{"id":{"repo_id":"milano","oai_identifier":"oai:air.unimi.it:2434/1200216"},"canonical_url":"https://search.dev.ndltd.org/etd/milano/oai:air.unimi.it:2434/1200216","repository":{"repo_id":"milano","name":"Università degli Studi di Milano","base_url":"https://air.unimi.it/oai/request"},"display":{"title":"DEEP LEARNING ALGORITHM FOR MOLECULAR CLASSIFICATION OF ENDOMETRIAL CANCER FROM WHOLE SLIDE HISTOPATHOLOGY IMAGES","abstract":"Endometrial cancer (EC) is a common malignancy whose molecular classification (POLEmut, MMRd, p53-abn, NSMP) guides prognosis and treatment. While MMRd and p53-abn can be assessed through IHC, POLEmut identification requires gene sequencing, which is costly and often unavailable. In this study, we developed a fully supervised deep learning (DL) model to classify EC molecular subtypes directly from H&E-stained whole-slide images (WSIs). From an initial cohort of 1,362 cases, 230 FFPE WSIs were selected and annotated to train three sequential binary classifiers (POLEmut vs non-POLE, MMRd vs non-MMRd, p53-abn vs NSMP), forming a hierarchical, clinically aligned architecture. Prediction heatmaps were generated to enhance interpretability. The model showed excellent performance for POLEmut (AUROC 0.95; accuracy 87.5%; F1 0.86) and good performance for MMRd (AUROC 0.88; F1 0.81) and p53-abn (accuracy 74%; F1 0.70). Overall, it achieved an average precision of 76% and recall of 88%. These results demonstrate the feasibility of DL-based prediction of EC molecular subtypes from routine histology, offering a scalable approach to support diagnostic workflows and expand access to precision oncology where molecular assays are limited.","abstract_html":"Endometrial cancer (EC) is a common malignancy whose molecular classification (POLEmut, MMRd, p53-abn, NSMP) guides prognosis and treatment. While MMRd and p53-abn can be assessed through IHC, POLEmut identification requires gene sequencing, which is costly and often unavailable. In this study, we developed a fully supervised deep learning (DL) model to classify EC molecular subtypes directly from H&E-stained whole-slide images (WSIs). From an initial cohort of 1,362 cases, 230 FFPE WSIs were selected and annotated to train three sequential binary classifiers (POLEmut vs non-POLE, MMRd vs non-MMRd, p53-abn vs NSMP), forming a hierarchical, clinically aligned architecture. Prediction heatmaps were generated to enhance interpretability. The model showed excellent performance for POLEmut (AUROC 0.95; accuracy 87.5%; F1 0.86) and good performance for MMRd (AUROC 0.88; F1 0.81) and p53-abn (accuracy 74%; F1 0.70). Overall, it achieved an average precision of 76% and recall of 88%. These results demonstrate the feasibility of DL-based prediction of EC molecular subtypes from routine histology, offering a scalable approach to support diagnostic workflows and expand access to precision oncology where molecular assays are limited.","abstract_has_math":false,"creators":["FRASCARELLI, CHIARA"],"institution":"Università degli Studi di Milano","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["tutor: N. Fusco ; co-tutor: E. Guerini Rocco ; phd coordinator: M. S. Clerici","C. Frascarelli","FUSCO, NICOLA","GUERINI ROCCO, ELENA","CLERICI, MARIO SALVATORE"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-01-22","date_published":"2026-01-22","updated_at":"2026-07-27T20:18:53Z","subjects":["Endometrial cancer","Molecular classification","Deep learning","Whole-slide imaging","Precision Oncology","Settore MEDS-09/A - Oncologia medica","Settore INFO-01/A - Informatica"],"languages":["eng"],"rights":["info:eu-repo/semantics/embargoedAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-sa/4.0/"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2434/1200216","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["tutor: N. Fusco ; co-tutor: E. Guerini Rocco ; phd coordinator: M. S. Clerici","C. Frascarelli","FUSCO, NICOLA","GUERINI ROCCO, ELENA","CLERICI, MARIO SALVATORE"]},{"key":"dc:creator","label":"Author","values":["FRASCARELLI, CHIARA"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-01-22"]},{"key":"dc:publisher","label":"Institution","values":["Università degli