{"id":"W4401228055","doi":"10.1007/s00521-024-10225-y","title":"SkinNet-14: a deep learning framework for accurate skin cancer classification using low-resolution dermoscopy images with optimized training time","year":2024,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Charles Darwin University","keywords":"Computational Science and Engineering; Computer science; Artificial intelligence; Skin cancer; Training (meteorology); Deep learning; Pattern recognition (psychology); Resolution (logic); Computer vision; Machine learning; Cancer; Medicine","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":[0.0001245071,0.0001421077,0.0001814009,0.0001071464,0.0004077231,0.0001433306,0.00004447813,0.00006645694,0.00001862445],"category_scores_gemma":[0.00002716443,0.0001238825,0.00005194346,0.0002961417,0.00005270926,0.00005431808,0.00002450166,0.0002543358,0.000006215511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006944601,"about_ca_system_score_gemma":0.00003744168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001760612,"about_ca_topic_score_gemma":0.000002189076,"domain_scores_codex":[0.9990732,0.00003017839,0.0002021308,0.0003682089,0.0001117204,0.0002145466],"domain_scores_gemma":[0.9994258,0.0002045731,0.00008774948,0.0001248762,0.00007751302,0.00007950449],"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":[0.000407019,0.0001094473,0.0001593611,0.0007704557,0.0002525494,0.00001698094,0.00173486,0.1394942,0.03574577,0.00410694,0.0002662211,0.8169362],"study_design_scores_gemma":[0.0004363156,0.00008659182,0.0004458311,0.000293112,0.0001795591,0.0001260222,0.0003251697,0.9929374,0.0004091546,0.000161011,0.004455979,0.0001438537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.14473,0.0005408147,0.8522227,0.000944121,0.00007998783,0.0009252285,0.00000515967,0.0003481781,0.000203749],"genre_scores_gemma":[0.9442241,0.00005261595,0.05458644,0.0001587267,0.0003978939,0.0001889804,0.00003868098,0.00003501385,0.0003175781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8534432,"threshold_uncertainty_score":0.5051782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03257895844605113,"score_gpt":0.3314168384903811,"score_spread":0.29883788004433,"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."}}