{"id":"W4405489389","doi":"10.1109/embc53108.2024.10782494","title":"Semantic AutoSAM: Self-Prompting Segment Anything Model for Semantic Segmentation of Medical Images","year":2024,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"HORIZON EUROPE Health; Alberta Innovates","keywords":"Computer science; Segmentation; Image segmentation; Artificial intelligence; Natural language processing; Semantics (computer science); Computer vision; Information retrieval; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007427162,0.00161304,0.000775001,0.0008878574,0.0003243666,0.000903374,0.001725688,0.00165747,0.004866295],"category_scores_gemma":[0.002156626,0.0005169474,0.00167316,0.0005827106,0.0005951727,0.001792888,0.001205087,0.00147412,0.002338322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008004756,"about_ca_system_score_gemma":0.001103009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003510274,"about_ca_topic_score_gemma":0.009528654,"domain_scores_codex":[0.9995757,0.00007576615,0.00001959519,0.0001992422,0.00008372787,0.0000459736],"domain_scores_gemma":[0.9994801,0.0002101861,0.00004903445,0.0001256422,0.00009010606,0.0000450153],"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":[0.001333262,0.0002881205,0.005373769,0.0005474638,0.0002001383,0.0004910753,0.000562333,0.1597099,0.03257458,0.01288996,0.04057964,0.7454497],"study_design_scores_gemma":[0.00006602444,0.0003134925,0.001211258,0.00006624909,0.00007270366,0.0003410262,0.0001187398,0.9445604,0.01767957,0.02096873,0.01455551,0.00004633749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03103231,0.000878729,0.9287574,0.0006114533,0.0001989052,0.0002391187,0.002300311,0.03270039,0.003281342],"genre_scores_gemma":[0.4374974,0.0009114053,0.533919,0.001709899,0.0002153481,0.0005770893,0.01062567,0.00254567,0.01199849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004866295,"threshold_uncertainty_score":0.0162794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02368429993196793,"score_gpt":0.3085619806043522,"score_spread":0.2848776806723843,"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."}}