Vascular Tree Segmentation in Medical Images Using Hessian-Based Multiscale Filtering and Level Set Method

Jiaoying Jin,Xuming Zhang,Linjun Yang,Mingyue Ding

doi:10.1155/2013/502013

Abstract

Vascular segmentation plays an important role in medical image analysis. A novel technique for the automatic extraction of vascular trees from 2D medical images is presented, which combines Hessian-based multiscale filtering and a modified level set method. In the proposed algorithm, the morphological top-hat transformation is firstly adopted to attenuate background. Then Hessian-based multiscale filtering is used to enhance vascular structures by combining Hessian matrix with Gaussian convolution to tune the filtering response to the specific scales. Because Gaussian convolution tends to blur vessel boundaries, which makes scale selection inaccurate, an improved level set method is finally proposed to extract vascular structures by introducing an external constrained term related to the standard deviation of Gaussian function into the traditional level set. Our approach was tested on synthetic images with vascular-like structures and 2D slices extracted from real 3D abdomen magnetic resonance angiography (MRA) images along the coronal plane. The segmentation rates for synthetic images are above 95%. The results for MRA images demonstrate that the proposed method can extract most of the vascular structures successfully and accurately in visualization. Therefore, the proposed method is effective for the vascular tree extraction in medical images.

Highlights

Accurate segmentation and quantification of vascular structures in medical images is a critical task for clinical practices such as computer-aided diagnosis, treatment, surgical planning, and navigation
The response of the Hessian-based multiscale filtering will be strongest when the scale of the filter matches the size of the local structures, which means scale selection is keeping with the strongest response among multiple scales
It can be seen that the proposed method can provide accurate segmentation results, and the segmentation rates for all the synthetic images are over 95%

Summary

Introduction

Accurate segmentation and quantification of vascular structures in medical images is a critical task for clinical practices such as computer-aided diagnosis, treatment, surgical planning, and navigation. Among existing vascular extraction methods, Hessian-based multiscale filtering has received much attention [1, 5,6,7,8,9,10,11,12] These methods share a common idea that the images are convolved with 2D or 3D Gaussian filters at multiple scales, and the eigenvalues of the Hessian matrix at each pixel or voxel are analyzed in terms of a response function to determine the shape of the local structures in the images [13]. Gaussian filter convolution with the image tends to blur vessel boundaries and makes the scale selection inaccurate To address these problems, we use morphological top-hat transformation and Hessian-based multiscale filtering to enhance vascular structures in medical images and an improved level

Methods

Results

Conclusion