Background Endometrial cancer can be molecularly classified into POLEmut , mismatch repair deficient (MMRd), p53 abnormal (p53abn), and no specific molecular profile (NSMP) subgroups. We aimed to... Show moreBackground Endometrial cancer can be molecularly classified into POLEmut , mismatch repair deficient (MMRd), p53 abnormal (p53abn), and no specific molecular profile (NSMP) subgroups. We aimed to develop an interpretable deep learning pipeline for whole-slide-image-based prediction of the four molecular classes in endometrial cancer (im4MEC), to identify morpho-molecular correlates, and to refine prognostication. Methods This combined analysis included diagnostic haematoxylin and eosin-stained slides and molecular and clinicopathological data from 2028 patients with intermediate-to-high-risk endometrial cancer from the PORTEC-1 (n=466), PORTEC-2 (n=375), and PORTEC-3 (n=393) randomised trials and the TransPORTEC pilot study (n=110), the Medisch Spectrum Twente cohort (n=242), a case series of patients with POLEmut endometrial cancer in the Leiden Endometrial Cancer Repository (n=47), and The Cancer Genome Atlas-Uterine Corpus Endometrial Carcinoma cohort (n=395). PORTEC-3 was held out as an independent test set and a four-fold cross validation was performed. Performance was measured with the macro and class-wise area under the receiver operating characteristic curve (AUROC). Whole-slide images were segmented into tiles of 360 & mu;m resized to 224 x 224 pixels. im4MEC was trained to learn tile-level morphological features with self-supervised learning and to molecularly classify whole-slide images with an attention mechanism. The top 20 tiles with the highest attention scores were reviewed to identify morpho-molecular correlates. Predictions of a nuclear classification deep learning model serve to derive interpretable morphological features. We analysed 5-year recurrence-free survival and explored prognostic refinement by molecular class using the Kaplan-Meier method. Findings im4MEC attained macro-average AUROCs of 0 & BULL;874 (95% CI 0 & BULL;856-0 & BULL;893) on four-fold cross-validation and 0 & BULL;876 on the independent test set. The class-wise AUROCs were 0 & BULL;849 for POLEmut (n=51), 0 & BULL;844 for MMRd (n=134), 0 & BULL;883 for NSMP (n=120), and 0 & BULL;928 for p53abn (n=88). POLEmut and MMRd tiles had a high density of lymphocytes, p53abn tiles had strong nuclear atypia, and the morphology of POLEmut and MMRd endometrial cancer overlapped. im4MEC highlighted a low tumour-to-stroma ratio as a potentially novel characteristic feature of the NSMP class. 5-year recurrence-free survival was significantly different between im4MEC predicted molecular classes in PORTEC-3 (log-rank p<0 & BULL;0001). The ten patients with aggressive p53abn endometrial cancer that was predicted as MMRd showed inflammatory morphology and appeared to have a better prognosis than patients with correctly predicted p53abn endometrial cancer (p=0 & BULL;30). The four patients with NSMP endometrial cancer that was predicted as p53abn showed higher nuclear atypia and appeared to have a worse prognosis than patients with correctly predicted NSMP (p=0 & BULL;13). Patients with MMRd endometrial cancer predicted as POLEmut had an excellent prognosis, as do those with true POLEmut endometrial cancer. Interpretation We present the first interpretable deep learning model, im4MEC, for haematoxylin and eosin-based prediction of molecular endometrial cancer classification. im4MEC robustly identified morpho-molecular correlates and could enable further prognostic refinement of patients with endometrial cancer. Copyright & COPY; 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Show less
Background Histopathological assessment of transplant biopsies is currently the standard method to diagnose allograft rejection and can help guide patient management, but it is one of the most... Show moreBackground Histopathological assessment of transplant biopsies is currently the standard method to diagnose allograft rejection and can help guide patient management, but it is one of the most challenging areas of pathology, requiring considerable expertise, time, and effort. We aimed to analyse the utility of deep learning to preclassify histology of kidney allograft biopsies into three main broad categories (ie, normal, rejection, and other diseases) as a potential biopsy triage system focusing on transplant rejection.Methods We performed a retrospective, multicentre, proof-of-concept study using 5844 digital whole slide images of kidney allograft biopsies from 1948 patients. Kidney allograft biopsy samples were identified by a database search in the Departments of Pathology of the Amsterdam UMC, Amsterdam, Netherlands (1130 patients) and the University Medical Center Utrecht, Utrecht, Netherlands (717 patients). 101 consecutive kidney transplant biopsies were identified in the archive of the Institute of Pathology, RWTH Aachen University Hospital, Aachen, Germany. Convolutional neural networks (CNNs) were trained to classify allograft biopsies as normal, rejection, or other diseases. Three times cross-validation (1847 patients) and deployment on an external real-world cohort (101 patients) were used for validation. Area under the receiver operating characteristic curve (AUROC) was used as the main performance metric (the primary endpoint to assess CNN performance).Findings Serial CNNs, first classifying kidney allograft biopsies as normal (AUROC 0.87 [ten times bootstrapped CI 0.85-0.88]) and disease (0.87 [0.86-0.88]), followed by a second CNN classifying biopsies classified as disease into rejection (0.75 [0.73-0.76]) and other diseases (0.75 [0.72-0.77]), showed similar AUROC in cross-validation and deployment on independent real-world data (first CNN normal AUROC 0.83 [0.80-0.85], disease 0.83 [0.73-0.91]; second CNN rejection 0.61 [0.51-0.70], other diseases 0.61 [0.50-4.74]). A single CNN classifying biopsies as normal, rejection, or other diseases showed similar performance in cross-validation (normal AUROC 0.80 [0.73-0.84], rejection 0.76 [0.66-0.80], other diseases 0.50 [0.36-0.57]) and generalised well for normal and rejection classes in the real-world data. Visualisation techniques highlighted rejection-relevant areas of biopsies in the tubulointerstitium.Interpretation This study showed that deep learning-based classification of transplant biopsies could support pathological diagnostics of kidney allograft rejection. Copyright (C) 2021 The Author(s). Published by Elsevier Ltd. Show less
