{"id":"W4313551754","doi":"10.47936/encephalitis.2022.00108","title":"Improving performance robustness of subject-based brain segmentation software","year":2023,"lang":"en","type":"article","venue":"encephalitis","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; BioClinica; F. Hoffmann-La Roche; University of Southern California; Biogen; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Segmentation; Artificial intelligence; Computer science; Preprocessor; Data pre-processing; Generalizability theory; Pattern recognition (psychology); Robustness (evolution); Software; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002587369,0.00008772641,0.00009378585,0.0001478389,0.0001469475,0.00002791166,0.0001528322,0.00004166275,0.0001506596],"category_scores_gemma":[0.0006550517,0.00009169681,0.00004245744,0.0008537459,0.00009601771,0.0002185575,0.00002110733,0.00008357735,0.00007528257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000426326,"about_ca_system_score_gemma":0.00006105061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001889749,"about_ca_topic_score_gemma":0.000004867422,"domain_scores_codex":[0.998921,0.0001109422,0.0002136555,0.0002768133,0.0002820121,0.0001955507],"domain_scores_gemma":[0.9992746,0.0003024647,0.0001405576,0.0001983485,0.00003931973,0.00004477422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000201188,0.00003003057,0.001723048,0.0001283354,0.000001243983,0.00000579708,0.0002620051,0.004026698,0.8817865,0.0002004109,0.000598477,0.1112173],"study_design_scores_gemma":[0.0003439358,0.0000710721,0.01913298,0.00002510931,0.000003089078,0.000007619843,0.0001740565,0.0716083,0.908245,0.00002217518,0.000256025,0.0001106027],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771124,0.000003610137,0.02127566,0.0003910386,0.0004324901,0.0001753344,0.00002119531,0.0003406938,0.0002476202],"genre_scores_gemma":[0.9980614,0.000006716333,0.0005151493,0.0002529476,0.00005035577,0.0000580078,0.00001559156,0.00001481582,0.001025081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1111067,"threshold_uncertainty_score":0.3739287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03347413287791966,"score_gpt":0.2673524906866486,"score_spread":0.233878357808729,"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."}}