{"id":"W4403649753","doi":"10.1007/978-3-031-72390-2_60","title":"MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Bridging (networking); Computer science; Image segmentation; Computer vision; Artificial intelligence; Image (mathematics); Segmentation; Computer security","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001093526,0.0005131952,0.0004330203,0.0009181697,0.0002538142,0.001059171,0.002077095,0.0003629565,0.00007703095],"category_scores_gemma":[0.00009804141,0.000490566,0.0001066657,0.0007297365,0.001185692,0.001353556,0.002077025,0.001160062,0.00008616965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007807778,"about_ca_system_score_gemma":0.0009106001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009965627,"about_ca_topic_score_gemma":0.0001103296,"domain_scores_codex":[0.9953387,0.00003903261,0.0004734737,0.00179447,0.00176361,0.0005907158],"domain_scores_gemma":[0.9982117,0.0002796491,0.0001971133,0.0008296281,0.0001952863,0.0002866566],"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":[0.000005420048,0.000009162636,0.000005939969,0.00009414099,0.00001667386,0.0003527538,0.0009355014,0.0003449068,0.0009873332,0.006683223,0.0001028987,0.9904621],"study_design_scores_gemma":[0.0003986957,0.0002049443,0.0000804716,0.0008201373,0.000025689,0.0004764832,0.000001385193,0.8940752,0.00804599,0.09352183,0.001522305,0.0008268426],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001295287,0.0006284864,0.9855542,0.003882535,0.003282176,0.0003192343,0.000007034628,0.00033934,0.00585747],"genre_scores_gemma":[0.08196294,0.0005599302,0.91088,0.00269817,0.00224516,0.0000214697,0.00001278915,0.0001266154,0.001492972],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9896352,"threshold_uncertainty_score":0.9999778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009981602077675383,"score_gpt":0.2561293308092154,"score_spread":0.24614772873154,"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."}}