{"id":"W4392631937","doi":"10.1136/ijgc-2024-esgo.368","title":"680 Is there a way to optimize the performance of preoperative diagnosis of patients with endometrial cancer on imaging? The artificial intelligence response","year":2024,"lang":"en","type":"article","venue":"International Journal of Gynecological Cancer","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Endometrial cancer; Sørensen–Dice coefficient; Segmentation; Artificial intelligence; Computer science; Pipeline (software); Cervical cancer; Stage (stratigraphy); Medicine; Radiology; Cancer; Image segmentation; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002919877,0.0005607447,0.0007833447,0.0006436899,0.0003112256,0.002111505,0.0004758985,0.001270506,0.001882223],"category_scores_gemma":[0.02481045,0.0001951759,0.0004503441,0.0003899351,0.00064708,0.00113415,0.0008070309,0.001469567,0.0006829297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006430575,"about_ca_system_score_gemma":0.0008945833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001566993,"about_ca_topic_score_gemma":0.001568267,"domain_scores_codex":[0.9984581,0.0008917841,0.0001114149,0.0001611077,0.0002639374,0.0001136415],"domain_scores_gemma":[0.9927205,0.005150388,0.0006692506,0.0002591653,0.0009286096,0.0002721363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00266051,0.0009379177,0.2279689,0.0004913515,0.0007717581,0.0003081283,0.0002445032,0.07050711,0.01173725,0.003822698,0.01784612,0.6627038],"study_design_scores_gemma":[0.0006897341,0.006407755,0.2724704,0.0007715481,0.001169465,0.002244893,0.002396973,0.5908756,0.02559246,0.05686113,0.04018159,0.0003384621],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6825135,0.0279511,0.1009885,0.1582288,0.00179204,0.0001946745,0.0009004758,0.001095999,0.02633485],"genre_scores_gemma":[0.9693916,0.00250005,0.01983565,0.006029398,0.0008188774,0.00002725383,0.0003095125,0.00009598646,0.0009916064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002919877,"threshold_uncertainty_score":0.01544201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02113890227282735,"score_gpt":0.3416441317647595,"score_spread":0.3205052294919322,"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."}}