Publications
A collection of my research work.
Rethinking the detail-preserved completion of complex tubular structures based on point cloud: A dataset and a benchmark
Yaolei Qi, Yikai Yang, Wenbo Peng, Shumei Miao, Yutao Hu, Guanyu Yang
Medical Image Analysis 2026
This paper introduces PC-CAC, an open-source clinical point cloud dataset for coronary artery completion, and proposes TSRNet as a strong benchmark method.
CMSA-Net: Causal Multi-scale Aggregation with Adaptive Multi-source Reference for Video Polyp Segmentation
Tong Wang, Yaolei Qi, Siwen Wang, Imran Razzak, Guanyu Yang†, Yutong Xie†
International Conference on Medical Image Computing and Computer-Assisted Intervention 2026
This paper introduces CMSA-Net for real-time video polyp segmentation using causal multi-scale aggregation and adaptive multi-source references.
AEGIS: Using Conditional Multi-View Diffusion Model to Achieve Angiographic Enhancement in Non-Contrast CT
Jiahao Xia, Xiaolei Zhang, Yuting He, Yaolei Qi, Yutao Hu, Pascal Haigron, Chunxiang Tang, Longjiang Zhang†, Guanyu Yang†
IEEE Transactions on Circuits and Systems for Video Technology 2025
This paper presents AEGIS, a multi-view conditional diffusion framework that generates angiographic enhancement from non-contrast CT to support contrast-agent-free clinical imaging.
PathFL: Multi-alignment Federated Learning for pathology image segmentation
Yuan Zhang, Feng Chen, Yaolei Qi, Guanyu Yang†, Huazhu Fu†
Medical Image Analysis 2025
This paper presents PathFL, a multi-alignment Federated Learning framework for pathology image segmentation.
Dscenet: Dynamic screening and clinical-enhanced multimodal fusion for mpns subtype classification
Yuan Zhang, Yaolei Qi, Xiaoming Qi, Yongyue Wei, Guanyu Yang†
International Conference on Medical Image Computing and Computer-Assisted Intervention 2024
This paper introduces DSCENet for MPN subtype classification by fusing whole slide images with clinical information.
Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation
Yaolei Qi, Yuting He, Xiaoming Qi, Yuan Zhang, Guanyu Yang†
Proceedings of the IEEE/CVF international conference on computer vision 2023
This work presents Dynamic Snake Convolution, which adaptively models the geometry of thin and curvilinear tubular structures to improve segmentation performance.
Partial vessels annotation-based coronary artery segmentation with self-training and prototype learning
Zheng Zhang, Xiaolei Zhang, Yaolei Qi, Guanyu Yang†
International Conference on Medical Image Computing and Computer-Assisted Intervention 2023
This paper introduces a label-efficient framework for coronary artery segmentation using partial vessel annotations, self-training, and prototype learning.
Examinee-examiner network: Weakly supervised accurate coronary lumen segmentation using centerline constraint
Yaolei Qi, Han Xu, Yuting He, Guanyu Li, Zehang Li, Youyong Kong, Jean-Louis Coatrieux, Huazhong Shu, Guanyu Yang†, Shengxian Tu†
IEEE Transactions on Image Processing 2021
This paper proposes EE-Net, a weakly supervised framework that leverages centerline-based topological constraints to improve the continuity and accuracy of coronary lumen segmentation in CCTA images.