{"id":"W4290612991","doi":"10.3389/fonc.2022.931141","title":"SkinNet-16: A deep learning approach to identify benign and malignant skin lesions","year":2022,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Lakehead University","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Preprocessor; Pattern recognition (psychology); Segmentation; Classifier (UML); Skin cancer; Feature extraction; Feature selection; Artificial neural network; Region of interest; Machine learning; Principal component analysis; Cancer; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004362621,0.0001165929,0.0003356694,0.0004827708,0.0002168043,0.00001274806,0.00009984636,0.00007269828,0.0002226845],"category_scores_gemma":[0.00007472282,0.0001220947,0.0000516549,0.0002925192,0.00004558816,0.00002096466,0.0002867329,0.0004280506,0.00001237324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007008449,"about_ca_system_score_gemma":0.00005144785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008379989,"about_ca_topic_score_gemma":0.00006321973,"domain_scores_codex":[0.9986706,0.0002236027,0.0002423379,0.0003809064,0.0001879379,0.0002945805],"domain_scores_gemma":[0.9995713,0.0000332204,0.00006312218,0.0001728258,0.00001791675,0.0001416741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001315679,0.001270984,0.01912448,0.000118701,0.000227028,0.00132743,0.008594593,0.005372731,0.00111315,0.001170133,0.1570378,0.8033273],"study_design_scores_gemma":[0.001725466,0.001448861,0.01221023,0.00001013431,0.0000767723,0.001044939,0.01564632,0.004833057,0.00004736852,0.0002827772,0.96249,0.0001840468],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7462262,0.0016521,0.1241321,0.004463132,0.005008009,0.002491041,0.000007151933,0.0002311444,0.1157892],"genre_scores_gemma":[0.9711947,0.0001092797,0.01546004,0.001531755,0.0001011452,0.000308815,0.00002553115,0.00002666896,0.01124202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8054522,"threshold_uncertainty_score":0.4978877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01542398793929368,"score_gpt":0.2859522906614273,"score_spread":0.2705283027221336,"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."}}