{"id":"W4403152519","doi":"10.1007/978-3-031-72111-3_50","title":"Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Computer vision; Domain (mathematical analysis); Segmentation; Artificial intelligence; Image segmentation; Image (mathematics); Computer graphics (images)","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":[0.0007197714,0.000506347,0.0004032156,0.0003771238,0.0003971354,0.0004932255,0.001932626,0.000219346,0.000006150858],"category_scores_gemma":[0.00002319528,0.0004111018,0.00009006485,0.0005952788,0.0004537114,0.0007839671,0.0009166799,0.0007028924,0.00001534473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004723847,"about_ca_system_score_gemma":0.0007438156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004822627,"about_ca_topic_score_gemma":0.00003762631,"domain_scores_codex":[0.9957604,0.00001743994,0.0004983488,0.001777888,0.00126742,0.0006784773],"domain_scores_gemma":[0.9981158,0.0002704647,0.0002695011,0.0008537309,0.0002792784,0.0002112162],"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":[0.00002997572,0.00003257922,0.000002024824,0.0001263953,0.00002346161,0.00005887003,0.00121178,0.6933397,0.000878825,0.1288032,0.00003469444,0.1754585],"study_design_scores_gemma":[0.0002003212,0.0002085538,3.92434e-7,0.0004098017,0.000008171436,0.00004874068,3.636925e-7,0.7045947,0.001278529,0.2927143,0.0001808647,0.0003552142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000358238,0.0001912074,0.9936267,0.001737608,0.000330343,0.002875842,0.000009067184,0.0002854092,0.0009080403],"genre_scores_gemma":[0.002514773,0.00001713543,0.9951239,0.0009635322,0.0003654557,0.000537894,0.000012553,0.00006057979,0.0004041468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1751032,"threshold_uncertainty_score":0.9998341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02114040181540897,"score_gpt":0.2802780704294546,"score_spread":0.2591376686140456,"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."}}