{"id":"W4387211908","doi":"10.1007/978-3-031-43898-1_27","title":"Maximum Entropy on Erroneous Predictions: Improving Model Calibration for Medical Image Segmentation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Image segmentation; Benchmark (surveying); Artificial neural network; Principle of maximum entropy; Pixel; Entropy (arrow of time); Calibration; Scale-space segmentation; Pattern recognition (psychology); Computer vision; Mathematics; Statistics","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":[0.0036885,0.001496463,0.001889966,0.00146153,0.0006444794,0.001833133,0.001946541,0.002456442,0.001953407],"category_scores_gemma":[0.01364094,0.001084599,0.001059029,0.001071543,0.001153303,0.002264356,0.002699145,0.002290157,0.0008951246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009296803,"about_ca_system_score_gemma":0.000930219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003736888,"about_ca_topic_score_gemma":0.003615704,"domain_scores_codex":[0.9984682,0.000556197,0.00009622395,0.0003520515,0.0004076332,0.0001196529],"domain_scores_gemma":[0.993558,0.004471319,0.0003833344,0.000772613,0.0007070382,0.0001077261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004395123,0.00008214072,0.0014766,0.0001333792,0.0001385553,0.0001531574,0.0001222345,0.6344651,0.0157549,0.003645054,0.002922366,0.340667],"study_design_scores_gemma":[0.00000278488,0.00001185897,0.0001878151,0.000005910745,0.000008555614,0.00002421185,0.000004379538,0.994347,0.002906837,0.002359354,0.0001362563,0.000004903891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02420795,0.0004831311,0.9724302,0.0002947989,0.00005795115,0.00002719504,0.0001048188,0.001632049,0.0007618746],"genre_scores_gemma":[0.6147688,0.0006912175,0.3786789,0.0004009818,0.0001983241,0.00008123316,0.0007360537,0.001185905,0.003258731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003736888,"threshold_uncertainty_score":0.01950687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01918680328178033,"score_gpt":0.2736180290045879,"score_spread":0.2544312257228076,"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."}}