{"id":"W4362663285","doi":"10.1101/2023.04.03.535465","title":"Implementation considerations for deep learning with diffusion MRI streamline tractography","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"National Institutes of Health; Vanderbilt University; National Science Foundation","keywords":"Tractography; Diffusion MRI; Deep learning; Computer science; Artificial intelligence; Diffusion; Data science; Magnetic resonance imaging; Medicine; Radiology; Physics","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":[0.002976071,0.001219759,0.0006480091,0.0005492928,0.000662044,0.002441884,0.003355081,0.001687343,0.01625283],"category_scores_gemma":[0.01395267,0.000815049,0.0007538829,0.0008640692,0.0008335583,0.004431387,0.002113943,0.00441464,0.007647596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001705945,"about_ca_system_score_gemma":0.002192888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008451147,"about_ca_topic_score_gemma":0.01110079,"domain_scores_codex":[0.998626,0.0004476568,0.0001270451,0.0002075725,0.0004431229,0.000148712],"domain_scores_gemma":[0.9966683,0.0013017,0.0001409822,0.0008430599,0.0008406577,0.0002052482],"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":[0.0008790088,0.0002851776,0.002927468,0.0006807307,0.000233769,0.0005102351,0.0003635132,0.3043084,0.02062142,0.1672488,0.06553059,0.4364108],"study_design_scores_gemma":[0.0001229594,0.00009156988,0.0002707597,0.0001289697,0.00003652667,0.0001731881,0.00005793808,0.8798249,0.01553839,0.06492901,0.03878484,0.00004093708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006598894,0.0005489551,0.9758406,0.002570242,0.000240329,0.00009293649,0.00028219,0.008819831,0.005006023],"genre_scores_gemma":[0.1472517,0.0008702188,0.8378449,0.001135574,0.0001533633,0.0004370605,0.001009041,0.002024887,0.009273124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01625283,"threshold_uncertainty_score":0.05437106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.051166974466269,"score_gpt":0.324176065798411,"score_spread":0.273009091332142,"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."}}