper rectal cancers were enrolled and the median follow‐up was 24.7 months (IQR: 21.1–26.1). All patients underwent R0 surgical resection without treatment‐related surgical delays. pCR occurred in 12 of 22 resected tumors (54.5%) and MPR occurred in 18 of 22 (81.8%) patients. At the cutoff date, all patients were alive, and 21/22 were recurrence‐free. Treatment‐related adverse events of grade 3 or higher occurred in of 2/22 (9.1%) patients. Among the pCR tumors, two were found to harbor POLE mutations. The degree of pathological regression was significantly greater than that of radiological regression (p = 1.35 × 10−8). The number of CD3+/CD4+ cells in the tumor and stroma in pretreated biopsied tissues was markedly lower in pCR tumors than in non‐pCR tumors (p = 0.038 and p = 0.015, respectively). Conclusions Neoadjuvant sintilimab combined with bevacizumab and mFOLFOX6 was associated with few side effects, did not delay surgery, and led to pCR and non‐pCR in 54.5% and 81.8% of the cases, respectively. Downregulation of CD3/CD4 expression in the tumor and stroma is related to pCR. However, the molecular mechanisms underlying PD‐1 blockade‐enhanced targeted chemotherapy require further investigation.

Abstract Background This study was to establish and validate prediction models to predict the cancer-specific survival (CSS) and overall survival (OS) of small-cell lung cancer (SCLC) patients with liver metastasis. Methods In the retrospective cohort study, SCLC patients with liver metastasis between 2010 and 2015 were retrospectively retrieved from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were randomly divided into the training group and testing group (3: 1 ratio). The Cox proportional hazards model was used to determine the predictive factors for CSS and OS in SCLC with liver metastasis. The prediction models were conducted based on the predictive factors. The performances of the prediction models were evaluated by concordance indexes (C-index), and calibration plots. The clinical value of the models was evaluated by decision curve analysis (DCA). Results In total, 8,587 patients were included, with 154 patients experiencing CSS and 154 patients experiencing OS. The median follow-up was 3 months. Age, gender, marital status, N stage, lung metastases, multiple metastases surgery of metastatic site, chemotherapy, and radiotherapy were independent predictive factors for the CSS and OS of SCLC patients with liver metastasis. The prediction models presented good performances of CSS and OS among patients with liver metastasis, with the C-index for CSS being 0.724, whereas the C-index for OS was 0.732, in the training set. The calibration curve showed a high degree of consistency between the actual and predicted CSS and OS. DCA suggested that the prediction models provided greater net clinical benefit to these patients. Conclusion Our prediction models showed good predictive performance for the CSS and OS among SCLC patients with liver metastasis. Our developed nomograms may help clinicians predict CSS and OS in SCLC patients with liver metastasis.

Abstract Background Lymph node metastasis (LNM) is a prognostic biomarker and affects therapeutic selection in colorectal cancer (CRC). Current evaluation methods are not adequate for estimating LNM in CRC. H&E images contain much pathological information, and collagen also affects the biological behavior of tumor cells. Hence, the objective of the study is to investigate whether a fully quantitative pathomics-collagen signature (PCS) in the tumor microenvironment can be used to predict LNM. Methods Patients with histologically confirmed stage I-III CRC who underwent radical surgery were included in the training cohort (n = 329), the internal validation cohort (n = 329), and the external validation cohort (n = 315). Fully quantitative pathomics features and collagen features were extracted from digital H&E images and multiphoton images of specimens, respectively. LASSO regression was utilized to develop the PCS. Then, a PCS-nomogram was constructed incorporating the PCS and clinicopathological predictors for estimating LNM in the training cohort. The performance of the PCS-nomogram was evaluated via calibration, discrimination, and clinical usefulness. Furthermore, the PCS-nomogram was tested in internal and external validation cohorts. Results By LASSO regression, the PCS was developed based on 11 pathomics and 9 collagen features. A significant association was found between the PCS and LNM in the three cohorts (P

Abstract Accurate identification of the physiological intersegmental plane is crucial for successful anatomical segmentectomy. Current techniques, such as the inflation‐deflation method, may result in uncertain cutting lines, leading to unsuitable resection extents. Here, we demonstrated the successful use of electromagnetic navigation with methylene blue dye‐marking to preoperatively and precisely identify the physiological intersegmental plane in two patients with small‐sized peripheral non‐small cell lung cancer (NSCLC). This novel technique offers the potential for precise cutting lines that align closely with the physiological intersegmental plane, thus improving the accuracy and efficacy of anatomical segmentectomy for these selected NSCLC patients.

