most citedYou Don't Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images

2 citations · 2 across the 5 of their papers we have counts for

collaborators

5 papers

eess.IV2023

Style Transfer and Self-Supervised Learning Powered Myocardium Infarction Super-Resolution Segmentation

Lichao Wang, Jiahao Huang, Xiaodan Xing +7

This study proposes a pipeline that incorporates a novel style transfer model and a simultaneous super-resolution and segmentation model. The proposed pipeline aims to enhance diff…

cs.CV20232 cited

You Don't Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images

Xiaodan Xing, Federico Felder, Yang Nan +3

Synthetic images generated from deep generative models have the potential to address data scarcity and data privacy issues. The selection of synthesis models is mostly based on ima…

eess.IV2023

Is Autoencoder Truly Applicable for 3D CT Super-Resolution?

Weixun Luo, Xiaodan Xing, Guang Yang

Featured by a bottleneck structure, autoencoder (AE) and its variants have been largely applied in various medical image analysis tasks, such as segmentation, reconstruction and de…

eess.IV2023

Less is More: Unsupervised Mask-guided Annotated CT Image Synthesis with Minimum Manual Segmentations

Xiaodan Xing, Giorgos Papanastasiou, Simon Walsh +1

As a pragmatic data augmentation tool, data synthesis has generally returned dividends in performance for deep learning based medical image analysis. However, generating correspond…

cs.CV2022

Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI

Jiahao Huang, Xiaodan Xing, Zhifan Gao +1

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhil…