• Publications
  • Influence
Optimal Multiple Surface Segmentation With Shape and Context Priors
TLDR
A graph-theoretic framework for multi-object segmentation that incorporates both shape and context prior knowledge in a 3-D graph representation to help overcome the stated challenges. Expand
  • 100
  • 11
Optimal Co-Segmentation of Tumor in PET-CT Images With Context Information
  • Q. Song, Junjie Bai, +6 authors X. Wu
  • Computer Science, Medicine
  • IEEE Transactions on Medical Imaging
  • 16 May 2013
TLDR
We propose a novel method for the co-segmentation of the tumor in both PET and CT images, which makes use of advantages from each modality: the functionality information from PET and the anatomical structure information from CT. Expand
  • 88
  • 5
Error-Tolerant Scribbles Based Interactive Image Segmentation
  • Junjie Bai, X. Wu
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 23 June 2014
TLDR
In this paper, we propose a novel ratio energy function that tolerates errors in user input while encouraging maximum use of the user input information. Expand
  • 25
  • 5
  • PDF
Dimensional music emotion recognition by valence-arousal regression
TLDR
In this paper, music emotions was modeled as continuous variables composed of valence and arousal values (VA values) based on Valence-Arousal model, and MER is formulated as a regression problem, and regression neural networks were adopted to recognize music emotion. Expand
  • 8
  • 3
MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images
TLDR
This paper addresses the issue of fully automatic segmentation of a hip CT image with the goal to preserve the joint structure for clinical applications in hip disease diagnosis and treatment. Expand
  • 28
  • 2
Automated anatomical labeling of coronary arteries via bidirectional tree LSTMs
  • Dan Wu, Xin Wang, +7 authors Y. Yin
  • Computer Science, Medicine
  • International Journal of Computer Assisted…
  • 27 November 2018
TLDR
A novel deep neural network framework, referred to Tree Labeling Network (TreeLab-Net), is proposed to resolve this problem in this work. Expand
  • 13
  • 2
Train a 3D U-Net to segment cranial vasculature in CTA volume without manual annotation
  • Xuhui Chen, Y. Lu, +6 authors J. Wu
  • Computer Science
  • IEEE 15th International Symposium on Biomedical…
  • 4 April 2018
TLDR
We adopted the incomplete vascular segmentation automatically obtained from time-of-flight magnetic resonance angiography (TOF-MRA) volume to train a segmentation network for CTA images. Expand
  • 4
  • 2
Surface-Region Context in Optimal Multi-object Graph-Based Segmentation: Robust Delineation of Pulmonary Tumors
TLDR
We report a novel solution to a segmentation problem, in which target objects of arbitrary shape mutually interact with terrain-like surfaces, which widely exists in the medical imaging field. Expand
  • 23
  • 1
Multi-scale segmentation using deep graph cuts: Robust lung tumor delineation in MVCBCT
TLDR
In this paper, we formulate the multi-scale segmentation as a Markov Random Field (MRF) energy minimization problem in a deep network (graph), which can be efficiently and exactly solved by computing a minimum s-t cut in an appropriately constructed graph. Expand
  • 5
  • 1
Optimal Multiple Surface Segmentation with Convex Priors in Irregularly Sampled Space
TLDR
We propose a generalized graph based optimal multiple surface segmentation method with convex priors to achieve subvoxel accurate segmentation by utilizing the partial volume information in the voxels. Expand
  • 2
  • 1