{"id":"W4362601298","doi":"10.1109/tmi.2023.3264433","title":"MISSU: 3D Medical Image Segmentation via Self-Distilling TransUNet","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Computer science; Encoder; Artificial intelligence; Segmentation; Image segmentation; Transformer; Inference; Image resolution; Pattern recognition (psychology); Computer vision","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":[0.00058705,0.0002517055,0.0002320417,0.0002608282,0.0004659681,0.00009913889,0.001000509,0.0001204397,0.0004150677],"category_scores_gemma":[0.00003503542,0.0002479006,0.0001269185,0.001528705,0.000168846,0.0006250856,0.000009036104,0.0007483692,0.0006541774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009409399,"about_ca_system_score_gemma":0.0001498066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001852146,"about_ca_topic_score_gemma":0.00001534817,"domain_scores_codex":[0.9964846,0.0001263625,0.0005028101,0.000685529,0.001610353,0.0005903832],"domain_scores_gemma":[0.9981046,0.000569711,0.00007835891,0.0005366509,0.0000756342,0.0006350338],"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":[0.00001083644,0.0002910923,0.00001244662,0.00004469411,0.00004541166,0.0003257274,0.0007951263,0.006433657,0.004866751,0.0003229355,0.001804318,0.985047],"study_design_scores_gemma":[0.0006404514,0.00002197611,0.00004187303,0.00007527381,0.00002353149,0.0001299514,0.00004156807,0.9877206,0.007385897,0.0009000288,0.002741554,0.0002772792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009751522,0.00004290416,0.9809564,0.01443406,0.0008737013,0.0002848079,0.000006637498,0.002123284,0.0003030135],"genre_scores_gemma":[0.8034607,0.0007434288,0.1896484,0.004924808,0.0004251498,0.0003981816,0.00003090774,0.00009411661,0.0002743735],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9847697,"threshold_uncertainty_score":0.9999973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01233891238311645,"score_gpt":0.2927286068209384,"score_spread":0.280389694437822,"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."}}