{"id":"W4378803348","doi":"10.1088/1361-6560/acda78","title":"Bidirectional feature matching based on deep pairwise contrastive learning for multiparametric MRI image synthesis","year":2023,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Modality (human–computer interaction); Pattern recognition (psychology); Feature vector; Feature learning; Matching (statistics); Deep learning; Pairwise comparison; Modalities; Parametric statistics; 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":[0.0002215141,0.00009626707,0.0001795972,0.0001476485,0.0001182225,0.000007184448,0.0001437723,0.00004667732,0.000001199895],"category_scores_gemma":[0.0003543851,0.00007365442,0.00002492565,0.0008632296,0.00009241503,0.00005668077,0.00004250809,0.0001949,0.000004619863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001963249,"about_ca_system_score_gemma":0.00001095845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008880081,"about_ca_topic_score_gemma":0.000003812052,"domain_scores_codex":[0.9992712,0.00006959918,0.0001018208,0.0003090305,0.00005497337,0.0001933695],"domain_scores_gemma":[0.9959682,0.003778868,0.00006119734,0.0001155382,0.00004004476,0.00003620257],"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":[0.0001269663,0.0001564907,0.005696878,0.00006902646,0.00004183835,0.00001168789,0.0007034047,0.1147377,0.02363137,0.06018866,0.002818416,0.7918176],"study_design_scores_gemma":[0.0005159997,0.0001718909,0.003594891,0.00004382643,0.000007119322,0.000001430878,0.00005739491,0.9513649,0.0006682685,0.0419549,0.001507907,0.0001114535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008489838,0.00006914695,0.9855631,0.005280661,0.00012674,0.0002341088,0.000003735692,0.0001069773,0.0001256998],"genre_scores_gemma":[0.9591758,0.00011943,0.03936894,0.0007049894,0.0003297362,0.0002321291,0.00003237621,0.000009444651,0.00002712685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.950686,"threshold_uncertainty_score":0.300354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09728787595367502,"score_gpt":0.3662861870463183,"score_spread":0.2689983110926433,"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."}}