{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000528941,0.0004130427,0.0003240917,0.0005384766,0.0004500268,0.0003523022,0.001977395,0.0003066636,0.000006363954],"category_scores_gemma":[0.0001649776,0.0003988198,0.0001167891,0.0005446922,0.0002985762,0.0007610027,0.0006633911,0.0006262805,0.00002932659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003911751,"about_ca_system_score_gemma":0.00054235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005109313,"about_ca_topic_score_gemma":0.00003885962,"domain_scores_codex":[0.9960813,0.00002311421,0.0005709666,0.001520946,0.001228817,0.0005748703],"domain_scores_gemma":[0.9974685,0.0008131613,0.0003135467,0.001013543,0.0001822558,0.000208943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009016598,0.00002339507,7.979067e-7,0.00002626014,0.000005234152,0.00001412204,0.0001453878,0.5698997,0.0006584295,0.0419363,0.00008391241,0.3871974],"study_design_scores_gemma":[0.0002049269,0.0001196816,0.000001768615,0.00009909314,0.000005703022,0.00002207112,1.036978e-7,0.7222491,0.001041599,0.2759544,0.00004349419,0.0002581013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001782961,0.00003527776,0.9945734,0.002295445,0.001138661,0.001187397,0.00002340037,0.0005292675,0.0001993258],"genre_scores_gemma":[0.01028305,0.00006813977,0.9862663,0.00171718,0.000772375,0.0002760279,0.00005958692,0.00007768198,0.0004796455],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3869393,"threshold_uncertainty_score":0.9998463,"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."}}