{"id":"W3009014237","doi":"10.1007/s11548-020-02128-9","title":"Segmentation and visualization of left atrium through a unified deep learning framework","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Visualization; Computer science; Segmentation; Artificial intelligence; Left atrium; Deep learning; Computer vision; Health informatics; Data science; Computer graphics (images); Human–computer interaction; Medicine; Cardiology; Pathology; 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":[0.0002412642,0.00007394418,0.0003208754,0.0001464084,0.00002995934,0.00001782599,0.00004152684,0.00007731476,0.00003365682],"category_scores_gemma":[0.0002361793,0.00006244374,0.0001036506,0.00007806386,0.00005869004,0.0001505893,0.00003059065,0.0001259488,5.797449e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001441645,"about_ca_system_score_gemma":0.00002795837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001115057,"about_ca_topic_score_gemma":1.374098e-7,"domain_scores_codex":[0.9990796,0.0001241078,0.0004640986,0.00009140359,0.0001796461,0.00006114327],"domain_scores_gemma":[0.9986178,0.0006582171,0.0004115109,0.00002699863,0.000232975,0.00005253427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009425707,0.00001292058,0.9666669,0.00006305578,0.00074071,0.00007691822,0.001615862,0.0006834118,0.001632119,0.002077474,0.0004224076,0.02506566],"study_design_scores_gemma":[0.001629445,0.0003974494,0.9780802,0.0001978304,0.0002049899,0.0008924155,0.0002709994,0.01224578,0.0005450851,0.0006775736,0.00472673,0.000131556],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6199155,0.0006329003,0.3728618,0.005878969,0.0005894238,0.00005849747,5.545054e-7,0.00001213279,0.00005020033],"genre_scores_gemma":[0.9888645,0.0007652026,0.008421323,0.0009317208,0.0009783357,9.761359e-8,0.0000194184,0.000006138222,0.00001323593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.368949,"threshold_uncertainty_score":0.2546382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05190352918255789,"score_gpt":0.3382800114899676,"score_spread":0.2863764823074096,"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."}}