{"id":"W4224089514","doi":"10.1016/j.cccb.2022.100142","title":"Automatic quantification of perivascular spaces in T2-weighted images at 7 T MRI","year":2022,"lang":"en","type":"article","venue":"Cerebral Circulation - Cognition and Behavior","topic":"Cerebrospinal fluid and hydrocephalus","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"H2020 European Research Council; HORIZON EUROPE Framework Programme; European Research Council; Seventh Framework Programme; Horizon 2020 Framework Programme; Weston Brain Institute","keywords":"Perivascular space; T2 weighted; Artificial intelligence; Magnetic resonance imaging; Computer science; Pattern recognition (psychology); Medicine; Computer vision; Radiology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001758471,0.0001297789,0.0001835427,0.0002418939,0.0003308304,0.00004584606,0.00009591206,0.0000439093,0.002883771],"category_scores_gemma":[0.00005025902,0.0001401002,0.00007461591,0.000431987,0.0001102018,0.0002429426,0.00009015665,0.0001248851,0.00002375148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008553234,"about_ca_system_score_gemma":0.00002532537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002996071,"about_ca_topic_score_gemma":0.000009787233,"domain_scores_codex":[0.9985344,0.0001809643,0.0003488385,0.0003774323,0.0003898983,0.0001684913],"domain_scores_gemma":[0.9995257,0.00005082861,0.0001599461,0.000159513,0.00004541736,0.00005863998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003609413,0.0004896525,0.05233587,0.00008231923,0.000003603722,0.00001309708,0.0006056126,0.00009631038,0.9381844,0.001004231,0.00004327891,0.007105567],"study_design_scores_gemma":[0.001696873,0.0001402956,0.8097947,0.00003348857,0.0001324016,0.000123514,0.0003728775,0.01893031,0.1676316,0.0006010677,0.0002229116,0.0003198931],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985459,0.00008374222,0.0001162796,0.0001690178,0.0001360981,0.0004910465,0.00007015657,0.0000712104,0.0003165319],"genre_scores_gemma":[0.9993787,0.00001961075,0.00006847851,0.0001006799,0.00001842351,0.0001505996,0.000124795,0.0000162919,0.0001223916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7705527,"threshold_uncertainty_score":0.9980277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03498815468777981,"score_gpt":0.2781392767309738,"score_spread":0.243151122043194,"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."}}