{"id":"W2612377680","doi":"10.1016/j.media.2017.04.008","title":"A structured latent model for ovarian carcinoma subtyping from histopathology slides","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Subtyping; Computer science; Discriminative model; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Feature vector; Histopathology; Machine learning; Pathology; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004373124,0.000139295,0.0003666365,0.000182073,0.000445455,0.0002380965,0.001494754,0.0001500711,0.0001058591],"category_scores_gemma":[0.0005582748,0.0001244065,0.0002827444,0.0002041859,0.0001614597,0.000408502,0.0003520622,0.0001784154,0.000008937805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001254923,"about_ca_system_score_gemma":0.0001266737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001199947,"about_ca_topic_score_gemma":0.00109525,"domain_scores_codex":[0.9983593,0.00006040966,0.0002852762,0.0005838092,0.0004213262,0.0002898341],"domain_scores_gemma":[0.9980628,0.00009156221,0.0002315552,0.001297209,0.0001254928,0.0001913426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002612948,0.0002851243,0.1784776,0.0001170948,0.003099057,0.001211876,0.008224704,0.007487975,0.02774945,0.008624752,0.007060622,0.7574005],"study_design_scores_gemma":[0.0003525719,0.00001755608,0.06059445,0.000004872985,0.0003354112,0.000004088486,0.000004921143,0.929603,0.0008250804,0.008010904,0.0001156307,0.0001315215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0621218,0.00008651273,0.9338486,0.003335251,0.0003150627,0.00008771969,0.00001422171,0.00007392489,0.0001169107],"genre_scores_gemma":[0.8799938,0.00000852259,0.1191952,0.0004111314,0.0001738456,0.00003226249,0.00001305885,0.000008698624,0.0001634452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.922115,"threshold_uncertainty_score":0.5073148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02534964989922344,"score_gpt":0.2903562549135529,"score_spread":0.2650066050143295,"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."}}