{"id":"W1990737836","doi":"10.1016/j.patcog.2007.01.012","title":"Semi-automatic computer aided lesion detection in dental X-rays using variational level set","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":76,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; CARE Canada","funders":"","keywords":"Segmentation; Artificial intelligence; Radiodensity; Computer science; Support vector machine; Pattern recognition (psychology); Image segmentation; Computer vision; Level set (data structures); Focus (optics); Classifier (UML); Level set method; Active contour model; Radiography; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004656674,0.0001527218,0.0001390244,0.0004372132,0.0001161705,0.00008601177,0.00007817358,0.0001010267,0.0002001023],"category_scores_gemma":[0.00001866944,0.0001773494,0.0001000001,0.0003375512,0.00002416359,0.0003255891,0.00003891426,0.0001872958,0.0002583465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001610541,"about_ca_system_score_gemma":0.00001012541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003216928,"about_ca_topic_score_gemma":0.0009140744,"domain_scores_codex":[0.9986483,0.00008919369,0.0004013493,0.0002846194,0.0003081347,0.0002683526],"domain_scores_gemma":[0.9995565,0.0000865293,0.0001474359,0.000103969,0.00004592801,0.00005963963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004472273,0.0001773585,0.3446736,0.00007642204,0.0000387403,0.0001515255,0.000259843,0.00009049243,0.03550938,0.000001233855,0.00004916458,0.6189275],"study_design_scores_gemma":[0.001108894,0.00003523758,0.8704405,0.0002256024,0.00003067127,0.0004995342,0.0001839556,0.1109629,0.01597592,0.0002846047,0.00001098559,0.0002412251],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6319189,0.00001069916,0.3669896,0.000003232668,0.0007482861,0.0001341272,0.00003635648,0.00005021536,0.0001085226],"genre_scores_gemma":[0.9962648,0.000002381213,0.002855731,0.0001906053,0.0003426842,0.000007240789,0.0003039801,0.00002378296,0.000008860647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6186863,"threshold_uncertainty_score":0.7232099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06774301782341154,"score_gpt":0.3020497124706224,"score_spread":0.2343066946472109,"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."}}