Biography
Xiaoxiang Han is a Ph.D. student with the School of Communication and Information Engineering, Shanghai University, Shanghai, China. His supervisors are Prof. Qi Zhang and Prof. Shugong Xu. His main research interests include medical image/video analysis, weakly/semi/self-supervised learning, computer vision and pattern recognition.
- Medical Image/Video Analysis
- Weakly/Semi/Self-Supervised Learning
- Computer Vision and Pattern Recognition
-
PhD in Information and Communication Engineering
Shanghai University
-
MEng in Electronic Information, 2024
University of Shanghai for Science and Technology
-
BEng in Computer Science and Technology, 2021
Jinling Institute of Technology
Featured Papers
Segmenting anatomical structures and lesions from ultrasound images contributes to disease assessment, diagnosis, and treatment. Weakly supervised learning (WSL) based on sparse annotation has achieved encouraging performance and demonstrated the potential to reduce annotation costs. This study attempts to introduce scribble-based WSL into ultrasound image segmentation tasks. However, ultrasound images often suffer from poor contrast and unclear edges, coupled with insufficient supervison signals for edges, posing challenges to edge prediction. Uncertainty modeling has been proven to facilitate models in dealing with these issues. Nevertheless, existing uncertainty estimation paradigms are not robust enough and often filter out predictions near decision boundaries, resulting in unstable edge predictions. Therefore, we propose leveraging predictions near decision boundaries effectively. Specifically, we introduce Dempster-Shafer Theory (DST) of evidence to design an Evidence-Guided Consistency (EGC) strategy. This strategy utilizes high-evidence predictions, which are more likely to occur near high-density regions, to guide the optimization of low-evidence predictions that may appear near decision boundaries. Furthermore, the diverse sizes and locations of lesions in ultrasound images pose a challenge for convolutional neural networks (CNNs) with local receptive fields, as they struggle to model global information. Therefore, we introduce Visual Mamba based on structured state space sequence models, which achieves long-range dependency with linear computational complexity, and we construct a novel hybrid CNN-Mamba framework. During training, the collaboration between the CNN branch and the Mamba branch in the proposed framework draws inspiration from each other based on the EGC strategy. Extensive experiments on four ultrasound public datasets for binary-class and multi-class segmentation demonstrate the competitiveness of the proposed method. The scribble-annotated dataset and code will be made available on https://github.com/GtLinyer/MambaEviScrib.
Papers
Popular Topics
Contact
- hanxx@shu.edu.cn
- No. 99 Shangda Road, Baoshan District, Shanghai, 200444