Automatic segmentation of neonatal images using convex optimization and coupled level set method

Authors:
Li Wang;Feng Shi;John H. Gilmore;Weili Lin;Dinggang Shen
Affiliations:
1School of Computer Science & Technology, Nanjing University of Science and Technology, China and IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill;IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill;Department of Psychiatry, University of North Carolina at Chapel Hill;MRI Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill;IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill
Venue:
MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
Year:
2010

Citing 6
Cited 1

A Variational Approach for the Segmentation of the Left Ventricle in MR Cardiac Images

VLSM '01 Proceedings of the IEEE Workshop on Variational and Level Set Methods (VLSM'01)
Fast Global Minimization of the Active Contour/Snake Model

Journal of Mathematical Imaging and Vision
A Variational Level Set Approach to Segmentation and Bias Correction of Images with Intensity Inhomogeneity

MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Active contours driven by local Gaussian distribution fitting energy

Signal Processing
Active contours without edges

IEEE Transactions on Image Processing
A Variational Method for Geometric Regularization of Vascular Segmentation in Medical Images

IEEE Transactions on Image Processing

Accurate and consistent 4D segmentation of serial infant brain MR images

MBIA'11 Proceedings of the First international conference on Multimodal brain image analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Accurate segmentation of neonatal brain MR images remains challenging mainly due to poor spatial resolution, low tissue contrast, high intensity inhomogeneity. Most existing methods for neonatal brain segmentation are atlas-based and voxel-wise. Although parametric or geometric deformable models have been successfully applied to adult brain segmentation, to the best of our knowledge, they are not explored in neonatal images. In this paper, we propose a novel neonatal image segmentation method, combining local intensity information, atlas spatial prior and cortical thickness constraint, in a level set framework. Besides, we also provide a robust and reliable tissue surfaces initialization for our proposed level set method by using a convex optimization technique. Validation is performed on 10 neonatal brain images with promising results.