{"id":"W2099397584","doi":"10.1109/titb.2011.2150758","title":"Generalizing Common Tasks in Automated Skin Lesion Diagnosis","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Information Technology in Biomedicine","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver General Hospital; Canadian Institutes of Health Research; University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Leverage (statistics); Artificial intelligence; Segmentation; Computer science; Skin lesion; Probabilistic logic; Receiver operating characteristic; Pattern recognition (psychology); Lesion; Machine learning; Computer vision; Dermatology; Medicine; Pathology","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":[0.0002168098,0.0001792695,0.0003155916,0.003991508,0.00007279546,0.000007232556,0.0001151966,0.0003112772,0.0002937251],"category_scores_gemma":[0.00001263607,0.0001643255,0.00005070496,0.001785158,0.0001418783,0.0002339702,0.000003360172,0.0004276649,0.0001597581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002717936,"about_ca_system_score_gemma":0.00002702248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004646952,"about_ca_topic_score_gemma":0.0002171974,"domain_scores_codex":[0.9986382,0.00002545291,0.0006925367,0.0001663887,0.0002093212,0.0002680756],"domain_scores_gemma":[0.9994051,0.0000254513,0.0001267839,0.0003251467,0.00004991595,0.00006759121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001361228,0.00243488,0.01295599,0.0004784743,0.0001946205,0.0004809791,0.005924569,0.0009505975,0.007725819,0.001158402,0.003650461,0.962684],"study_design_scores_gemma":[0.03231764,0.008806643,0.09625054,0.003073585,0.0004392506,0.002712874,0.01487316,0.08982866,0.7011029,0.001923769,0.04685232,0.001818653],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9417074,0.00005930202,0.04620613,0.004501637,0.00095996,0.001302482,0.00001552561,0.001765684,0.003481846],"genre_scores_gemma":[0.9971126,0.0002918663,0.001348942,0.0008431381,0.00001242358,0.000279963,0.00002074239,0.00001250122,0.00007778613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9608653,"threshold_uncertainty_score":0.6701001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02358587816888326,"score_gpt":0.2709464642981784,"score_spread":0.2473605861292952,"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."}}