Yanwu Xu

Yanwu Xu

Auto-generated profile, based on publicly available information

Yanwu Xu

Google {yanwuxu

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 June 2024 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YXYanwu Xu
Yanwu Xu
LSLi Sun
Li Sun
WPWei Peng
Wei Peng
SJShuyue Jia
Shuyue Jia
KMKatelyn Morrison
Katelyn Morrison
KBKayhan Batmanghelich
Kayhan Batmanghelich
This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. While diffusion-based generative models are increasingly used in medical imaging, current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports’ abundant information. The radiology reports can enhance the generation process by providing additional guidance and offering fine-grained control over the synthesis of images. Nevertheless, expanding text-guided generation to high-resolution 3D images poses significant memory and anatomical detail-preserving challenges. Addressing the memory issue, we introduce a hierarchical scheme that uses a modified UNet architecture. We start by synthesizing low-resolution images conditioned on the text, serving as a foundation for subsequent generators for complete volumetric data. To ensure the anatomical plausibility of the generated samples, we provide further guidance by generating vascular, airway, and lobular segmentation masks in conjunction with the CT images. The model demonstrates the capability to use textual input and segmentation tasks to generate synthesized images. Algorithmic comparative assessments and blind evaluations conducted by 10 board-certified radiologists indicate that our approach exhibits superior performance compared to the most advanced models based on GAN and diffusion techniques, especially in accurately retaining crucial anatomical features such as fissure lines and airways. This innovation introduces novel possibilities. This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements. The advancements in image generation can be applied to enhance numerous downstream tasks.

31 October 2024
Verified
Book Chapter
Closed access
PDF file
YZYang Zhao
Yang Zhao
YXYanwu Xu
Yanwu Xu
ZXZhisheng Xiao
Zhisheng Xiao
HJHaolin Jia
Haolin Jia
THTingbo Hou
Tingbo Hou

10 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
YXYanwu Xu
Yanwu Xu
MGMingming Gong
Mingming Gong
SXShaoan Xie
Shaoan Xie
WWWei Wei
Wei Wei
MGMatthias Grundmann
Matthias Grundmann
THTingbo Hou
Tingbo Hou
Despite the proliferation of generative models, achieving fast sampling during inference without compromising sample diversity and quality remains challenging. Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. The Denoising Diffusion Generative Adversarial Networks (DDGAN) attempted to circumvent this limitation by integrating a GAN model for larger jumps in the diffusion process. However, DDGAN encountered scalability limitations when applied to large datasets. To address these limitations, we introduce a novel approach that tackles the problem by matching implicit and explicit factors. More specifically, our approach involves utilizing an implicit model to match the marginal distributions of noisy data and the explicit conditional distribution of the forward diffusion. This combination allows us to effectively match the joint denoising distributions. Unlike DDPM but similar to DDGAN, we do not enforce a parametric distribution for the reverse step, enabling us to take large steps during inference. Similar to the DDPM but unlike DDGAN, we take advantage of the exact form of the diffusion process. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.