{"id":"W4406200569","doi":"10.1007/s10439-024-03675-x","title":"Swin UNETR Segmentation with Automated Geometry Filtering for Biomechanical Modeling of Knee Joint Cartilage","year":2025,"lang":"en","type":"article","venue":"Annals of Biomedical Engineering","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Hausdorff distance; Biomechanics; Computer science; Artificial intelligence; Knee Joint; Sørensen–Dice coefficient; Similarity (geometry); Cartilage; Biomedical engineering; Image segmentation; Computer vision; Pattern recognition (psychology); Algorithm; Engineering; Anatomy; Medicine; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002286547,0.0001528559,0.0004201488,0.0004850479,0.00002208228,0.000006021058,0.00005038151,0.000119777,0.00001491044],"category_scores_gemma":[0.0001140344,0.0001287851,0.0001184084,0.0005034739,0.00003151978,0.00005803439,0.00003457481,0.00007515759,6.790546e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002225769,"about_ca_system_score_gemma":0.00006381649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009995279,"about_ca_topic_score_gemma":6.769706e-7,"domain_scores_codex":[0.998838,0.000007315045,0.0004427829,0.0001972309,0.0002529271,0.0002617361],"domain_scores_gemma":[0.9994577,0.00005711262,0.00007029388,0.0001634665,0.0001266897,0.0001247261],"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":[0.0002180027,0.0001765414,0.00001484652,0.0009516806,0.0001438644,0.00001495046,0.00005623799,0.002102026,0.9847167,0.0006188833,0.00007474762,0.01091152],"study_design_scores_gemma":[0.002297468,0.001774211,0.00003000043,0.001125387,0.00009648681,0.000008674871,0.0000783667,0.3679032,0.6264402,0.00004862686,0.00009838104,0.00009895373],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7632563,0.0003653465,0.2350359,0.0003777321,0.0001778855,0.0004952894,0.00004763616,0.0001957244,0.00004815396],"genre_scores_gemma":[0.9785644,0.00002610872,0.02108838,0.00007150492,0.00003834188,0.00004856733,0.0001032556,0.00002146812,0.00003795323],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3658012,"threshold_uncertainty_score":0.5251706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02954060442578413,"score_gpt":0.2952146962379312,"score_spread":0.2656740918121471,"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."}}