{"id":"W1038736503","doi":"10.1016/j.media.2015.07.003","title":"Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation","year":2015,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cardiovascular Function and Risk Factors","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":false,"ca_institutions":"London Health Sciences Centre; St Joseph's Health Care; CARE Canada; Western University","funders":"Government of Ontario","keywords":"Computer science; Artificial intelligence; Ground truth; Segmentation; Volume (thermodynamics); Regression; Estimation; Scale (ratio); Deep learning; Machine learning; Random forest; Pattern recognition (psychology); Statistics; Mathematics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008820344,0.000154008,0.00057353,0.0002747395,0.00008911195,0.00003529197,0.00005873349,0.0001937677,0.0001856726],"category_scores_gemma":[0.001690252,0.0001027007,0.0006101471,0.0007767975,0.0001100274,0.00009475298,0.00004573924,0.00016479,0.00001642488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006271153,"about_ca_system_score_gemma":0.00005129301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001360434,"about_ca_topic_score_gemma":0.0002217631,"domain_scores_codex":[0.9983714,0.000091679,0.0002911455,0.0003372296,0.000675281,0.0002332705],"domain_scores_gemma":[0.9985813,0.00007372448,0.00007864118,0.0003074199,0.0002880261,0.0006708581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003361083,0.0004862697,0.7766924,0.0001146057,0.005012693,0.0004887145,0.0002965407,0.007373719,0.00005791033,0.000001939032,0.02727741,0.1818617],"study_design_scores_gemma":[0.002078572,0.00006970113,0.09508465,0.00003757873,0.004190288,0.0000441628,0.00008994012,0.8926474,0.00006363225,0.00000482354,0.005573629,0.0001155513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05222605,0.00164164,0.9446332,0.0008762407,0.0001648931,0.0002830945,0.000004024104,0.00008330431,0.00008751113],"genre_scores_gemma":[0.9700118,0.0003106953,0.02616505,0.0005222209,0.0004241858,0.00006459873,0.0007243871,0.00003543685,0.001741622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9184682,"threshold_uncertainty_score":0.4188011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01389788869040394,"score_gpt":0.2905070853804426,"score_spread":0.2766091966900387,"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."}}