Blood vessel segmentation using line-direction vector based on Hessian analysis

Yukitaka Nimura; Takayuki Kitasaka; Kensaku Mori

doi:10.1117/12.844672

12 March 2010 Blood vessel segmentation using line-direction vector based on Hessian analysis

Yukitaka Nimura, Takayuki Kitasaka, Kensaku Mori

Proceedings Volume 7623, Medical Imaging 2010: Image Processing; 76233Q (2010) https://doi.org/10.1117/12.844672
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

Abstract

For decision of the treatment strategy, grading of stenoses is important in diagnosis of vascular disease such as arterial occlusive disease or thromboembolism. It is also important to understand the vasculature in minimally invasive surgery such as laparoscopic surgery or natural orifice translumenal endoscopic surgery. Precise segmentation and recognition of blood vessel regions are indispensable tasks in medical image processing systems. Previous methods utilize only ``lineness'' measure, which is computed by Hessian analysis. However, difference of the intensity values between a voxel of thin blood vessel and a voxel of surrounding tissue is generally decreased by the partial volume effect. Therefore, previous methods cannot extract thin blood vessel regions precisely. This paper describes a novel blood vessel segmentation method that can extract thin blood vessels with suppressing false positives. The proposed method utilizes not only lineness measure but also line-direction vector corresponding to the largest eigenvalue in Hessian analysis. By introducing line-direction information, it is possible to distinguish between a blood vessel voxel and a voxel having a low lineness measure caused by noise. In addition, we consider the scale of blood vessel. The proposed method can reduce false positives in some line-like tissues close to blood vessel regions by utilization of iterative region growing with scale information. The experimental result shows thin blood vessel (0.5 mm in diameter, almost same as voxel spacing) can be extracted finely by the proposed method.

Citation Download Citation

Yukitaka Nimura, Takayuki Kitasaka, and Kensaku Mori "Blood vessel segmentation using line-direction vector based on Hessian analysis", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 76233Q (12 March 2010); https://doi.org/10.1117/12.844672

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available