{"id":"W2024384381","doi":"10.1088/0031-9155/52/13/010","title":"Evaluating an optical-flow-based registration algorithm for contrast-enhanced magnetic resonance imaging of the breast","year":2007,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Johnson and Johnson","keywords":"Contrast (vision); Computer science; Optical flow; Magnetic resonance imaging; Computer vision; Voxel; Intensity (physics); Dynamic contrast; SIGNAL (programming language); Image registration; Displacement (psychology); Artificial intelligence; Algorithm; Breast MRI; Breast cancer; Mammography; Optics; Image (mathematics); Physics; Radiology; Medicine; Cancer","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001006745,0.0001074553,0.0003019499,0.00004118431,0.00004049785,0.000002105475,0.00007768814,0.00005467866,0.00001293884],"category_scores_gemma":[0.0001956397,0.00007035587,0.00003271283,0.0001851402,0.0004394014,0.00002981294,0.0000145631,0.0001383519,1.545285e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003933298,"about_ca_system_score_gemma":0.0000815021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008788012,"about_ca_topic_score_gemma":0.0000492016,"domain_scores_codex":[0.9990194,0.00005168759,0.0003384341,0.0002484398,0.0001224968,0.0002194824],"domain_scores_gemma":[0.9988168,0.0006028483,0.0001222591,0.0002258325,0.0001788302,0.00005337906],"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":[0.000146757,0.00008885877,0.01556037,0.00005388346,0.000003943472,0.000001044744,0.0001452014,0.00001344885,0.05211959,0.0007314316,0.00009761355,0.9310378],"study_design_scores_gemma":[0.02708536,0.007397391,0.3373829,0.002938897,0.0005459344,0.00009752787,0.001443127,0.4150666,0.1832753,0.02274533,0.00146,0.0005617042],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4294744,0.005448116,0.5422566,0.01820976,0.0006891185,0.002240621,0.00007069511,0.00004375365,0.001566949],"genre_scores_gemma":[0.9688166,0.0001040945,0.02895759,0.001382233,0.0006293975,0.00005116876,0.00003566673,0.00001175519,0.00001151944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9304761,"threshold_uncertainty_score":0.2869029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1486982621233438,"score_gpt":0.439720842421399,"score_spread":0.2910225802980552,"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."}}