{"id":"W4393158677","doi":"10.1609/aaai.v38i2.27839","title":"Learning Generalized Medical Image Segmentation from Decoupled Feature Queries","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Feature (linguistics); Artificial intelligence; Segmentation; Computer science; Image (mathematics); Pattern recognition (psychology); Computer vision; Image segmentation","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":[],"consensus_categories":[],"category_scores_codex":[0.0005074873,0.0001919532,0.0002029129,0.0001116526,0.0001823476,0.0006803043,0.001384234,0.0001369399,0.0003729884],"category_scores_gemma":[0.0005427366,0.0001346523,0.0001230457,0.0006840663,0.0002426943,0.0006591143,0.0002702785,0.0004805961,0.0002068949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005434139,"about_ca_system_score_gemma":0.0001686313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005854663,"about_ca_topic_score_gemma":0.000007559385,"domain_scores_codex":[0.9981171,0.00003058644,0.0003962858,0.0004823967,0.0007465272,0.0002271106],"domain_scores_gemma":[0.9989772,0.0001319439,0.0001800579,0.0001910278,0.0004309073,0.00008885798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002636574,0.00004108604,0.00003953274,0.00003724983,0.00001929611,0.00000188006,0.00123733,0.000001214655,0.3063528,0.5504065,0.0006790496,0.1411577],"study_design_scores_gemma":[0.00001459896,0.00007537533,0.00004263623,0.0002611653,0.000009693282,0.00000350712,0.0003051314,0.1361814,0.7755973,0.08672106,0.0006478538,0.0001402359],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09425629,0.0003781322,0.8626312,0.03312084,0.001132395,0.0006682422,0.00001130409,0.001197652,0.006603912],"genre_scores_gemma":[0.9776282,0.0003154145,0.02074434,0.0002326257,0.0001264946,0.00004351513,0.000005100516,0.00001568258,0.0008886801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8833718,"threshold_uncertainty_score":0.656019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03911934002344062,"score_gpt":0.3130278229339875,"score_spread":0.2739084829105468,"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."}}