{"id":"W4402199097","doi":"10.1016/j.neucom.2024.128532","title":"Semi-supervised segmentation of medical images focused on the pixels with unreliable predictions","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Pixel; Artificial intelligence; Segmentation; Ground truth; Supervised learning; Pattern recognition (psychology); Function (biology); Image segmentation; Entropy (arrow of time); Cross entropy; Machine learning; Computer vision; Artificial neural network","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":[0.001052795,0.0007191827,0.0007973949,0.001210736,0.0003804096,0.0010665,0.0008662409,0.001193767,0.0008642384],"category_scores_gemma":[0.001841077,0.0004381688,0.0007042684,0.0007271529,0.0005895341,0.0005560112,0.0006341164,0.0006018807,0.0005015831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000382334,"about_ca_system_score_gemma":0.001168541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002196759,"about_ca_topic_score_gemma":0.004271729,"domain_scores_codex":[0.9995759,0.00009338117,0.0000323871,0.0001216613,0.0001131857,0.00006343651],"domain_scores_gemma":[0.9989541,0.0004049759,0.0001523006,0.0001772442,0.0002592824,0.00005220054],"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":[0.002164302,0.0003501099,0.009005903,0.001125952,0.000428023,0.001123767,0.0007356443,0.2015263,0.2988023,0.005179328,0.007796179,0.4717623],"study_design_scores_gemma":[0.00002219824,0.00008922783,0.004938214,0.00004721725,0.00009187674,0.000496643,0.00008451563,0.9293672,0.0596417,0.003488828,0.001710013,0.00002236438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2171297,0.00133778,0.7758838,0.0004902477,0.0001040284,0.0001700632,0.0006049637,0.00232913,0.00195024],"genre_scores_gemma":[0.7793037,0.0004989466,0.2157936,0.0001733787,0.0001182103,0.0001059193,0.001237875,0.0003077566,0.002460619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002196759,"threshold_uncertainty_score":0.005567789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01972842978115154,"score_gpt":0.2722476784626602,"score_spread":0.2525192486815087,"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."}}