{"id":"W2964260085","doi":"10.1109/ijcnn.2018.8489717","title":"The Effects of Image Pre- and Post-Processing, Wavelet Decomposition, and Local Binary Patterns on U-Nets for Skin Lesion Segmentation","year":2018,"lang":"en","type":"article","venue":"","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Wavelet; Segmentation; Artifact (error); Image processing; Jaccard index; Grayscale; Image segmentation; Thresholding; Wavelet transform; Computer vision; Image (mathematics)","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":[0.00008251343,0.00007172464,0.00008539771,0.00004794915,0.0001405349,0.00002227543,0.00001847996,0.00002781537,0.00001058187],"category_scores_gemma":[0.00002101565,0.0000460604,0.00001865233,0.00002996727,0.00008356239,0.00003565314,0.00002412321,0.00002958815,0.000001930373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002087365,"about_ca_system_score_gemma":0.000008388306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003088222,"about_ca_topic_score_gemma":0.00003867902,"domain_scores_codex":[0.9995467,0.00001856743,0.0001135425,0.0001356213,0.00009241977,0.00009312447],"domain_scores_gemma":[0.9996455,0.00009509547,0.00004852482,0.00008101783,0.00008456695,0.00004525969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001644208,0.0001719633,0.000402451,0.001026238,0.00005032209,0.00001353019,0.0007004472,4.083703e-7,0.3574729,0.0001554764,0.002965064,0.635397],"study_design_scores_gemma":[0.004974991,0.01506932,0.2051459,0.0005581107,0.0002169323,0.0002497485,0.001390032,0.01138264,0.7574412,0.0001646663,0.003195101,0.0002113159],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713236,0.00004786328,0.02656058,0.0008299396,0.0001004642,0.0007020108,0.000002753284,0.00002465785,0.0004081142],"genre_scores_gemma":[0.9974062,0.00007161117,0.0008439383,0.0007494715,0.00005244321,0.00002547764,0.00001501679,0.000009120382,0.0008266549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6351857,"threshold_uncertainty_score":0.1878289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005841689622693566,"score_gpt":0.2812883001246402,"score_spread":0.2754466105019467,"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."}}