# Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis Source: [Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis]() Collection index: [llms.txt]() Data updated: 2026-01-01T13:38:27.108Z Authors: Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo, Reese Timothy, Jerry L. Prince, Georges El Fakhri, Jonghye Woo Published: 2021-06-23T16:19:00.000Z ## Abstract Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target domains. However, while the self-training UDA has demonstrated its effectiveness on discriminative tasks, such as classification and segmentation, via the reliable pseudo-label selection based on the softmax discrete histogram, the self-training UDA for generative tasks, such as image synthesis, is not fully investigated. In this work, we propose a novel generative self-training (GST) UDA framework with continuous value prediction and regression objective for cross-domain image synthesis. Specifically, we propose to filter the pseudo-label with an uncertainty mask, and quantify the predictive confidence of generated images with practical variational Bayes learning. The fast test-time adaptation is achieved by a round-based alternative optimization scheme. We validated our framework on the tagged-to-cine magnetic resonance imaging (MRI) synthesis problem, where datasets in the source and target domains were acquired from different scanners or centers. Extensive validations were carried out to verify our framework against popular adversarial training UDA methods. Results show that our GST, with tagged MRI of test subjects in new target domains, improved the synthesis quality by a large margin, compared with the adversarial training UDA methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Tagged-to-cine MR Image Synthesis on Cross-scanner tagged-to-cine MR](): Tagged-to-cine MR image synthesis; Cross-scanner tagged-to-cine MR; L1 Loss: 158.6. - [Tagged-to-cine MR Image Synthesis on Cross-center tagged-to-cine MR Clinical Center B](): Tagged-to-cine MR image synthesis; Cross-center tagged-to-cine MR Clinical Center B; IS: 9.76. ## Original sources and implementation [Original paper]() [PDF]()