Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts.

Autor:	Fremond S; Department of Pathology, Leiden University Medical Center, Leiden, Netherlands., Andani S; Department of Computer Science, ETH Zurich, Zurich, Switzerland; Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zurich, Zurich, Switzerland; Swiss Institute of Bioinformatics, Lausanne, Switzerland., Barkey Wolf J; Department of Pathology, Leiden University Medical Center, Leiden, Netherlands., Dijkstra J; Department of Vascular and Molecular Imaging, Leiden University Medical Center, Leiden, Netherlands., Melsbach S; Department of Pathology, Leiden University Medical Center, Leiden, Netherlands., Jobsen JJ; Department of Radiation Oncology, Medisch Spectrum Twente, Enschede, Netherlands., Brinkhuis M; Department of Pathology, LabPON, Hengelo, Netherlands., Roothaan S; Department of Pathology, LabPON, Hengelo, Netherlands., Jurgenliemk-Schulz I; Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, Netherlands., Lutgens LCHW; Department of Radiation Oncology, Maastricht University Medical Center+, Maastricht, Netherlands., Nout RA; Department of Radiation Oncology, Erasmus University Medical Center, Rotterdam, Netherlands., van der Steen-Banasik EM; Department of Radiation Oncology, Radiotherapiegroep, Arnhem, Netherlands., de Boer SM; Department of Radiation Oncology, Leiden University Medical Center, Leiden, Netherlands., Powell ME; Department of Clinical Oncology, Barts Health NHS Trust, London, UK., Singh N; Department of Pathology, Barts Health NHS Trust, London, UK., Mileshkin LR; Department of Medical Oncology, Peter MacCallum Cancer Center, Melbourne, VIC, Australia., Mackay HJ; Department of Medical Oncology and Hematology, Odette Cancer Center Sunnybrook Health Sciences Center, Toronto, ON, Canada., Leary A; Medical Oncology Department, Gustave Roussy Institute, Villejuif, France., Nijman HW; Department of Obstetrics and Gynecology, University Medical Center Groningen, Groningen, Netherlands., Smit VTHBM; Department of Pathology, Leiden University Medical Center, Leiden, Netherlands., Creutzberg CL; Department of Radiation Oncology, Leiden University Medical Center, Leiden, Netherlands., Horeweg N; Department of Radiation Oncology, Leiden University Medical Center, Leiden, Netherlands., Koelzer VH; Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zurich, Zurich, Switzerland. Electronic address: viktor.koelzer@usz.ch., Bosse T; Department of Pathology, Leiden University Medical Center, Leiden, Netherlands. Electronic address: t.bosse@lumc.nl.
Jazyk:	angličtina
Zdroj:	The Lancet. Digital health [Lancet Digit Health] 2023 Feb; Vol. 5 (2), pp. e71-e82. Date of Electronic Publication: 2022 Dec 07.
DOI:	10.1016/S2589-7500(22)00210-2
Abstrakt:	Background: Endometrial cancer can be molecularly classified into POLE mut , 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 POLE mut 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 μm resized to 224 × 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 0·874 (95% CI 0·856-0·893) on four-fold cross-validation and 0·876 on the independent test set. The class-wise AUROCs were 0·849 for POLE mut (n=51), 0·844 for MMRd (n=134), 0·883 for NSMP (n=120), and 0·928 for p53abn (n=88). POLE mut and MMRd tiles had a high density of lymphocytes, p53abn tiles had strong nuclear atypia, and the morphology of POLE mut 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<0·0001). 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=0·30). 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=0·13). Patients with MMRd endometrial cancer predicted as POLE mut had an excellent prognosis, as do those with true POLE mut 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. Funding: The Hanarth Foundation, the Promedica Foundation, and the Swiss Federal Institutes of Technology. Competing Interests: Declaration of interests HWN and JJJ declare grants from Merck, NH declares grants from Varian, and VHK declares research funding from Roche, unrelated to the subject of this manuscript. All other authors declare no competing interests. (Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu