Hangbei Cheng

Hangbei Cheng

Auto-generated profile, based on publicly available information

Hangbei Cheng

College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
5 April 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
HCHangbei Cheng
Hangbei Cheng
XLXueyu Liu
Xueyu Liu
JZJun Zhang
Jun Zhang
XDXiaorong Dong
Xiaorong Dong
XMXuetao Ma
Xuetao Ma
YWYongfei Wu
Yongfei Wu

25 March 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
XLXueyu Liu
Xueyu Liu
RWRui Wang
Rui Wang
YLYexin Lai
Yexin Lai
YWYongfei Wu
Yongfei Wu
HCHangbei Cheng
Hangbei Cheng
Wen ZhengWen Zheng
Wen Zheng
Accurately diagnosing chronic kidney disease requires pathologists to assess the structure of multiple tissues under different stains, a process that is timeconsuming and labor-intensive. Current AI-based methods for automatic structure assessment, like segmentation, often demand extensive manual annotation and focus on single stain domain. To address these challenges, we introduce MSMTSeg, a generative self-supervised meta-learning framework for multi-stained multi-tissue segmentation in renal biopsy whole slide images (WSIs). MSMTSeg incorporates multiple stain transform models for style translation of inter-stain domains, a self-supervision module for obtaining pre-trained models with the domain-specific feature representation, and a meta-learning strategy that leverages generated virtual data and pre-trained models to learn the domain-invariant feature representation across multiple stains, thereby enhancing segmentation performance. Experimental results demonstrate that MSMTSeg achieves superior and robust performance, with mDSC of 0.836 and mIoU of 0.718 for multiple tissues under different stains, using only one annotated training sample for each stain. Our ablation study confirms the effectiveness of each component, positioning MSMTSeg ahead of classic advanced segmentation networks, recent few-shot segmentation methods, and unsupervised domain adaptation methods. In conclusion, our proposed few-shot cross-domain technology offers a feasible and cost-effective solution for multi-stained renal histology segmentation, providing convenient assistance to pathologists in clinical practice. The source code and conditionally accessible data are available at https://github.com/SnowRain510/MSMTSeg.

4 June 2026 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
DCDaoxi Cao
Daoxi Cao
HCHangbei Cheng
Hangbei Cheng
YLYijin Li
Yijin Li
RZRuolin Zhou
Ruolin Zhou
XZXuehan Zhang
Xuehan Zhang
YWYongfei Wu
Yongfei Wu


5 March 2026 in Pattern Recognition
Verified
Journal Article
Closed access
HCHangbei Cheng
Hangbei Cheng
XDXiaorong Dong
Xiaorong Dong
JSJia Shen
Jia Shen
GSGuangze Shi
Guangze Shi
XLXueyu Liu
Xueyu Liu
YWYongfei Wu
Yongfei Wu