{"id":"W3004558551","doi":"10.1007/s11045-020-00703-6","title":"Novel convolutional neural network architecture for improved pulmonary nodule classification on computed tomography","year":2020,"lang":"en","type":"article","venue":"Multidimensional Systems and Signal Processing","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Convolutional neural network; Computer science; Nodule (geology); Artificial intelligence; Pattern recognition (psychology); Computed tomography; Lung cancer; Scale (ratio); Deep learning; Solitary pulmonary nodule; Radiology; Medicine; Pathology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003840141,0.0005988309,0.0004106537,0.0004285988,0.0002523999,0.0004227728,0.0007038769,0.000712968,0.00192546],"category_scores_gemma":[0.0007344664,0.0002206326,0.0004312026,0.0004060993,0.0001386905,0.0004394733,0.0005460419,0.0006329779,0.0006889724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004862777,"about_ca_system_score_gemma":0.0008060916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01474047,"about_ca_topic_score_gemma":0.02414165,"domain_scores_codex":[0.9998533,0.00002017232,0.000008748458,0.00003730908,0.00004396814,0.00003659674],"domain_scores_gemma":[0.9997465,0.00005742702,0.00001634951,0.00002897936,0.0001343167,0.00001648007],"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":[0.0004054229,0.0002532875,0.005773066,0.0001119625,0.0001674085,0.0002171762,0.00004135029,0.1658893,0.05570818,0.002755262,0.01162654,0.7570511],"study_design_scores_gemma":[0.000004682527,0.00002523047,0.001025251,0.00000507707,0.00002386164,0.00003229459,0.000004063396,0.9928358,0.005056228,0.0003702475,0.0006123111,0.00000494556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2275487,0.002615446,0.7570934,0.0009631739,0.0004562751,0.00009098992,0.0008964258,0.003494031,0.006841514],"genre_scores_gemma":[0.8466591,0.0008138638,0.1376723,0.0003225067,0.0001368982,0.00006858487,0.001514414,0.0001064056,0.01270589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01474047,"threshold_uncertainty_score":0.02930933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03353059460876703,"score_gpt":0.2658548423579747,"score_spread":0.2323242477492077,"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."}}