Background Platinum resistance is a major determinant of poor outcome in advanced epithelial ovarian cancer, yet reliable predictors available before treatment initiation remain scarce. Ascitic fluid is commonly obtained during diagnostic work-up and directly reflects the peritoneal tumour microenvironment, but its cytomorphological information has not been systematically exploited for treatment-response prediction. Methods We present OVCAP, a multi-scale deep-learning framework that analyses pretreatment ascites cytology whole-slide images to estimate platinum-resistance risk. The study included 438 patients with FIGO stage IIIB\u2013IV epithelial ovarian cancer. Model performance was evaluated in one internal and two independent external validation cohorts. Attention-guided cytopathology review was performed to identify high-risk morphologic patterns, and integrated single-cell RNA sequencing analyses were used to characterise the underlying biological features. Results OVCAP achieved area under the receiver operating characteristic curve (ROC-AUC) values of 0.894, 0.863, and 0.828 in the internal and two independent external validation cohorts, respectively, and outperformed the KELIM score (AUC 0.619). Attention-guided cytopathology review identified recurrent high-risk morphologic patterns in resistant disease: epithelial cytoplasmic vacuolization and interaction-rich malignant aggregates accompanied by immune and mesothelial cells. Integrated single-cell analyses linked these phenotypes to membrane remodelling, lipid reprogramming, hypoxia-associated stress signalling, and reinforced adhesion and immunoregulatory networks. Conclusion These findings support pretreatment ascites cytology as a clinically accessible substrate for early risk stratification before first-line platinum-based therapy.<\/p>\n","protected":false},"excerpt":{"rendered":"
Background Platinum resistance is a major determinant of poor outcome in advanced epithelial ovarian cancer, yet reliable predictors available before treatment initiation remain scarce. Ascitic fluid is commonly obtained during diagnostic work-up and directly reflects the peritoneal tumour microenvironment, but its cytomorphological information has not been systematically exploited for treatment-response prediction. Methods We present OVCAP, […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"text","value":"Yangyang Zhang","user_id":0},{"type":"text","value":"Xiaochun Wan","user_id":0},{"type":"text","value":"Yongqi Chen","user_id":0},{"type":"text","value":"Jianbo Xu","user_id":0},{"type":"text","value":"Weijie Wang","user_id":0},{"type":"text","value":"Haiming Li","user_id":0},{"type":"text","value":"Zhihao Zhang","user_id":0},{"type":"text","value":"Yi Luo","user_id":0},{"type":"text","value":"Liujia Wang","user_id":0},{"type":"text","value":"X. Ju","user_id":0},{"type":"text","value":"Xiaohua Wu","user_id":0},{"type":"user_nicename","value":"Zilong Wang","user_id":"43764"},{"type":"text","value":"Bo Ping","user_id":0},{"type":"text","value":"Qinhao Guo","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"Neoplasia","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"Neoplasia (New York, N.Y.)","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"79","msr_copyright":"","msr_conference_name":"","msr_doi":"10.1016\/j.neo.2026.101330","msr_arxiv_id":"","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2026-06-28","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2026,"msr_month":6,"msr_day":28,"msr_microsoftintellectualproperty":false,"msr_pub_id":"e38b68ba0c591d1c7f9e67816bced5dde130cb3b","msr_publication_uploader":[{"type":"url","title":"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/13330694","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/pubmed.ncbi.nlm.nih.gov\/42365738","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"e38b68ba0c591d1c7f9e67816bced5dde130cb3b","msr_s2_pdf_url":"https:\/\/doi.org\/10.1016\/j.neo.2026.101330","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":40,"msr_s2_open_access":true,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"e38b68ba0c591d1c7f9e67816bced5dde130cb3b"},{"provider":"doi","id":"10.1016\/j.neo.2026.101330"},{"provider":"pubmed","id":"42365738"},{"provider":"pubmedcentral","id":"13330694"},{"provider":"corpusid","id":"289676609"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13553],"msr-publication-type":[193715],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[259639,246985],"msr-conference":[],"msr-journal":[270446],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1178884","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-field-of-study-medical-imaging","msr-field-of-study-medicine"],"msr_publishername":"","msr_edition":"Neoplasia","msr_affiliation":"","msr_published_date":"2026-06-28","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"Neoplasia (New York, N.Y.)","msr_volume":"79","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"10.1016\/j.neo.2026.101330","msr_publication_uploader":[{"type":"url","title":"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/13330694","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/pubmed.ncbi.nlm.nih.gov\/42365738","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"e38b68ba0c591d1c7f9e67816bced5dde130cb3b","msr_influential_citations":0,"msr_reference_count":40,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":true,"msr_s2_pdf_url":"https:\/\/doi.org\/10.1016\/j.neo.2026.101330","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Yangyang Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Xiaochun Wan","user_id":0,"rest_url":false},{"type":"text","value":"Yongqi Chen","user_id":0,"rest_url":false},{"type":"text","value":"Jianbo Xu","user_id":0,"rest_url":false},{"type":"text","value":"Weijie Wang","user_id":0,"rest_url":false},{"type":"text","value":"Haiming Li","user_id":0,"rest_url":false},{"type":"text","value":"Zhihao Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Yi Luo","user_id":0,"rest_url":false},{"type":"text","value":"Liujia Wang","user_id":0,"rest_url":false},{"type":"text","value":"X. Ju","user_id":0,"rest_url":false},{"type":"text","value":"Xiaohua Wu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Zilong Wang","user_id":43764,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Zilong Wang"},{"type":"text","value":"Bo Ping","user_id":0,"rest_url":false},{"type":"text","value":"Qinhao Guo","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[815140],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1178884","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1178884\/revisions"}],"predecessor-version":[{"id":1179044,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1178884\/revisions\/1179044"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1178884"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1178884"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1178884"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1178884"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1178884"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1178884"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1178884"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1178884"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1178884"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1178884"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1178884"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1178884"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1178884"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1178884"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}