X
Xin Yi
Researcher at University of Saskatchewan
Publications - 11
Citations - 1512
Xin Yi is an academic researcher from University of Saskatchewan. The author has contributed to research in topics: Catheter & Feature extraction. The author has an hindex of 7, co-authored 10 publications receiving 885 citations.
Papers
More filters
Journal ArticleDOI
Generative adversarial network in medical imaging: A review.
TL;DR: A review of recent advances in medical imaging using the adversarial training scheme with the hope of benefiting researchers interested in this technique.
Journal ArticleDOI
Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network
Xin Yi,Paul Babyn +1 more
TL;DR: A deep learning-based approach was proposed to mitigate the quantum noise in low-dose computed tomography, using an adversarially trained network and a sharpness detection network to guide the training process.
Journal ArticleDOI
LBP-Based Segmentation of Defocus Blur
Xin Yi,Mark Eramian +1 more
TL;DR: A sharpness metric based on local binary patterns and a robust segmentation algorithm to separate in- and out-of-focus image regions are proposed and obtained high-quality sharpness maps.
Journal ArticleDOI
Sharpness-aware Low dose CT denoising using conditional generative adversarial network
Xin Yi,Paul Babyn +1 more
TL;DR: In this article, an adversarially trained network and a sharpness detection network were trained to guide the training process and the results of the proposed method have very small resolution loss and achieves better performance relative to the state-of-the-art methods both quantitatively and visually.
Posted Content
Unsupervised and semi-supervised learning with Categorical Generative Adversarial Networks assisted by Wasserstein distance for dermoscopy image Classification.
Xin Yi,Ekta Walia,Paul Babyn +2 more
TL;DR: This work proposes to use categorical generative adversarial network to automatically learn the feature representation of dermoscopy images in an unsupervised and semi-supervised manner and demonstrates that the proposed feature learning method has achieved an average precision score of 0.424.