{"id":"W4399821708","doi":"10.3389/fonc.2024.1320220","title":"Improving skin cancer detection by Raman spectroscopy using convolutional neural networks and data augmentation","year":2024,"lang":"en","type":"article","venue":"Frontiers in Oncology","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; Vancouver Coastal Health Research Institute; University of British Columbia; Vancouver Coastal Health","funders":"Canadian Institutes of Health Research; BC Hydro; Canadian Dermatology Foundation; Canadian Cancer Society; VGH and UBC Hospital Foundation; University of British Columbia","keywords":"Receiver operating characteristic; Artificial intelligence; Linear discriminant analysis; Pattern recognition (psychology); Convolutional neural network; Principal component analysis; Support vector machine; Computer science; Raman spectroscopy; Pooling; Basal cell carcinoma; Mathematics; Machine learning; Medicine; Pathology; Physics; Basal cell; Optics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002529019,0.0001041374,0.0001262271,0.00006734041,0.00005284116,0.00003183477,0.0002054229,0.0002508835,0.00002331425],"category_scores_gemma":[0.00005061315,0.0001006765,0.00002115971,0.0001422156,0.0002408965,0.00001197573,0.0002523955,0.0002675927,2.351207e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000254165,"about_ca_system_score_gemma":0.00009084344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002083201,"about_ca_topic_score_gemma":0.00006226497,"domain_scores_codex":[0.99891,0.00006280199,0.0001690176,0.0004658077,0.0001118519,0.0002805708],"domain_scores_gemma":[0.9996836,0.00002031483,0.00003225687,0.0001741405,0.00001714903,0.00007252038],"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":[0.0001435491,0.00003203292,0.001520453,0.00002724804,0.00003083098,0.000006997543,0.000008322705,0.00002937662,0.8911785,0.000009136048,0.03015146,0.07686209],"study_design_scores_gemma":[0.0004276332,0.000330069,0.0001394514,0.00001832091,0.00002234672,0.0000241519,0.00005035654,0.6835651,0.272038,0.0002542036,0.04296432,0.0001660929],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3190934,0.01383013,0.6650479,0.0003703066,0.001233023,0.0002098749,0.0000582206,0.0000325286,0.0001245849],"genre_scores_gemma":[0.97978,0.002051551,0.01656657,0.000268184,0.0006566586,0.00005335382,0.0004681954,0.00002372179,0.0001318315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6835357,"threshold_uncertainty_score":0.4105469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01601570372987302,"score_gpt":0.3742931622299826,"score_spread":0.3582774585001096,"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."}}