{"id":"W4362603616","doi":"10.1117/12.2654492","title":"Revisiting the supervision level in semi-supervised learning for automated tumor segmentation: application to lymphoma FDG PET imaging","year":2023,"lang":"en","type":"article","venue":"","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dice; Segmentation; Artificial intelligence; Ground truth; Computer science; Machine learning; Supervised learning; Semi-supervised learning; Pattern recognition (psychology); Mathematics; Artificial neural network; 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":[0.005231372,0.001212508,0.0009454925,0.0007235556,0.0007823686,0.001214943,0.001741571,0.001601862,0.0006505331],"category_scores_gemma":[0.01363653,0.0003967253,0.0006729599,0.0004843497,0.001230682,0.001737836,0.001231189,0.001725371,0.0002626444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001376,"about_ca_system_score_gemma":0.001669958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006203194,"about_ca_topic_score_gemma":0.008122696,"domain_scores_codex":[0.9977163,0.0009755298,0.0001382549,0.0004812873,0.0005269155,0.0001618463],"domain_scores_gemma":[0.9917477,0.004458589,0.0006616375,0.0009728683,0.001886771,0.0002724146],"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":[0.001196789,0.0006608637,0.01749433,0.0006794922,0.0004280833,0.0002853623,0.0007238177,0.4652838,0.05024954,0.003216606,0.003881453,0.4558998],"study_design_scores_gemma":[0.00001864889,0.0001468839,0.002019051,0.00002651159,0.00003416272,0.00006959061,0.00004680115,0.9808854,0.01476212,0.001450203,0.0005213654,0.00001906357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3565868,0.002013452,0.6348834,0.00089469,0.00008796796,0.0002227367,0.0002390581,0.003158255,0.001913723],"genre_scores_gemma":[0.8660237,0.0002219002,0.1323321,0.0001488905,0.00005011461,0.00006316536,0.0003442198,0.0001735944,0.0006424196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006203194,"threshold_uncertainty_score":0.02766645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03431566519380718,"score_gpt":0.3484795213703296,"score_spread":0.3141638561765224,"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."}}