{"id":"W3046454211","doi":"10.11159/icbes20.120","title":"Multi-Dataset Training for Skin Lesion Classification on Multimodal and Multitask Deep Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Computer science; Artificial intelligence; Deep learning; Training (meteorology); Multi-task learning; Machine learning; Pattern recognition (psychology); Task (project management); Engineering; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001943432,0.0001005666,0.0001722583,0.0001266975,0.0001530286,0.00008888629,0.00008237244,0.00002374046,1.769034e-7],"category_scores_gemma":[0.0001011308,0.00007107588,0.00002113821,0.0002729274,0.00006006554,0.00005352767,0.00004957092,0.0001458545,1.879797e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002037739,"about_ca_system_score_gemma":0.0000073418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004612429,"about_ca_topic_score_gemma":3.817479e-7,"domain_scores_codex":[0.9992378,0.000003364588,0.0001467771,0.0002855069,0.0001723109,0.000154278],"domain_scores_gemma":[0.9996398,0.00006554773,0.00007034765,0.00004154322,0.00005951547,0.0001232273],"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":[0.001386136,0.0003827571,0.005487559,0.003356217,0.0002061407,0.00001154737,0.003626122,0.02013895,0.347843,0.03293075,0.001991597,0.5826393],"study_design_scores_gemma":[0.000599793,0.0004341007,0.005047984,0.0001610563,0.00001595541,0.0000263591,0.00006274832,0.9889919,0.001187795,8.073406e-7,0.003390905,0.00008065908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987981,0.0002547445,0.008669696,0.001283008,0.0005726765,0.001054473,0.000008513611,0.0001129108,0.00006304144],"genre_scores_gemma":[0.9980105,0.00001719466,0.001652332,0.0001155643,0.00009395697,0.00001698905,0.00000119338,0.000007167082,0.00008513387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9688529,"threshold_uncertainty_score":0.289839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03065823501377087,"score_gpt":0.2541329196987936,"score_spread":0.2234746846850227,"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."}}