{"id":"W4385466175","doi":"10.1007/978-3-031-37742-6_47","title":"Weakly Supervised Medical Image Segmentation with Soft Labels and Noise Robust Loss","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Alberta Bone and Joint Health Institute; University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Cross entropy; Deep learning; Probabilistic logic; Ground truth; Pattern recognition (psychology); Medical diagnosis; Noise (video); Image segmentation; Binary classification; Machine learning; Image (mathematics); Support vector machine","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":[0.001147841,0.0003996083,0.0003626813,0.00053841,0.0002800104,0.0007091864,0.001908955,0.0002585897,0.0000296495],"category_scores_gemma":[0.0002008383,0.0003224627,0.00004135294,0.0006204204,0.0007744175,0.0007744443,0.0009346696,0.0008093873,0.00007434359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064627,"about_ca_system_score_gemma":0.0005140569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005284895,"about_ca_topic_score_gemma":0.0001616146,"domain_scores_codex":[0.9962273,0.00005945523,0.0003807181,0.001433806,0.001436256,0.0004625288],"domain_scores_gemma":[0.9978201,0.000540893,0.0002050013,0.000989838,0.000188305,0.0002558117],"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":[0.0000162085,0.00003751349,0.0007636109,0.0001230729,0.00001831754,0.0002817161,0.001184538,0.008696948,0.0004305475,0.01303305,0.00007624573,0.9753382],"study_design_scores_gemma":[0.0005688933,0.0002214666,0.001911785,0.0005029179,0.00001283212,0.0001668128,8.316481e-7,0.9831129,0.0002726603,0.01213813,0.0004489667,0.000641847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003312763,0.00009065842,0.9936742,0.004150393,0.000479897,0.0002760777,0.000009261764,0.0003032714,0.0006849937],"genre_scores_gemma":[0.0642515,0.0002579935,0.930716,0.002552178,0.0006220053,0.00003292034,0.000132224,0.0001006642,0.00133453],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9746964,"threshold_uncertainty_score":0.9999228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01713412965787675,"score_gpt":0.2517878722043876,"score_spread":0.2346537425465108,"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."}}