{"id":"W4393399813","doi":"10.48550/arxiv.2403.20253","title":"MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bridging (networking); Image (mathematics); Computer science; Segmentation; Computer vision; Image segmentation; Artificial intelligence; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002130847,0.00181626,0.0009444616,0.001569338,0.0005059369,0.00148029,0.003680435,0.003289068,0.008765414],"category_scores_gemma":[0.006706572,0.0007865296,0.001579262,0.0008266746,0.001300049,0.001800599,0.003488849,0.002477174,0.005668989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001150356,"about_ca_system_score_gemma":0.001428204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002606292,"about_ca_topic_score_gemma":0.004738271,"domain_scores_codex":[0.9989547,0.0002517335,0.00006574192,0.0004080131,0.000224712,0.00009517493],"domain_scores_gemma":[0.9982617,0.0007386326,0.0001233905,0.0004280062,0.0002711094,0.0001771616],"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":[0.001245676,0.0002998195,0.001905742,0.001112411,0.0002118954,0.0008190536,0.0005265253,0.123396,0.0424571,0.01373248,0.1053085,0.7089847],"study_design_scores_gemma":[0.0001206023,0.000195998,0.0005679319,0.00007633585,0.0000318333,0.0005878746,0.00006495763,0.9156601,0.03516709,0.02204937,0.02542151,0.00005644726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00656095,0.0005483555,0.9369403,0.0007239829,0.0001989933,0.0004518713,0.001943954,0.05068162,0.001949932],"genre_scores_gemma":[0.1067586,0.0005575083,0.8677236,0.001727963,0.0002408636,0.0007970101,0.009612347,0.006339226,0.006242898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008765414,"threshold_uncertainty_score":0.02932328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0276601246887999,"score_gpt":0.2380637647780604,"score_spread":0.2104036400892605,"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."}}