{"id":"W3024581418","doi":"10.1016/j.media.2020.101723","title":"Dynamically constructed network with error correction for accurate ventricle volume estimation","year":2020,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Volume (thermodynamics); Residual; Algorithm; Ventricle; Constraint (computer-aided design); Artificial intelligence; Mathematics; 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":[0.0004588877,0.0001623329,0.0003686824,0.0001315683,0.0001427651,0.0001933301,0.0006234731,0.0001010333,0.0006990213],"category_scores_gemma":[0.001898493,0.0001331903,0.0001625576,0.002796547,0.0001862751,0.0005847474,0.0001217233,0.0002190613,0.0000443603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005404504,"about_ca_system_score_gemma":0.0001438289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000301313,"about_ca_topic_score_gemma":0.00001664767,"domain_scores_codex":[0.9977198,0.0001365943,0.000458013,0.0005036073,0.0008540692,0.0003279654],"domain_scores_gemma":[0.9983523,0.0002458783,0.0002251019,0.0003066575,0.0003640534,0.0005059885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001924826,0.0002488656,0.003498369,0.0001155992,0.001709695,0.0002590173,0.0007196011,0.008417823,0.0009601797,0.0004677433,0.1296766,0.853734],"study_design_scores_gemma":[0.00040019,0.0001615209,0.0008369461,0.00001905001,0.0003450521,0.000008837113,0.00003016034,0.9965394,0.001175138,0.0001501142,0.0001716898,0.0001619724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008513934,0.00001703786,0.9898732,0.008225525,0.0001199641,0.0003013144,0.00000566755,0.000500781,0.0001051112],"genre_scores_gemma":[0.1759614,0.000008242522,0.8173423,0.006118571,0.000156528,0.00009464946,0.0001888812,0.0000159354,0.000113493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9881215,"threshold_uncertainty_score":0.7653793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01063916756955281,"score_gpt":0.2815315884678082,"score_spread":0.2708924208982554,"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."}}