{"id":"W2910094941","doi":"10.1016/j.media.2022.102680","title":"The Liver Tumor Segmentation Benchmark (LiTS)","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1164,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"National Cancer Institute; National Institutes of Health; Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; International Graduate School of Science and Engineering; Universität Zürich; Deutsche Forschungsgemeinschaft","keywords":"Benchmark (surveying); Segmentation; Computer science; Artificial intelligence; Medical physics; Medicine; Pattern recognition (psychology); Cartography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005617029,0.00007964259,0.0001211712,0.00009148031,0.0009141251,0.00009444047,0.001253837,0.00001157418,0.001010731],"category_scores_gemma":[0.0001202665,0.00005859865,0.0001434654,0.002639343,0.00009728655,0.0002100285,0.0006511899,0.0002380598,0.00006076638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006536023,"about_ca_system_score_gemma":0.00004546697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003417503,"about_ca_topic_score_gemma":0.00004581247,"domain_scores_codex":[0.9981198,0.0001929051,0.0002288449,0.0003216941,0.0009128981,0.0002237994],"domain_scores_gemma":[0.9987161,0.0004054899,0.0001013113,0.0005944103,0.0000484159,0.000134255],"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":[0.00001739301,0.0003986204,0.001981643,0.000008671672,0.001095283,0.0005054162,0.001198138,0.009216052,0.001413884,0.04580027,0.06759614,0.8707685],"study_design_scores_gemma":[0.0001622089,0.00003002764,0.002173926,0.000001013879,0.000196667,0.00002095455,0.000145062,0.9451938,0.0003137721,0.00284923,0.04875661,0.0001567828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003332629,0.0004221789,0.9870038,0.008218525,0.00008523368,0.0001253658,0.000003524128,0.00009734214,0.0007114176],"genre_scores_gemma":[0.9018634,0.000432051,0.08322024,0.01009703,0.0002910784,0.0009539301,0.0001125765,0.00002227448,0.003007416],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9359777,"threshold_uncertainty_score":0.9999025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007724142912540659,"score_gpt":0.2656009642944292,"score_spread":0.2578768213818886,"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."}}