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

Sarah Fremond, Sonali Andani, Jurriaan Barkey Wolf, Jouke Dijkstra, Sinéad Melsbach, Jan J. Jobsen, Mariel Brinkhuis, Suzan Roothaan, Ina Jurgenliemk-Schulz, Ludy C.H.W. Lutgens, Remi A. Nout, Elzbieta M. van der Steen-Banasik, Stephanie M. de Boer, Melanie E. Powell, Naveena Singh, Linda R. Mileshkin, Helen J. Mackay, Alexandra Leary, Hans W. Nijman, Vincent T.H.B.M. SmitCarien L. Creutzberg, Nanda Horeweg, Viktor H. Koelzer*, Tjalling Bosse*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

21 Citations (Scopus)
99 Downloads (Pure)

Abstract

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 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 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 POLEmut (n=51), 0·844 for MMRd (n=134), 0·883 for NSMP (n=120), and 0·928 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<0·0001). 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 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. Funding: The Hanarth Foundation, the Promedica Foundation, and the Swiss Federal Institutes of Technology.

Original languageEnglish
Pages (from-to)e71-e82
JournalThe Lancet Digital Health
Volume5
Issue number2
Early online dateFeb 2022
DOIs
Publication statusPublished - Feb 2023

Bibliographical note

Funding Information:
The PORTEC-1, PORTEC-2, and PORTEC-3 trials were supported by grants from the Dutch Cancer Society (CKTO 90–01, CKTO 2001–04, and CKTO 2006–04, respectively), and HWN, JJJ, and NH received grants from the Dutch Cancer Society unrelated to the subject of this manuscript. This study was supported by a translational research project grant from the Hanarth Foundation and the Swiss Federal Institutes of Technology (strategic focus area of personalised health and related technologies; 2021–367) and a grant from the Promedica Foundation (F-87701–41–01) during the conduct of the study. We thank the participants, investigators, and pathologists who recruited patients and collected samples in the PORTEC-1, PORTEC-2, and PORTEC-3 randomised trials. We thank the PORTEC-3 study group and the TransPORTEC Research Consortium for the establishment of the TransPORTEC biobank and JJJ and investigators of the prospective MST cohort. We thank the Netherlands Cancer Institute for the use of their 3DHISTECH P1000 scanner, and Tessa Rutten and Natalja ter Haar, Leiden University Medical Center, Leiden, the Netherlands, for excellent technical support. We express our gratitude towards Gunnar Rätsch, ETH Zurich, Zurich, Switzerland, for providing valuable feedback, thesis supervision, and sharing his biomedical expertise during the course of the project.

Funding Information:
The PORTEC-1, PORTEC-2, and PORTEC-3 trials were supported by grants from the Dutch Cancer Society (CKTO 90–01, CKTO 2001–04, and CKTO 2006–04, respectively), and HWN, JJJ, and NH received grants from the Dutch Cancer Society unrelated to the subject of this manuscript. This study was supported by a translational research project grant from the Hanarth Foundation and the Swiss Federal Institutes of Technology (strategic focus area of personalised health and related technologies; 2021–367) and a grant from the Promedica Foundation (F-87701–41–01) during the conduct of the study. We thank the participants, investigators, and pathologists who recruited patients and collected samples in the PORTEC-1, PORTEC-2, and PORTEC-3 randomised trials. We thank the PORTEC-3 study group and the TransPORTEC Research Consortium for the establishment of the TransPORTEC biobank and JJJ and investigators of the prospective MST cohort. We thank the Netherlands Cancer Institute for the use of their 3DHISTECH P1000 scanner, and Tessa Rutten and Natalja ter Haar, Leiden University Medical Center, Leiden, the Netherlands, for excellent technical support. We express our gratitude towards Gunnar Rätsch, ETH Zurich, Zurich, Switzerland, for providing valuable feedback, thesis supervision, and sharing his biomedical expertise during the course of the project.

Publisher Copyright:
© 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license

Fingerprint

Dive into the research topics of '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'. Together they form a unique fingerprint.

Cite this