{"id":"W4411779693","doi":"10.18280/ts.420343","title":"A Semi-Supervised Framework for Cardiac MRI Segmentation via Multi-Constraint Collaborative Self-Training","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Constraint (computer-aided design); Segmentation; Training (meteorology); Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Mathematics; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004034948,0.0002219366,0.0002381792,0.0001654505,0.0004159707,0.0001334096,0.0001842066,0.0001126954,0.0001650192],"category_scores_gemma":[0.0001848297,0.0002286856,0.0001364614,0.0006789757,0.0001029292,0.0001977644,0.00002449778,0.0001871086,0.00002034545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001945253,"about_ca_system_score_gemma":0.0001886747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002864278,"about_ca_topic_score_gemma":0.000003802511,"domain_scores_codex":[0.998179,0.000234356,0.0004117056,0.0005630236,0.0002776185,0.0003342754],"domain_scores_gemma":[0.9988345,0.0005972456,0.0001567264,0.0001854037,0.0001325193,0.00009364224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001686041,0.0003505732,0.0002065759,0.00008772057,0.00008365433,0.000002797088,0.007099763,0.0003023203,0.9119907,0.03655193,0.0006833244,0.04247206],"study_design_scores_gemma":[0.003777507,0.0003567052,0.001875998,0.0001388914,0.0001473269,0.000004706441,0.00946265,0.1129857,0.8550829,0.005572913,0.01002627,0.0005684513],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04465456,0.00003520128,0.9490839,0.001719947,0.0007786801,0.002102691,0.0001330271,0.0003598376,0.001132132],"genre_scores_gemma":[0.9595563,0.0000191286,0.03741361,0.001791143,0.0001277689,0.0008704537,0.00002486893,0.00002204939,0.0001746183],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9149018,"threshold_uncertainty_score":0.9325526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03871408262314244,"score_gpt":0.3018111329188579,"score_spread":0.2630970502957155,"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."}}