{"id":"W2051106546","doi":"10.1109/embc.2012.6346956","title":"Extracting morphological high-level intuitive features (HLIF) for enhancing skin lesion classification","year":2012,"lang":"en","type":"article","venue":"","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Feature extraction; Set (abstract data type); Skin lesion; Computer vision","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":[0.0003130408,0.0001146704,0.0001639699,0.00009130268,0.0001209785,0.00001916534,0.00003871758,0.0001091131,0.0003835286],"category_scores_gemma":[0.0002486611,0.00008680518,0.00007649244,0.00008605243,0.00002153977,0.00009372058,0.00003134364,0.0001441473,0.00007769129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192905,"about_ca_system_score_gemma":0.0000135042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004103297,"about_ca_topic_score_gemma":0.00004534289,"domain_scores_codex":[0.9991488,0.00002787153,0.0002001336,0.0002023783,0.0001568577,0.0002639732],"domain_scores_gemma":[0.999414,0.0001587013,0.00008514743,0.0001504239,0.00007314184,0.000118608],"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":[0.0006842354,0.0006191045,0.001116951,0.0001321548,0.0001002783,0.00002864259,0.0006685926,0.000004597935,0.6908324,0.02162819,0.01734021,0.2668446],"study_design_scores_gemma":[0.002954496,0.001021015,0.4252523,0.0001417595,0.0003247363,0.001480431,0.009032184,0.0006577743,0.4737448,0.0004452002,0.08437756,0.000567656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7329961,0.0001096478,0.2381616,0.002191096,0.001001885,0.001279298,0.000007152808,0.0002863588,0.02396682],"genre_scores_gemma":[0.973727,0.00001467374,0.01197378,0.0007392073,0.0005662697,0.00007473379,0.00003736193,0.00001605302,0.01285086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4241354,"threshold_uncertainty_score":0.4199369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0917907499056919,"score_gpt":0.3325859866482439,"score_spread":0.240795236742552,"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."}}