C
Chupeng Zhang
Researcher at University of California, Irvine
Publications - 6
Citations - 175
Chupeng Zhang is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Segmentation & Deep learning. The author has an hindex of 4, co-authored 6 publications receiving 84 citations.
Papers
More filters
Book ChapterDOI
NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation
TL;DR: Wang et al. as discussed by the authors proposed a new end-to-end 3D deep convolutional neural network (DCNN) to solve nodule detection, false positive reduction and nodule segmentation jointly in a multi-task fashion.
Posted Content
NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
TL;DR: A new end-to-end 3D deep convolutional neural net (DCNN) to solve nodule detection, false positive reduction and nodule segmentation jointly in a multi-task fashion is proposed, called NoduleNet.
Journal ArticleDOI
A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy.
Xuming Chen,Shanlin Sun,Narisu Bai,Hao Tang,Qianqian Liu,Shengyu Yao,Kun Han,Chupeng Zhang,Zhipeng Lu,Qian Huang,Guoqi Zhao,Yi Xu,Tingfeng Chen,Xiaohui Xie,Yong Liu +14 more
TL;DR: WBNet as discussed by the authors is a deep learning-based automatic segmentation (AS) algorithm that can accurately and efficiently delineate all major OARs in the entire body directly on CT scans.
Proceedings ArticleDOI
Automatic Pulmonary Lobe Segmentation Using Deep Learning
TL;DR: Wang et al. as mentioned in this paper proposed pre-processing CT image by cropping region that is covered by the convex hull of the lungs in order to mitigate the influence of noise from outside the lungs.
Posted Content
Automatic Pulmonary Lobe Segmentation Using Deep Learning
TL;DR: This work proposes pre-processing CT image by cropping region that is covered by the convex hull of the lungs in order to mitigate the influence of noise from outside the lungs, and uses a hybrid loss function with dice loss to tackle extreme class imbalance issue and focal loss to force model to focus on voxels that are hard to be discriminated.