{"id":"W4318833378","doi":"10.1002/ima.22853","title":"Effective data augmentation for brain tumor segmentation","year":2023,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Outlier; Segmentation; Dice; Robustness (evolution); Training set; Artificial intelligence; Generalization; Pattern recognition (psychology); Data set; Synthetic data; Sampling (signal processing); Machine learning; Mathematics; Computer vision; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966774,0.0007625889,0.0006955714,0.0008043456,0.0003349983,0.0006784936,0.0009729535,0.0008216888,0.00152615],"category_scores_gemma":[0.00183592,0.0003981495,0.0007236548,0.0007416388,0.0005663318,0.0009799005,0.001036183,0.0007105008,0.0005381966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003863557,"about_ca_system_score_gemma":0.0004767597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00141731,"about_ca_topic_score_gemma":0.001690941,"domain_scores_codex":[0.999508,0.0001457296,0.0000300887,0.0001208966,0.0001403476,0.00005485518],"domain_scores_gemma":[0.9993285,0.0002274117,0.00007414693,0.0001578063,0.0001802002,0.00003200534],"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":[0.0006374099,0.0002118495,0.003411662,0.0002183539,0.00009503065,0.0002240017,0.0002714529,0.2757652,0.09519655,0.003480603,0.003794109,0.6166938],"study_design_scores_gemma":[0.000005648928,0.0000761073,0.0006413858,0.000009569725,0.000009793132,0.00008619737,0.00002574929,0.9729003,0.02356297,0.001217342,0.001455003,0.000009933749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0731173,0.0004643873,0.9228503,0.0002601838,0.0000822399,0.00007733692,0.0002095508,0.001720986,0.001217716],"genre_scores_gemma":[0.6193105,0.0002295356,0.3777231,0.000184121,0.00005630534,0.0001274821,0.00071355,0.0001766969,0.001478781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00152615,"threshold_uncertainty_score":0.005271018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03430739277089406,"score_gpt":0.3422438189296304,"score_spread":0.3079364261587363,"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."}}