{"id":"W3037439917","doi":"10.1016/j.compbiomed.2020.103871","title":"Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Thyroid Cancer Diagnosis and Treatment","field":"Medicine","cited_by":113,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Deep learning; Deconvolution; Segmentation; Pattern recognition (psychology); Ultrasound; Nodule (geology); Hyperparameter; Regularization (linguistics); Artificial neural network; Thyroid nodules; Radiology; Thyroid; Medicine; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003259239,0.0008126682,0.0005544754,0.001111705,0.0001811662,0.0005397504,0.0007221221,0.000780498,0.001331279],"category_scores_gemma":[0.001023654,0.0004015637,0.0006679568,0.000474931,0.0001577497,0.0004101559,0.0006738825,0.0006638182,0.0008760953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005393226,"about_ca_system_score_gemma":0.0007662647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01225548,"about_ca_topic_score_gemma":0.02258823,"domain_scores_codex":[0.9998196,0.00002277182,0.00001002624,0.00004853909,0.00005559539,0.00004357062],"domain_scores_gemma":[0.9996848,0.0001205529,0.00003882034,0.00002973142,0.0001024039,0.00002375424],"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":[0.0005406439,0.000311359,0.0163552,0.0002353006,0.0001800287,0.0004708434,0.00005321637,0.06512349,0.08345448,0.001282076,0.008723399,0.8232699],"study_design_scores_gemma":[0.00001246311,0.00005458612,0.005321506,0.00002755048,0.00005354851,0.0002641296,0.00001671866,0.9724574,0.01895176,0.001367752,0.001456967,0.00001561772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2437319,0.004277754,0.7400904,0.0008355455,0.0002115695,0.0001645418,0.001791164,0.004720668,0.004176514],"genre_scores_gemma":[0.8358612,0.001408401,0.1515255,0.0003687394,0.0001469058,0.00008380193,0.002626006,0.0001530678,0.007826463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01225548,"threshold_uncertainty_score":0.02436829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01743048036080084,"score_gpt":0.2950969158532978,"score_spread":0.2776664354924969,"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."}}