{"id":"W4411948899","doi":"10.1109/tmi.2025.3584641","title":"In Vivo Laparoscopic Image De-Smoking Dataset, Evaluation, and Beyond","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Robarts Clinical Trials; Western University","funders":"","keywords":"Computer vision; Image (mathematics); Artificial intelligence; Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001633917,0.0001689411,0.0003025562,0.0004174328,0.0001623338,0.00005422568,0.0001288032,0.0000915316,0.001147548],"category_scores_gemma":[0.0004246922,0.0001589585,0.00005052358,0.0003894282,0.000281768,0.0001884465,0.000004851796,0.001032325,0.000007249516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001860719,"about_ca_system_score_gemma":0.0004169198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001816813,"about_ca_topic_score_gemma":0.00002510745,"domain_scores_codex":[0.9980784,0.0001481077,0.0003659728,0.0003868611,0.0006588876,0.0003617847],"domain_scores_gemma":[0.9990493,0.000286171,0.00004054107,0.0002688241,0.0000622556,0.0002929166],"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":[0.0002908137,0.001272205,0.01750712,0.0007603603,0.0003016639,0.001146268,0.001373775,0.0008956068,0.02670231,0.0005269649,0.07979839,0.8694245],"study_design_scores_gemma":[0.01125659,0.00007194879,0.003313886,0.001730825,0.0006050102,0.0004922284,0.0005644564,0.9350576,0.01516417,0.001906801,0.02941926,0.0004171814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1376242,0.0009427347,0.7800167,0.07106348,0.001524512,0.0007073245,0.00005340101,0.0001425975,0.007925076],"genre_scores_gemma":[0.975027,0.0003015344,0.003061586,0.02097586,0.0001045397,0.00006835913,0.00002334007,0.00002716333,0.0004106144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.934162,"threshold_uncertainty_score":0.9997655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009056886740524706,"score_gpt":0.3393344746544332,"score_spread":0.3302775879139085,"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."}}