ObjectiveTo investigate the performance of a novel feature fusion radiomics (RFF) model that incorporates features from multiparametric MRIs (mpMRI) in distinguishing different statuses of molecular receptors in breast cancer (BC) preoperatively.Methods460 patients with 466 pathology-confirmed BCs who underwent breast mpMRI at 1.5T in our center were retrospectively included hormone receptor (HR) positive (HR+) (n=336) and HR negative (HR-) (n=130). The HR- patients were further categorized into human epidermal growth factor receptor 2 (HER-2) enriched BC (HEBC) (n=76) and triple negative BC (TNBC) (n=54). All lesions were divided into a training/validation cohort (n=337) and a test cohort (n=129). Volumes of interest (VOIs) delineation, followed by radiomics feature extraction, was performed on T2WI, DWI600 (b=600 s/mm2), DWI800 (b=800 s/mm2), ADC map, and DCE1-6 (six continuous DCE-MRI) images of each lesion. Simulating a radiologist’s work pattern, 150 classification base models were constructed and analyzed to determine the top four optimum sequences for classifying HR+ vs. HR-, TNBC vs. HEBC, TNBC vs. non-TNBC in a random selected training cohort (n=337). Building upon these findings, the optimal single sequence models (Rss) and combined sequences models (RFF) were developed. The AUC, sensitivity, accuracy and specificity of each model for subtype differentiation were evaluated. The paired samples Wilcoxon signed rank test was used for performance comparison.ResultsDuring the three classification tasks, the optimal single sequence for classifying HR+ vs. HR- was DWI600, while the ADC map, derived from DWI800 performed the best in distinguishing TNBC vs. HEBC, as well as identifying TNBC vs. non-TNBC, with corresponding training AUC values of 0.787, 0.788, and 0.809, respectively. Furthermore, the integration of the top four sequences in RFF models yielded improved performance, achieving AUC values of 0.809, 0.805 and 0.847, respectively. Consistent results was observed in both the training/validation and testing cohorts, with AUC values of 0.778, 0.787, 0.818 and 0.726, 0.773, 0.773, respectively (all p < 0.05 except HR+ vs. HR-).ConclusionThe RFF model, integrating mpMRI radiomics features, demonstrated promising ability to mimic radiologists’ diagnosis for preoperative identification of molecular receptors of BC.

The non-destructive study of soil micromorphology via computed tomography (CT) imaging has yielded significant insights into the three-dimensional configuration of soil pores. Precise pore analysis is contingent on the accurate transformation of CT images into binary image representations. Notably, segmentation of 2D CT images frequently harbors inaccuracies. This paper introduces a novel three-dimensional pore segmentation method, BDULSTM, which integrates U-Net with convolutional long short-term memory (CLSTM) networks to harness sequence data from CT images and enhance the precision of pore segmentation. The BDULSTM method employs an encoder–decoder framework to holistically extract image features, utilizing skip connections to further refine the segmentation accuracy of soil structure. Specifically, the CLSTM component, critical for analyzing sequential information in soil CT images, is strategically positioned at the juncture of the encoder and decoder within the U-shaped network architecture. The validation of our method confirms its efficacy in advancing the accuracy of soil pore segmentation beyond that of previous deep learning techniques, such as U-Net and CLSTM independently. Indeed, BDULSTM exhibits superior segmentation capabilities across a diverse array of soil conditions. In summary, BDULSTM represents a state-of-the-art artificial intelligence technology for the 3D segmentation of soil pores and offers a promising tool for analyzing pore structure and soil quality.

Abstract The current tumor‐node‐metastasis staging system does not provide sufficient prognostic prediction or adjuvant chemotherapy benefit information for stage II‐III colon cancer (CC) patients. Collagen in the tumor microenvironment affects the biological behaviors and chemotherapy response of cancer cells. Hence, in this study, we proposed a collagen deep learning (collagenDL) classifier based on the 50‐layer residual network model for predicting disease‐free survival (DFS) and overall survival (OS). The collagenDL classifier was significantly associated with DFS and OS (P

Abstract Bronchial carcinoid tumors are low‐grade malignant and lung‐sparing surgery is preferred for the removal of these tumors. We describe a surgical technique of robot‐assisted sleeve segmentectomy via single utility port approach with three robotic arms. This operation was performed in an aged patient with decreased pulmonary function, whose carcinoid tumor was located at the origin of the right superior segmental bronchus. A 1.5‐cm incision was performed in the eighth intercostal space of the midaxillary line and another 4‐cm incision was made in the fifth intercostal space of the anterior axillary line. Postoperative recovery of the patient was smooth without postoperative complications.

BackgroundEndoscopic submucosal dissection has become the primary option of treatment for early gastric cancer. However, lymph node metastasis may lead to poor prognosis. We analyzed factors related to lymph node metastasis in EGC patients, and we developed a construction prediction model with machine learning using data from a retrospective series.MethodsTwo independent cohorts’ series were evaluated including 305 patients with EGC from China as cohort I and 35 patients from Spain as cohort II. Five classifiers obtained from machine learning were selected to establish a robust prediction model for lymph node metastasis in EGC.ResultsThe clinical variables such as invasion depth, histologic type, ulceration, tumor location, tumor size, Lauren classification, and age were selected to establish the five prediction models: linear support vector classifier (Linear SVC), logistic regression model, extreme gradient boosting model (XGBoost), light gradient boosting machine model (LightGBM), and Gaussian process classification model. Interestingly, all prediction models of cohort I showed accuracy between 70 and 81%. Furthermore, the prediction models of the cohort II exhibited accuracy between 48 and 82%. The areas under curve (AUC) of the five models between cohort I and cohort II were between 0.736 and 0.830.ConclusionsOur results support that the machine learning method could be used to predict lymph node metastasis in early gastric cancer and perhaps provide another evaluation method to choose the suited treatment for patients.