{"id":"W2592740045","doi":"10.1117/12.2254320","title":"Automated assessment of breast tissue density in non-contrast 3D CT images without image segmentation based on a deep CNN","year":2017,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"AI in cancer detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Breast tissue; Convolutional neural network; Breast density; Segmentation; Ground truth; Pattern recognition (psychology); Contrast (vision); Breast imaging; Deep learning; Robustness (evolution); Tomography; Mammography; Computer vision; Breast cancer; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004567757,0.000869461,0.0004906097,0.001522398,0.0001736421,0.0005525624,0.0008697502,0.0005847287,0.0007704044],"category_scores_gemma":[0.001068158,0.0004478137,0.0004980512,0.0006234721,0.0002838639,0.0006834714,0.0007483819,0.0003858912,0.0004140824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005664018,"about_ca_system_score_gemma":0.0005008376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004945674,"about_ca_topic_score_gemma":0.008727545,"domain_scores_codex":[0.9996842,0.00004153305,0.0000197663,0.00009568554,0.0001061934,0.00005266638],"domain_scores_gemma":[0.9996526,0.0000870021,0.00007200769,0.00005382624,0.0001078414,0.00002676636],"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":[0.0004661266,0.0002141452,0.03088474,0.000268352,0.0002611667,0.0005107225,0.0001595253,0.08708146,0.1736126,0.001385496,0.003669537,0.7014862],"study_design_scores_gemma":[0.00001429927,0.00008365222,0.01630657,0.00003030194,0.0000772351,0.000575915,0.00005007178,0.9403579,0.03941898,0.001104525,0.001952709,0.00002782317],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2014441,0.001220544,0.7902591,0.0002556523,0.00007664991,0.0001765378,0.0006489403,0.003260198,0.002658134],"genre_scores_gemma":[0.7024102,0.0009407387,0.2921058,0.0002529022,0.00006578444,0.0001298383,0.001430601,0.0001495892,0.002514528],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004945674,"threshold_uncertainty_score":0.009833753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00762455197650479,"score_gpt":0.2643549811413109,"score_spread":0.2567304291648061,"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."}}