{"id":"W2062322640","doi":"10.1016/j.compmedimag.2012.04.005","title":"An edge-region force guided active shape approach for automatic lung field detection in chest radiographs","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Segmentation; Radiography; Computer science; Artificial intelligence; Active shape model; Computer vision; Lung; Field (mathematics); Edge detection; Sensitivity (control systems); Radiology; Image segmentation; Computer-aided diagnosis; Pattern recognition (psychology); Image processing; Medicine; Image (mathematics); Mathematics; Engineering","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":[0.0006289473,0.0007092205,0.0007526406,0.001278928,0.000437264,0.0008140299,0.001663413,0.001399473,0.00195661],"category_scores_gemma":[0.001393784,0.000691077,0.0008546395,0.0006630395,0.0004225619,0.0006723423,0.0009449269,0.0009288697,0.0008003684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003280318,"about_ca_system_score_gemma":0.0008099152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00284302,"about_ca_topic_score_gemma":0.004491315,"domain_scores_codex":[0.9995901,0.00006544963,0.00001932003,0.00005568152,0.0002416433,0.00002778433],"domain_scores_gemma":[0.9993452,0.0002637802,0.00006407627,0.00006836377,0.0002165639,0.0000419621],"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":[0.0004659686,0.0002597195,0.001072011,0.0001649292,0.00007189669,0.0001904474,0.0002105148,0.07675636,0.2372576,0.002984737,0.001904517,0.6786612],"study_design_scores_gemma":[0.00001833477,0.00007842253,0.0008556714,0.00001344334,0.00002332727,0.0002657969,0.00002300533,0.9654457,0.03102071,0.0008172972,0.001414508,0.00002387194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01578456,0.0001455886,0.9826508,0.00006555334,0.00001945131,0.00005431362,0.00003338569,0.0007007972,0.0005454816],"genre_scores_gemma":[0.1539751,0.0002220845,0.8426476,0.0001493863,0.00003980536,0.0001053218,0.0001202063,0.0002687817,0.002471736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00284302,"threshold_uncertainty_score":0.006545544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02098830458150127,"score_gpt":0.308642393935357,"score_spread":0.2876540893538558,"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."}}