{"id":"W4407633965","doi":"10.1007/s12672-025-01973-x","title":"Benchmarking histopathology foundation models for ovarian cancer bevacizumab treatment response prediction from whole slide images","year":2025,"lang":"en","type":"article","venue":"Discover Oncology","topic":"AI in cancer detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital; Vancouver General Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; BC Cancer Foundation; Canadian Institutes of Health Research; Canada's Michael Smith Genome Sciences Centre","keywords":"Benchmarking; Bevacizumab; Histopathology; Ovarian cancer; Foundation (evidence); Medicine; Medical physics; Computer science; Oncology; Cancer; Internal medicine; Pathology; Chemotherapy; Geography; Business","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001435847,0.001117008,0.000624739,0.001207666,0.0002407425,0.0008241349,0.0008845043,0.001044185,0.001091618],"category_scores_gemma":[0.003418577,0.0002897995,0.001287785,0.0006373343,0.0003292738,0.000540584,0.0005577873,0.0009549854,0.000450494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001202578,"about_ca_system_score_gemma":0.001065857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063413,"about_ca_topic_score_gemma":0.01247901,"domain_scores_codex":[0.9995777,0.0001139993,0.0000251181,0.0001444763,0.00007493962,0.00006369717],"domain_scores_gemma":[0.9987454,0.0007072813,0.000171051,0.0001307206,0.0001733945,0.00007210684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006074965,0.0003538191,0.0329661,0.0001550158,0.0003139561,0.0002732504,0.00005000068,0.8176074,0.007564441,0.0006407187,0.005212328,0.1342556],"study_design_scores_gemma":[0.00001069848,0.000073713,0.002963169,0.000007125237,0.00002410298,0.00004993202,0.00001410536,0.9941474,0.001834544,0.0005299166,0.0003384532,0.000006710177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8039974,0.003229283,0.1772761,0.001583992,0.0002238048,0.0002984985,0.004164163,0.005477018,0.003749772],"genre_scores_gemma":[0.9639786,0.0003578603,0.03015413,0.0001830484,0.00005795529,0.00008859218,0.003883552,0.00008712889,0.001209134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01063413,"threshold_uncertainty_score":0.02114445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02478473114011203,"score_gpt":0.323553310106249,"score_spread":0.298768578966137,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}