{"id":"W2582207877","doi":"10.1109/tbme.2017.2649481","title":"Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"AI in cancer detection","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Jaccard index; Segmentation; Mammography; Pectoral muscle; Artificial intelligence; Hausdorff distance; Computer-aided diagnosis; Sørensen–Dice coefficient; Pattern recognition (psychology); Computer science; Breast cancer; Breast tissue; Image segmentation; Computer vision; Medicine; Cancer; Anatomy","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":[0.0001627622,0.0001867501,0.0001710105,0.0002744932,0.0003424915,0.000258753,0.0007204278,0.0001344278,0.00009412732],"category_scores_gemma":[0.00001417991,0.0001897569,0.0001205557,0.000306091,0.00006969986,0.0004817402,0.000004945984,0.0003172541,0.0000806527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002092397,"about_ca_system_score_gemma":0.00005139508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002354207,"about_ca_topic_score_gemma":0.00003528551,"domain_scores_codex":[0.9985672,0.00002106676,0.0002449791,0.0004124215,0.0004615105,0.0002927872],"domain_scores_gemma":[0.9987936,0.00009103216,0.00009104875,0.0007859809,0.00003105163,0.0002072909],"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":[0.00001472417,0.0001965744,0.00001535125,0.00002654727,0.00005447638,0.00001995564,0.0001371236,0.04501315,0.05539779,0.00003505358,0.0001589602,0.8989303],"study_design_scores_gemma":[0.0009806522,0.0002098531,0.002277348,0.00008369123,0.00002351286,0.000003769552,0.000008549771,0.9000157,0.08322015,0.00003901951,0.01278446,0.0003533149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01997818,0.00002598469,0.9750134,0.0006759677,0.003671512,0.0001554269,0.000021323,0.0004356023,0.00002264252],"genre_scores_gemma":[0.9186703,0.00001542444,0.08089941,0.0001017542,0.000177047,0.00007521574,0.000004969304,0.0000212787,0.00003461106],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8986921,"threshold_uncertainty_score":0.7738063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316322466870595,"score_gpt":0.2649810204851122,"score_spread":0.2418177958164062,"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."}}