Honglun Li
Qingdao University
10 Papers
26 Citations
Honglun Li is an academic researcher from Qingdao University. The author has contributed to research in topics: Segmentation & Image segmentation. The author has an hindex of 2, co-authored 7 publications.
Chat about Author
Papers
Integrating support vector machine and graph cuts for medical image segmentation
TL;DR: A novel graph cuts-based segmentation method that combines the constraint information of machine learning result, the edge information, the local information, and the remote-local information is proposed for post-processing and can achieve better performance than the state-of-the-art.
28
How segmentation methods affect hippocampal radiomic feature accuracy in Alzheimer’s disease analysis?
TL;DR: The hippocampal radiomic features exhibited high measurement/statistical/clinical consistency across different hippocampal segmentation methods, and the best performance in AD classification was obtained when HRFs were extracted by the naïve majority voting method with a more sufficient segmentation and relatively low hippocampus segmentation accuracy.
9
HPCSeg-Net: Hippocampus Segmentation Network Integrating Autofocus Attention Mechanism and Feature Recombination and Recalibration Module
Bin Liu,Qiang Zheng,Kun Zhao,Honglun Li,Chaoqing Ma,Shuanhu Wu,Xiangrong Tong +6 more
- 06 Aug 2021
TL;DR: In this article, a novel HPCSeg-Net was proposed for hippocampus segmentation based on the U-Net framework, which adopted a cascaded autofocus attention mechanism and adaptive feature recombination and recalibration module.
2
Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer’s disease on routinely acquired T1-weighted imaging-based brain network
Chuanzhen Zhu,Honglun Li,Zhiwei Song,Minbo Jiang,Limei Song,Lin Li,Xuan Wang,Qiang Zheng +7 more
2
HPCReg-Net: Unsupervised U-Net Integrating Dilated Convolution and Residual Attention for Hippocampus Registration
Hu Yu,Qiang Zheng,Kun Zhao,Honglun Li,Chaoqing Ma,Shuanhu Wu,Xiangrong Tong +6 more
- 29 Oct 2021
TL;DR: In this paper, a 3D unsupervised U-Net registration model HPCReg-Net was proposed under a coarse-fine registration strategy, which combined dilated convolution and residual attention module.
1