{"id":"W2990405126","doi":"10.1101/860700","title":"Skin Lesions Classification Using Deep Learning Based on Dilated Convolution","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Convolution (computer science); Deep learning; Lesion; Class (philosophy); Pattern recognition (psychology); Training set; Convolutional neural network; Medicine; Pathology; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004459021,0.0004723263,0.0005478185,0.0006193168,0.0002379072,0.0001195784,0.0001796011,0.000580205,0.0001538164],"category_scores_gemma":[0.0002556417,0.0005089619,0.0002156312,0.0004780435,0.00006732195,0.0000578412,0.0001556493,0.001152578,0.0002740097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000993163,"about_ca_system_score_gemma":0.0004127166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000540383,"about_ca_topic_score_gemma":0.000001707917,"domain_scores_codex":[0.9973907,0.0001944907,0.0005152947,0.0009472613,0.0005212779,0.0004309642],"domain_scores_gemma":[0.997674,0.00007234594,0.0004810118,0.001112963,0.0004145075,0.0002451892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004945588,0.0006446367,0.009461104,0.001159979,0.0003321115,0.0001753996,0.00001587532,0.04617003,0.940804,0.0004259797,0.0002485734,0.00006773171],"study_design_scores_gemma":[0.0015997,0.000310734,0.1897819,0.001237239,0.0005670852,1.572505e-7,0.00001350239,0.7500588,0.04386211,5.69069e-7,0.01174335,0.000824909],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9430591,0.0002190906,0.05083728,0.0004003577,0.002183993,0.002114203,0.00002703569,0.0009595409,0.0001993282],"genre_scores_gemma":[0.9967749,0.00007494088,0.002168515,0.0003608763,0.0003370219,0.00008007986,0.000002775928,0.0001388971,0.00006197271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8969419,"threshold_uncertainty_score":0.9997362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02582355702094894,"score_gpt":0.2457399311157866,"score_spread":0.2199163740948377,"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."}}