no code implementations • MIDL 2019 • Leixin Zhou, Wenxiang Deng, Xiaodong Wu
Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications.
no code implementations • 25 May 2019 • Jirong Yi, Hui Xie, Leixin Zhou, Xiaodong Wu, Weiyu Xu, Raghuraman Mudumbai
In this paper, we present a simple hypothesis about a feature compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations.
no code implementations • 11 Jun 2019 • Leixin Zhou, Zisha Zhong, Abhay Shah, Bensheng Qiu, John Buatti, Xiaodong Wu
To the best of our knowledge, this is the first study to apply a 3-D neural network with a CRFs model for direct surface segmentation.
no code implementations • 19 May 2020 • Leixin Zhou, Wenxiang Deng, Xiaodong Wu
An VAE trained on normal images is expected to only be able to reconstruct normal images, allowing the localization of anomalous pixels in an image via manipulating information within the VAE ELBO loss.
no code implementations • 2 Jul 2020 • Hui Xie, Zhe Pan, Leixin Zhou, Fahim A Zaman, Danny Chen, Jost B Jonas, Yaxing Wang, Xiaodong Wu
In this work, we propose to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters.
no code implementations • 2 Jul 2020 • Leixin Zhou, Xiaodong Wu
Automated surface segmentation is important and challenging in many medical image analysis applications.