{"id":"W4413140919","doi":"10.1007/s11548-025-03494-y","title":"Benchmarking NousNav: quantifying the spatial accuracy and clinical performance of an affordable, open-source neuronavigation system","year":2025,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Neuronavigation; Computer science; Benchmarking; Benchmark (surveying); Baseline (sea); Imaging phantom; Software; Open source; Artificial intelligence; Calibration; Medical physics; Computer vision; Medicine; Nuclear medicine; Radiology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001704226,0.0006509018,0.0004828076,0.0007471481,0.0002157084,0.001124004,0.001273847,0.0009633395,0.001901601],"category_scores_gemma":[0.01190875,0.0002424854,0.0003213118,0.000617491,0.0006945792,0.0007925761,0.001532431,0.0004287599,0.001196829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008923966,"about_ca_system_score_gemma":0.001694982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01114441,"about_ca_topic_score_gemma":0.01877012,"domain_scores_codex":[0.998393,0.0003821246,0.0001432765,0.0002884428,0.0006888089,0.0001043581],"domain_scores_gemma":[0.996182,0.00167484,0.0002608584,0.0004828577,0.001121355,0.0002779637],"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":[0.009732558,0.001017623,0.0935879,0.001592107,0.001165449,0.001172981,0.001325956,0.2351027,0.08424488,0.003920883,0.03626481,0.5308722],"study_design_scores_gemma":[0.00112158,0.006384325,0.09820044,0.0003120695,0.0006582577,0.005980322,0.001487067,0.6971431,0.1395297,0.004772901,0.04395176,0.0004584041],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8808653,0.003325265,0.0907803,0.0006051575,0.0004492397,0.000251435,0.003448817,0.01433,0.005944499],"genre_scores_gemma":[0.9528317,0.0004345603,0.03912145,0.0002175971,0.00003937453,0.00006580368,0.004308154,0.0009105653,0.002070794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01114441,"threshold_uncertainty_score":0.02215904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02759047444598533,"score_gpt":0.3447341492770163,"score_spread":0.317143674831031,"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."}}