{"id":"W3193289316","doi":"10.1109/icip42928.2021.9506285","title":"SepUnet: Depthwise Separable Convolution Integrated U-Net For MRI Reconstruction","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Unavailability; Deep learning; Artificial intelligence; Rendering (computer graphics); Convolution (computer science); Deep neural networks; Latency (audio); Iterative reconstruction; Artificial neural network; Machine learning; Computer engineering","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":[0.000487597,0.0009095217,0.0006346128,0.0004264911,0.0002820462,0.0007213961,0.001429816,0.00109116,0.003801979],"category_scores_gemma":[0.001124335,0.0003498664,0.0005824174,0.0004019662,0.0003517696,0.0009197504,0.001138292,0.001220989,0.00134124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004915115,"about_ca_system_score_gemma":0.001216562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004478743,"about_ca_topic_score_gemma":0.007925245,"domain_scores_codex":[0.9998209,0.00002774157,0.00001046771,0.00004408011,0.00006227953,0.0000344902],"domain_scores_gemma":[0.9998198,0.00004876237,0.00001949841,0.00003312681,0.00005508364,0.00002368772],"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":[0.000517746,0.0001827478,0.001607054,0.0001933768,0.0001321491,0.0003634096,0.00006588745,0.2990624,0.01857766,0.009077272,0.01980809,0.6504122],"study_design_scores_gemma":[0.000009046646,0.00006287581,0.0001159084,0.00001218521,0.000009299538,0.000114586,0.000007491083,0.9903261,0.005203253,0.001925579,0.00220601,0.000007648235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01650209,0.0008408848,0.9736225,0.0002741804,0.0001317682,0.0000872028,0.0003144426,0.00495202,0.003274852],"genre_scores_gemma":[0.3333679,0.0009073152,0.6480485,0.0006626024,0.0000810409,0.0002043314,0.002249875,0.0004804998,0.0139979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004478743,"threshold_uncertainty_score":0.01271886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01988420649640424,"score_gpt":0.3217015679332629,"score_spread":0.3018173614368587,"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."}}