{"id":"W4393115599","doi":"10.1007/s11548-024-03077-3","title":"Deep learning-based automatic pipeline for 3D needle localization on intra-procedural 3D MRI","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System","funders":"David Geffen School of Medicine, University of California, Los Angeles; National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Siemens Medical Solutions USA","keywords":"Computer science; Segmentation; Artificial intelligence; Deep learning; Pipeline (software); 3D ultrasound; 3d model; Workflow; Magnetic resonance imaging; Computer vision; Medicine; Ultrasound; Radiology","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":[0.0008569938,0.001030665,0.0005577152,0.0007591994,0.0003410088,0.0007895228,0.00124396,0.0009808083,0.002791937],"category_scores_gemma":[0.001640299,0.0006237193,0.0008854256,0.0004906415,0.0005157841,0.0008409366,0.001096021,0.001280714,0.001473302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009249697,"about_ca_system_score_gemma":0.001717718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004515473,"about_ca_topic_score_gemma":0.007139628,"domain_scores_codex":[0.9995763,0.00006207432,0.00002654047,0.0001144999,0.0001643467,0.00005621935],"domain_scores_gemma":[0.9994057,0.0001965348,0.00009210345,0.0001106845,0.000158159,0.00003675661],"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":[0.000358471,0.0001378227,0.002097741,0.0002730812,0.000104645,0.0002367338,0.0002173882,0.243337,0.1387296,0.003284858,0.004439532,0.6067832],"study_design_scores_gemma":[0.0000152072,0.0001090666,0.0009412389,0.00002063665,0.00002147735,0.0001866845,0.00001805762,0.9540254,0.04035561,0.00180272,0.002482101,0.00002180866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01200508,0.0001052176,0.9837166,0.000073263,0.00001175444,0.00006261713,0.00009163861,0.003439044,0.000494901],"genre_scores_gemma":[0.221251,0.0002473659,0.7748684,0.0001953756,0.00001672751,0.0002072449,0.0007211034,0.0005263222,0.001966381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004515473,"threshold_uncertainty_score":0.009339988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01617526567683683,"score_gpt":0.3067646888866739,"score_spread":0.2905894232098371,"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."}}