{"id":"W4411600325","doi":"10.1109/tbme.2025.3582749","title":"Prompt Learning With Bounding Box Constraints for Medical Image Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; École de Technologie Supérieure","funders":"National Research Council Canada","keywords":"Image segmentation; Minimum bounding box; Artificial intelligence; Computer science; Segmentation; Medical imaging; Computer vision; Bounding overwatch; Image (mathematics); Scale-space segmentation; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0005253618,0.0001914701,0.0002059541,0.0004261219,0.0001947343,0.0001347609,0.000416434,0.0001458646,0.0001121844],"category_scores_gemma":[0.0001130658,0.0001692086,0.0000741004,0.0006820892,0.0002217191,0.0003544739,0.000005078082,0.000459888,0.000009647571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001408575,"about_ca_system_score_gemma":0.0002201572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000515851,"about_ca_topic_score_gemma":0.000001163653,"domain_scores_codex":[0.9981664,0.000037883,0.0003628208,0.0003988155,0.0006790469,0.0003550453],"domain_scores_gemma":[0.9990016,0.000387186,0.00005343733,0.000204964,0.00007789697,0.0002748836],"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":[0.00004608606,0.0003828833,0.000004952169,0.00036179,0.0001972212,0.00006037278,0.000484357,0.001924977,0.100685,0.001835216,0.000751298,0.8932659],"study_design_scores_gemma":[0.002433373,0.0005776257,0.00002106724,0.0007869139,0.00004675523,0.00005916589,0.000127605,0.5030535,0.4903454,0.0001253354,0.001993385,0.0004297697],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004168539,0.00001157901,0.9962263,0.001334411,0.0005827348,0.0004715013,0.000005151831,0.0008353598,0.0001161744],"genre_scores_gemma":[0.2801487,0.00003185217,0.7184029,0.0005796792,0.00005923602,0.0004697376,0.00001293515,0.00002671829,0.0002681994],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8928361,"threshold_uncertainty_score":0.6900128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006084229846036147,"score_gpt":0.2664600677688148,"score_spread":0.2603758379227786,"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."}}