{"id":"W4412163792","doi":"10.1158/1557-3265.aimachine-a049","title":"Abstract A049: Development of a tri-modal contrast learning model integrating pathology-text and CT-text for clinical oncology tasks","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Precision oncology; Medicine; Contrast (vision); Clinical Oncology; Pathology; Modal; Medical physics; Anatomical pathology; Radiology; Computer science; Internal medicine; Artificial intelligence; Cancer; Precision medicine; Immunohistochemistry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001873392,0.001138985,0.000689236,0.000848512,0.0004145565,0.001090545,0.002081822,0.002069578,0.003832085],"category_scores_gemma":[0.00433761,0.0004083069,0.001427948,0.0006191443,0.0005221477,0.001751137,0.00165511,0.002700223,0.002128054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008552183,"about_ca_system_score_gemma":0.001278364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006238258,"about_ca_topic_score_gemma":0.006289482,"domain_scores_codex":[0.9993128,0.0001841872,0.00002959537,0.000303515,0.00009640799,0.00007362596],"domain_scores_gemma":[0.9988594,0.000522517,0.00007901694,0.0001486554,0.0002954567,0.00009493661],"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":[0.001279609,0.001013684,0.006871365,0.0002844673,0.0003067698,0.0003850638,0.0003039251,0.3157643,0.03078446,0.005829297,0.02279819,0.6143789],"study_design_scores_gemma":[0.00002073927,0.0001037737,0.0004331783,0.00001227492,0.00002473065,0.00005424632,0.00002088858,0.9925969,0.003364184,0.002260341,0.001095734,0.00001305465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1188045,0.001176573,0.8644087,0.001649929,0.0002942123,0.0003108266,0.001944173,0.007638593,0.003772457],"genre_scores_gemma":[0.6580944,0.0003899217,0.3236782,0.001442653,0.0002106693,0.000552343,0.005494998,0.0004124673,0.009724376],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006238258,"threshold_uncertainty_score":0.01281953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2350418241790677,"score_gpt":0.590668948559425,"score_spread":0.3556271243803573,"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."}}