Studi di Milano"]},{"key":"dc:relation","label":"Dc Relation","values":["numberofpages:115"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/doctoralThesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Endometrial cancer","Molecular classification","Deep learning","Whole-slide imaging","Precision Oncology","Settore MEDS-09/A - Oncologia medica","Settore INFO-01/A - Informatica"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/embargoedAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2434/1200216"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Endometrial cancer (EC) is a common malignancy whose molecular classification (POLEmut, MMRd, p53-abn, NSMP) guides prognosis and treatment. While MMRd and p53-abn can be assessed through IHC, POLEmut identification requires gene sequencing, which is costly and often unavailable. In this study, we developed a fully supervised deep learning (DL) model to classify EC molecular subtypes directly from H&E-stained whole-slide images (WSIs). From an initial cohort of 1,362 cases, 230 FFPE WSIs were selected and annotated to train three sequential binary classifiers (POLEmut vs non-POLE, MMRd vs non-MMRd, p53-abn vs NSMP), forming a hierarchical, clinically aligned architecture. Prediction heatmaps were generated to enhance interpretability. The model showed excellent performance for POLEmut (AUROC 0.95; accuracy 87.5%; F1 0.86) and good performance for MMRd (AUROC 0.88; F1 0.81) and p53-abn (accuracy 74%; F1 0.70). Overall, it achieved an average precision of 76% and recall of 88%. These results demonstrate the feasibility of DL-based prediction of EC molecular subtypes from routine histology, offering a scalable approach to support diagnostic workflows and expand access to precision oncology where molecular assays are limited."]},{"key":"dc:title","label":"Title","values":["DEEP LEARNING ALGORITHM FOR MOLECULAR CLASSIFICATION OF ENDOMETRIAL CANCER FROM WHOLE SLIDE HISTOPATHOLOGY IMAGES"]}]}],"canonical_facts":{"dc:contributor":["tutor: N. Fusco ; co-tutor: E. Guerini Rocco ; phd coordinator: M. S. Clerici","C. Frascarelli","FUSCO, NICOLA","GUERINI ROCCO, ELENA","CLERICI, MARIO SALVATORE"],"dc:creator":["FRASCARELLI, CHIARA"],"dc:date":["2026-01-22"],"dc:description":["Endometrial cancer (EC) is a common malignancy whose molecular classification (POLEmut, MMRd, p53-abn, NSMP) guides prognosis and treatment. While MMRd and p53-abn can be assessed through IHC, POLEmut identification requires gene sequencing, which is costly and often unavailable. In this study, we developed a fully supervised deep learning (DL) model to classify EC molecular subtypes directly from H&E-stained whole-slide images (WSIs). From an initial cohort of 1,362 cases, 230 FFPE WSIs were selected and annotated to train three sequential binary classifiers (POLEmut vs non-POLE, MMRd vs non-MMRd, p53-abn vs NSMP), forming a hierarchical, clinically aligned architecture. Prediction heatmaps were generated to enhance interpretability. The model showed excellent performance for POLEmut (AUROC 0.95; accuracy 87.5%; F1 0.86) and good performance for MMRd (AUROC 0.88; F1 0.81) and p53-abn (accuracy 74%; F1 0.70). Overall, it achieved an average precision of 76% and recall of 88%. These results demonstrate the feasibility of DL-based prediction of EC molecular subtypes from routine histology, offering a scalable approach to support diagnostic workflows and expand access to precision oncology where molecular assays are limited."],"dc:identifier":["https://hdl.handle.net/2434/1200216"],"dc:language":["eng"],"dc:publisher":["Università degli Studi di Milano"],"dc:relation":["numberofpages:115"],"dc:rights":["info:eu-repo/semantics/embargoedAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-sa/4.0/"],"dc:subject":["Endometrial cancer","Molecular classification","Deep learning","Whole-slide imaging","Precision Oncology","Settore MEDS-09/A - Oncologia medica","Settore INFO-01/A - Informatica"],"dc:title":["DEEP LEARNING ALGORITHM FOR MOLECULAR CLASSIFICATION OF ENDOMETRIAL CANCER FROM WHOLE SLIDE HISTOPATHOLOGY IMAGES"],"dc:type":["info:eu-repo/semantics/doctoralThesis"]},"updated_at":"2026-07-27T20:18:53Z"}