{"id":"W2056206824","doi":"10.1118/1.1591192","title":"A real‐time biopsy needle segmentation technique using Hough Transform","year":2003,"lang":"en","type":"article","venue":"Medical Physics","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"Robarts Clinical Trials","funders":"","keywords":"Hough transform; Computer vision; Computer science; Segmentation; Artificial intelligence; Robustness (evolution); Computation; Imaging phantom; Image segmentation; Residual; Image (mathematics); Algorithm; Radiology; Medicine","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":[0.0003631416,0.0001225657,0.0001405615,0.00005372601,0.000118853,0.00005689329,0.0003105853,0.0001080789,0.00005711802],"category_scores_gemma":[0.00003770321,0.0001121488,0.00007340575,0.0005511016,0.00006152843,0.0004460228,0.00003233222,0.0001830764,0.00003350265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008281931,"about_ca_system_score_gemma":0.0001395405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005779712,"about_ca_topic_score_gemma":4.081148e-7,"domain_scores_codex":[0.9988182,0.00006343857,0.0001941266,0.0002336092,0.0004619713,0.0002286664],"domain_scores_gemma":[0.9994751,0.00003526025,0.000052968,0.0002731324,0.00005214584,0.0001114143],"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":[0.000009203033,0.000395619,0.00001952951,0.00006935423,0.00003742535,0.0001293142,0.001404684,0.000008915201,0.3597149,0.005826362,0.001299629,0.631085],"study_design_scores_gemma":[0.000148304,0.00005767579,0.000004675906,0.00002622208,0.000005343587,0.0000735271,0.00001176673,0.001266539,0.9753703,0.02257448,0.0003209664,0.0001402174],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001857575,0.000008961006,0.9892707,0.0001117833,0.0001101295,0.0002386726,9.164347e-7,0.0005127853,0.007888485],"genre_scores_gemma":[0.6767906,0.00005599435,0.3215679,0.0007160591,0.0003181024,0.0001387565,0.000007372809,0.00004374124,0.0003615447],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.674933,"threshold_uncertainty_score":0.4573295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01273722669061151,"score_gpt":0.2698265809042925,"score_spread":0.257089354213681,"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."}}