{"id":"W3124703593","doi":"10.59275/j.melba.2021-3581","title":"FlowReg: Fast Deformable Unsupervised Medical Image Registration using Optical Flow","year":2021,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; York University; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Alzheimer's Disease Neuroimaging Initiative; U.S. Department of Defense","keywords":"Artificial intelligence; Computer science; Image registration; Pixel; Computer vision; Neuroimaging; Affine transformation; Similarity (geometry); Optical flow; Pattern recognition (psychology); Deep learning; Image (mathematics); Mathematics","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":[0.0048241,0.0002029764,0.0003581224,0.0001895352,0.0003751435,0.0002564129,0.001173814,0.0000984534,0.0002037625],"category_scores_gemma":[0.004325868,0.0001368691,0.0002062395,0.0005650119,0.0004071209,0.0009242274,0.0003446637,0.001076291,0.000007028061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119642,"about_ca_system_score_gemma":0.0006356529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002239384,"about_ca_topic_score_gemma":0.00000216523,"domain_scores_codex":[0.9962031,0.0004824346,0.0009637582,0.000237371,0.001658336,0.0004550209],"domain_scores_gemma":[0.9974476,0.0007265291,0.0004604829,0.0003393221,0.0005534877,0.0004725896],"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":[0.0001160063,0.0003592713,0.0002583194,0.000186545,0.0001249999,0.0007451217,0.001247235,0.0007597464,0.1118019,0.0007975088,0.004149055,0.8794543],"study_design_scores_gemma":[0.001289867,0.0001433996,0.00004933031,0.000195886,0.00006426318,0.00311714,0.0001805147,0.9650901,0.02630311,0.000837116,0.002560693,0.0001686095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002192823,0.0005351202,0.9809822,0.01540259,0.0004471046,0.0001226717,0.000002016548,0.0001037311,0.0002117314],"genre_scores_gemma":[0.0882025,0.0001500679,0.9087496,0.002064055,0.0006079259,0.000004257026,0.00003027774,0.00003588993,0.0001554492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9643303,"threshold_uncertainty_score":0.558136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499695075815004,"score_gpt":0.3027160138397985,"score_spread":0.2877190630816484,"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."}}