{"id":"W2959113037","doi":"10.1007/s10916-019-1414-2","title":"The Application of Deep Learning in the Risk Grading of Skin Tumors for Patients Using Clinical Images","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Systems","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"SKiN Health","funders":"National Key Research and Development Program of China; Hunan Provincial Science and Technology Department","keywords":"Medicine; Seborrheic keratosis; Dermatology; Grading (engineering); Basal cell carcinoma; Actinic keratosis; Skin cancer; Melanoma; Radiology; Basal cell; Pathology; Cancer; Internal 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001000183,0.000524941,0.000335494,0.001475957,0.0002071826,0.0009568421,0.0004233253,0.0006185698,0.0009502051],"category_scores_gemma":[0.00358964,0.0001829501,0.0004388236,0.0005303918,0.0001236988,0.0005153099,0.0005579123,0.0006731604,0.0003115548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003987552,"about_ca_system_score_gemma":0.000500613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005292528,"about_ca_topic_score_gemma":0.007380616,"domain_scores_codex":[0.9996159,0.0001272848,0.00003708797,0.00006582453,0.0001015357,0.00005234184],"domain_scores_gemma":[0.9990977,0.0004130388,0.00009475336,0.00005821585,0.0002537038,0.00008251116],"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":[0.0007237269,0.0004744769,0.1571678,0.0001726504,0.0001910646,0.0004193662,0.0001841916,0.0521109,0.009972826,0.001344215,0.008954591,0.7682841],"study_design_scores_gemma":[0.00002498494,0.0002008053,0.03324671,0.00005534483,0.00008924655,0.0003934634,0.0001398515,0.9537503,0.007440089,0.002690922,0.001942642,0.00002566254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8162987,0.002413253,0.1715968,0.002013069,0.0002024148,0.0002029996,0.001798392,0.001141446,0.004332963],"genre_scores_gemma":[0.9629752,0.0003856851,0.03476074,0.0001128736,0.00006443822,0.00002624405,0.000622797,0.00002927903,0.001022671],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005292528,"threshold_uncertainty_score":0.01052344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01688364929187354,"score_gpt":0.3255812294165533,"score_spread":0.3086975801246797,"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."}}