{"id":"W2003590746","doi":"10.1186/1532-429x-15-105","title":"Evaluation of current algorithms for segmentation of scar tissue from late Gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge","year":2013,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":178,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"National Institute for Health and Care Research; Engineering and Physical Sciences Research Council; King's College London; National Institute of General Medical Sciences; Medical Research Council; Wellcome Trust","keywords":"Medicine; Angiology; Magnetic resonance imaging; Gadolinium; Segmentation; Cardiac magnetic resonance; Left atrium; Radiology; Algorithm; Internal medicine; Artificial intelligence; Computer science; Atrial fibrillation","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":[0.004507579,0.0002785061,0.001485713,0.0001921683,0.00007410229,0.00006535012,0.000785582,0.0001096034,0.0002180471],"category_scores_gemma":[0.0003354469,0.0002085837,0.001510568,0.000356826,0.0001588217,0.0006311715,0.0002452774,0.000173034,0.000002274695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001146622,"about_ca_system_score_gemma":0.0002903637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002163625,"about_ca_topic_score_gemma":0.000009188356,"domain_scores_codex":[0.9940532,0.0007395927,0.001531327,0.0003888681,0.003024039,0.0002629448],"domain_scores_gemma":[0.9950952,0.0001265106,0.0008946878,0.001096521,0.002674447,0.0001126195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003325257,0.00009550794,0.003141035,0.0003665161,0.001049952,0.000002213464,0.0003712587,0.002508179,0.002255448,0.00001989255,0.0002216813,0.9896358],"study_design_scores_gemma":[0.02542388,0.003600328,0.5919732,0.001806146,0.01636138,0.00002644421,0.0002685795,0.008828472,0.04143154,0.001889446,0.3078462,0.000544336],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.4141959,0.5777813,0.003174931,0.0002216276,0.0008249471,0.003591699,0.00003162335,0.000005166388,0.0001727973],"genre_scores_gemma":[0.9258705,0.0661095,0.006577511,0.00002640863,0.001042461,0.00006612411,0.00002365529,0.00006103919,0.0002227874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9890915,"threshold_uncertainty_score":0.8505796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173788759279773,"score_gpt":0.3857392961966855,"score_spread":0.2683604202687082,"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."}}