D
Dehui Xiang
Researcher at Soochow University (Suzhou)
Publications - 96
Citations - 1479
Dehui Xiang is an academic researcher from Soochow University (Suzhou). The author has contributed to research in topics: Segmentation & Computer science. The author has an hindex of 16, co-authored 73 publications receiving 876 citations. Previous affiliations of Dehui Xiang include Chinese Academy of Sciences.
Papers
More filters
Journal ArticleDOI
CPFNet: Context Pyramid Fusion Network for Medical Image Segmentation
Shuanglang Feng,Heming Zhao,Fei Shi,Xuena Cheng,Meng Wang,Yuhui Ma,Dehui Xiang,Weifang Zhu,Xinjian Chen +8 more
TL;DR: Experimental results show that the proposed novel Context Pyramid Fusion Network (named CPFNet) is very competitive with other state-of-the-art methods on four different challenging tasks, including skin lesion segmentation, retinal linear lesion segmentsation, multi-class segmentation of thoracic organs at risk and multi- class segmentsation of retinal edema lesions.
Journal ArticleDOI
Automatic Liver Segmentation Based on Shape Constraints and Deformable Graph Cut in CT Images
TL;DR: In order to accurately detect the liver surface, deformable graph cut was proposed, which effectively integrates the properties and inter-relationship of the input images and initialized surface.
Journal ArticleDOI
Automated 3-D Retinal Layer Segmentation of Macular Optical Coherence Tomography Images With Serous Pigment Epithelial Detachments
TL;DR: A method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes, is proposed.
Journal ArticleDOI
Speckle noise reduction in optical coherence tomography images based on edge-sensitive cGAN.
TL;DR: An end-to-end framework for simultaneous speckle reduction and contrast enhancement for retinal OCT images based on the conditional generative adversarial network (cGAN), with edge loss function added to the final objective so that the model is sensitive to the edge-related details.
Journal ArticleDOI
Surrogate-Assisted Retinal OCT Image Classification Based on Convolutional Neural Networks
TL;DR: A surrogate-assisted classification method to classify retinal OCT images automatically based on convolutional neural networks (CNNs) that has been evaluated on different databases and shows that the proposed method is a very promising tool for classifying the retinal Oct images automatically.