{"id":"W3024083990","doi":"10.1038/s41598-020-64824-5","title":"3D-MCN: A 3D Multi-scale Capsule Network for Lung Nodule Malignancy Prediction","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Malignancy; Nodule (geology); Convolutional neural network; Computer science; Lung cancer; Interpretability; Artificial intelligence; Scale (ratio); Artificial neural network; Machine learning; Medicine; Pathology; Biology; Cartography","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":[0.00127516,0.0001700858,0.0003350687,0.00006774354,0.0004042529,0.0001416343,0.00009534573,0.00009306381,0.0001585434],"category_scores_gemma":[0.0007206694,0.0001487094,0.0001585031,0.0004408239,0.0001815076,0.0001204928,0.00006480944,0.0002881279,0.00001527026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005737422,"about_ca_system_score_gemma":0.0001744009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002208585,"about_ca_topic_score_gemma":0.000003344773,"domain_scores_codex":[0.9975486,0.00003325666,0.0005884055,0.0008606415,0.0004883085,0.0004807911],"domain_scores_gemma":[0.9985952,0.00002699138,0.0002528634,0.000510385,0.0001818751,0.0004326224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001123993,0.0003849918,0.1361124,0.0009187305,0.0001769047,0.001414068,0.003454224,0.008832168,0.1018276,0.00004139186,0.7176787,0.02904652],"study_design_scores_gemma":[0.001082016,0.0001182286,0.004848163,0.0002557197,0.0001769319,0.0004498247,0.00005753592,0.7211919,0.001424748,0.0001411279,0.27005,0.0002037833],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4448308,0.00226804,0.5062267,0.01138229,0.02765938,0.003300181,0.00003274916,0.0008376575,0.003462201],"genre_scores_gemma":[0.7328082,0.00002916637,0.2476085,0.00271102,0.003552341,0.0001991546,0.0007513296,0.0001242393,0.0122161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7123598,"threshold_uncertainty_score":0.6064194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01625267343293068,"score_gpt":0.2798751634241486,"score_spread":0.263622489991218,"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."}}