{"id":"W3122230257","doi":"10.1016/j.neucom.2020.04.157","title":"Convolutional neural networks for medical image analysis: State-of-the-art, comparisons, improvement and perspectives","year":2021,"lang":"en","type":"article","venue":"Neurocomputing","topic":"AI in cancer detection","field":"Computer Science","cited_by":395,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; St. Francis Xavier University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Image (mathematics); Pattern recognition (psychology); Medical imaging; Segmentation; Image segmentation; Image retrieval; Computer vision; Machine learning","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":[0.0003215386,0.0001190303,0.0002247595,0.00006577944,0.0002331031,0.00009840015,0.0003919481,0.00003742919,0.00000592568],"category_scores_gemma":[0.0001066249,0.0001060333,0.0001548358,0.0006648862,0.000109514,0.0001437523,0.000543314,0.0002244423,3.681462e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005026007,"about_ca_system_score_gemma":0.0001121452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001089843,"about_ca_topic_score_gemma":0.00003343013,"domain_scores_codex":[0.9984426,0.0001133694,0.000327577,0.0004751534,0.000384731,0.0002565348],"domain_scores_gemma":[0.9988817,0.0003230649,0.0001894187,0.0003063445,0.0002161757,0.00008332031],"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":[0.0001099361,0.0006395298,0.04339861,0.0002769959,0.00157475,0.00006648044,0.003552675,0.3541917,0.009493604,0.01525152,0.009556685,0.5618875],"study_design_scores_gemma":[0.000340832,0.00006210975,0.02247332,0.00001239378,0.00004745165,0.00002067649,0.00005884214,0.9752873,0.001011952,0.0001963896,0.0003937345,0.00009505088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06974781,0.000400325,0.9271548,0.001940968,0.0004652268,0.0001844147,0.000002734402,0.00005899993,0.00004468637],"genre_scores_gemma":[0.9760172,0.00001206368,0.02340648,0.000378875,0.0001313751,0.00001354749,0.000002014724,0.000008080191,0.00003032374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9062694,"threshold_uncertainty_score":0.4323911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01326633878535696,"score_gpt":0.2582385736075495,"score_spread":0.2449722348221925,"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."}}