{"id":"W4310278111","doi":"10.1186/s12968-022-00899-5","title":"Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment","year":2022,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministero della Salute","keywords":"Medicine; Segmentation; Ventricle; Artificial intelligence; Magnetic resonance imaging; Ejection fraction; Deep learning; Convolutional neural network; Angiology; Cardiac magnetic resonance imaging; Artifact (error); Radiology; Cardiology; Computer science; Pattern recognition (psychology); Heart failure","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002924122,0.0004299429,0.001475832,0.0002696971,0.0003558318,0.0001382161,0.0002455389,0.00008518419,0.00005704137],"category_scores_gemma":[0.0003729493,0.0003507185,0.00158681,0.0005700069,0.000369581,0.0001892589,0.0001102278,0.0006908821,0.000002055304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003251398,"about_ca_system_score_gemma":0.0004831816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001059409,"about_ca_topic_score_gemma":0.00000599579,"domain_scores_codex":[0.9949366,0.0004709389,0.0008984726,0.0007323175,0.002370036,0.0005915744],"domain_scores_gemma":[0.9971428,0.0002640648,0.0002893402,0.001098538,0.0009161567,0.0002890925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001602219,0.0003582342,0.04960541,0.0003677061,0.001287016,0.002727902,0.0001124786,0.006677435,0.0002178391,0.00006095887,0.0004044203,0.9365784],"study_design_scores_gemma":[0.005891149,0.01066472,0.4172585,0.0007256364,0.009277434,0.008231932,0.00133071,0.005134459,0.001449736,0.0006978011,0.5383642,0.000973651],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2091897,0.6875409,0.1002784,0.0005243676,0.0004374056,0.00172494,0.00007597278,0.00004508173,0.0001832895],"genre_scores_gemma":[0.9619467,0.009123052,0.02764069,0.0001257185,0.0006139135,0.0002461656,0.00002007827,0.000104264,0.0001794523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9356048,"threshold_uncertainty_score":0.9998945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01088199671892735,"score_gpt":0.2435638373282126,"score_spread":0.2326818406092853,"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."}}