{"id":"W4312099364","doi":"10.1101/2022.12.18.520922","title":"Applying Unet for extraction of vascular metrics from T1-weighted and T2-weighted MRI","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bishop's University","funders":"","keywords":"Generalizability theory; Segmentation; Artificial intelligence; Computer science; Deep learning; Contrast (vision); Pattern recognition (psychology); Focus (optics); Ground truth; Convolutional neural network; Neuroimaging; Computer vision; Mathematics; Medicine; Statistics; 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":[0.001548215,0.001250878,0.0008650569,0.001851251,0.000389937,0.001885022,0.001195648,0.001919983,0.001730496],"category_scores_gemma":[0.006021146,0.000708759,0.001205903,0.0009569639,0.0006440878,0.00184573,0.001755374,0.002019607,0.001227744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008070398,"about_ca_system_score_gemma":0.001127261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004110693,"about_ca_topic_score_gemma":0.006914396,"domain_scores_codex":[0.9994422,0.00009047108,0.00004033438,0.0002441543,0.0001185077,0.00006427467],"domain_scores_gemma":[0.9988163,0.0003766068,0.0001248235,0.0003234791,0.0002851314,0.00007369712],"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":[0.0004119618,0.0002707306,0.009376569,0.0004035263,0.0002717487,0.0007476209,0.0002558607,0.1955982,0.09782693,0.01123257,0.01478677,0.6688175],"study_design_scores_gemma":[0.00001990972,0.0001109291,0.002810742,0.00004476833,0.00003668259,0.0006221389,0.0000423761,0.9347072,0.03929951,0.01542199,0.006838257,0.00004551277],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03618194,0.0005079986,0.9551278,0.0004122271,0.000107734,0.000115731,0.001394153,0.004201538,0.001950896],"genre_scores_gemma":[0.2446003,0.0008640821,0.7395943,0.0005118533,0.0001757618,0.0002949793,0.007340752,0.001129933,0.005488021],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004110693,"threshold_uncertainty_score":0.00818783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01367333308494661,"score_gpt":0.2382939913620721,"score_spread":0.2246206582771255,"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."}}