{"id":"W4403147824","doi":"10.1016/j.compmedimag.2024.102437","title":"MultiNet 2.0: A lightweight attention-based deep learning network for stenosis measurement in carotid ultrasound scans and cardiovascular risk assessment","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Stenosis; Ultrasound; Radiology; Deep learning; Computer science; Artificial intelligence; Medicine; Cardiology; Internal medicine","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":[0.001790053,0.0002646693,0.0005692726,0.000216402,0.0002177917,0.0001674761,0.00007719833,0.00009278744,0.00001555804],"category_scores_gemma":[0.000244921,0.0002236354,0.0004902357,0.0003261095,0.0002027241,0.00007500739,0.00005031345,0.0004956169,6.323136e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005390408,"about_ca_system_score_gemma":0.0001876789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00010423,"about_ca_topic_score_gemma":0.00002925614,"domain_scores_codex":[0.997479,0.0002544305,0.0003799552,0.0006109255,0.0008670266,0.0004087031],"domain_scores_gemma":[0.9987289,0.0003942861,0.00004296071,0.0002460103,0.000154092,0.0004337641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005247209,0.0002053965,0.9295003,0.001362531,0.001336113,0.00007589203,0.0001863727,0.0005255774,0.0001767606,0.0002227137,0.0005293032,0.06582654],"study_design_scores_gemma":[0.00673564,0.0001725179,0.5012041,0.002610805,0.001558289,0.0001239654,0.0001646517,0.4779525,0.00001892918,0.0001884606,0.008856083,0.00041408],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2971358,0.03452403,0.6628842,0.002198157,0.001008247,0.001731622,0.00003662866,0.0003945781,0.00008676798],"genre_scores_gemma":[0.9909495,0.003474651,0.00434369,0.0004780881,0.0004457562,0.0001408983,0.0001201689,0.00004215266,0.000005104587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6938137,"threshold_uncertainty_score":0.9119589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009978911662491624,"score_gpt":0.2526533477406034,"score_spread":0.2426744360781118,"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."}}