{"id":"W4412487816","doi":"10.1109/tmi.2025.3589543","title":"Frenet–Serret Frame-Based Decomposition for Part Segmentation of 3-D Curvilinear Structures","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Institute of Neurological Disorders and Stroke; National Institutes of Health; Harvard University; National Science Foundation","keywords":"Frenet–Serret formulas; Segmentation; Curvilinear coordinates; Artificial intelligence; Computer science; Computer vision; Benchmark (surveying); Pattern recognition (psychology); Geometry; Mathematics; Curvature; Geology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002069724,0.000138651,0.0002180113,0.0002351193,0.00009317813,0.0000227018,0.0001286302,0.00007689066,0.0003359066],"category_scores_gemma":[0.00003483022,0.0001324289,0.0001480743,0.0002832018,0.00009920423,0.00007162789,5.935263e-7,0.0002664578,0.000003577255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004691242,"about_ca_system_score_gemma":0.00005935319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000271734,"about_ca_topic_score_gemma":0.000008781825,"domain_scores_codex":[0.9988868,0.0000372363,0.0003563309,0.0001795878,0.0003451167,0.0001949479],"domain_scores_gemma":[0.9993539,0.0002628467,0.00003262983,0.0001637429,0.00006105917,0.0001258175],"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":[0.00004015231,0.0002291631,0.00033965,0.0007574706,0.0003381886,0.000006646077,0.0001357933,0.3773739,0.02138023,0.0001421605,0.006563331,0.5926933],"study_design_scores_gemma":[0.0007415479,0.00001036823,0.0000280509,0.0002510419,0.0001398972,0.000001070707,0.00006084199,0.8609883,0.1361992,0.0004599744,0.001008255,0.0001115442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01031914,0.0001860185,0.9870624,0.001018208,0.0009049024,0.0001315067,0.00003846832,0.0001828825,0.0001564588],"genre_scores_gemma":[0.9875957,0.00005825911,0.0113805,0.0007250417,0.00007658007,0.00005852886,0.00004455718,0.000019768,0.0000410367],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9772766,"threshold_uncertainty_score":0.5400293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007461822799660337,"score_gpt":0.2914499922012302,"score_spread":0.2839881694015699,"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."}}