{"id":"W4293062274","doi":"10.1007/s40846-022-00712-9","title":"Applying a Convolutional Neural Network Based Iterative Algorithm to Automatically Measure Spinal Curvature on Radiographs for Children with Scoliosis","year":2022,"lang":"en","type":"article","venue":"Journal of Medical and Biological Engineering","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Women and Children's Health Research Institute","keywords":"Radiography; Scoliosis; Vertebra; Convolutional neural network; Cobb angle; Segmentation; Standard deviation; Curvature; Gold standard (test); Artificial intelligence; Algorithm; Computer science; Mathematics; Medicine; Radiology; Surgery; Statistics; Geometry","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":[0.0006163832,0.0001702534,0.0004261561,0.0001409357,0.0001357642,0.00002213031,0.000108712,0.00009545407,0.00005782363],"category_scores_gemma":[0.0001956802,0.00009321296,0.0001666242,0.0003210854,0.0000409839,0.00002414462,0.00004079878,0.0004963494,2.287582e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006993086,"about_ca_system_score_gemma":0.00008281387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001446585,"about_ca_topic_score_gemma":2.138234e-7,"domain_scores_codex":[0.9984179,0.00004771752,0.0003123183,0.0001812023,0.0007796028,0.0002612431],"domain_scores_gemma":[0.9991359,0.0001782411,0.00009062373,0.00005833471,0.00008970115,0.0004471705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01384929,0.006772028,0.472796,0.0003884232,0.005975474,0.002406891,0.0002518148,0.1212534,0.0007461137,0.005953389,0.009429204,0.3601779],"study_design_scores_gemma":[0.009830365,0.0320035,0.821082,0.002124182,0.0004045153,0.002793606,0.00005415603,0.1279028,0.00009611466,0.00005128507,0.003255486,0.000401999],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9437594,0.0040336,0.03687774,0.01338971,0.0003142222,0.001520222,0.00004046699,0.00005585241,0.000008822916],"genre_scores_gemma":[0.9811562,0.00003217435,0.0148283,0.003112732,0.0005383393,0.0003107601,0.00001021392,0.00001033704,9.223343e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3597759,"threshold_uncertainty_score":0.3801114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01958906424244049,"score_gpt":0.2619842552203245,"score_spread":0.242395190977884,"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."}}