{"id":"W2318448983","doi":"10.1109/embc.2014.6945106","title":"Enhanced classification of malignant melanoma lesions via the integration of physiological features from dermatological photographs","year":2014,"lang":"en","type":"article","venue":"","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Melanoma; Artificial intelligence; Computer science; Variegation (histology); Feature (linguistics); Pattern recognition (psychology); Dermatological diseases; Homogeneous; Dermatology; Skin lesion; Lesion; Dermatoscopy; Medicine; Pathology; Mathematics","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":[0.0001051156,0.00009638917,0.0002475025,0.00006164935,0.00004739753,0.000004974649,0.00008979516,0.00009337542,0.000316596],"category_scores_gemma":[0.00009635867,0.00004753764,0.0001230764,0.000145679,0.000123179,0.00001709174,0.0000302304,0.0001048758,0.00001085387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001077478,"about_ca_system_score_gemma":0.000007912204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001431102,"about_ca_topic_score_gemma":0.00006744047,"domain_scores_codex":[0.9991733,0.000103332,0.0002848547,0.0001750077,0.0001705791,0.00009288332],"domain_scores_gemma":[0.9993104,0.0001314123,0.0001475427,0.0002871803,0.0000834631,0.00004003175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001513775,0.0001568508,0.0002430862,0.00001260736,0.00004009801,0.000001123725,0.0001210489,0.000002388394,0.9663498,0.007360084,0.0006659055,0.0248956],"study_design_scores_gemma":[0.0004427428,0.0004105993,0.3115741,0.00004120667,0.00009181952,0.00002675429,0.0007888013,0.002265885,0.6823781,0.001337537,0.0005689535,0.00007358188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9280428,0.00003881155,0.06311505,0.0006624929,0.00009611848,0.0003582797,0.000003208932,0.00005113237,0.007632077],"genre_scores_gemma":[0.9982308,0.0000410053,0.001078047,0.0002811202,0.0000347875,0.00002603236,0.00003526447,0.000004873989,0.0002680846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.311331,"threshold_uncertainty_score":0.3466505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02971843250609531,"score_gpt":0.2719182372821535,"score_spread":0.2421998047760582,"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."}}