{"id":"W2165012181","doi":"10.1007/s10278-014-9723-y","title":"Semi-Automatic Region-of-Interest Segmentation Based Computer-Aided Diagnosis of Mass Lesions from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Based Breast Cancer Screening","year":2014,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Health Sciences Centre; North York General Hospital; Sunnybrook Health Science Centre","funders":"","keywords":"Segmentation; Magnetic resonance imaging; Context (archaeology); Receiver operating characteristic; BI-RADS; Medicine; Computer-aided diagnosis; Radiology; Breast cancer; Breast imaging; Breast MRI; Computer-aided; Artificial intelligence; Computer science; Dynamic contrast-enhanced MRI; Cancer; Mammography; Internal 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000286877,0.0003094805,0.0008478148,0.0004312627,0.00006418264,0.0001185233,0.0002801777,0.00004799447,0.0001299887],"category_scores_gemma":[0.000169647,0.0002887904,0.0003367724,0.0003606422,0.0002064326,0.000787655,0.00004706769,0.0003121103,0.000001817482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002942784,"about_ca_system_score_gemma":0.0002461777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203575,"about_ca_topic_score_gemma":0.00002151646,"domain_scores_codex":[0.997359,0.0001133512,0.001292036,0.0003216067,0.00056438,0.0003496289],"domain_scores_gemma":[0.9961778,0.001227067,0.00137765,0.0003596624,0.0006256289,0.0002321726],"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":[0.0002550571,0.0002938748,0.4742143,0.000282083,0.00007114085,0.00008780695,0.0001360534,0.001678337,0.01524735,0.000002763816,0.0009139435,0.5068172],"study_design_scores_gemma":[0.007788397,0.0003380027,0.2904283,0.01614336,0.0005663073,0.0001609897,0.0003022669,0.6332759,0.0502901,0.0001694948,0.0001484964,0.0003884288],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5811767,0.002511425,0.4087835,0.006317934,0.0004126293,0.0003837777,0.0002755087,0.00004827962,0.00009025636],"genre_scores_gemma":[0.9783241,0.0001195128,0.02061944,0.0006089198,0.0002004625,0.00002869439,0.00002957493,0.00006156084,0.000007762638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6315975,"threshold_uncertainty_score":0.9999564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02090043687909863,"score_gpt":0.2839348754077451,"score_spread":0.2630344385286464,"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."}}