Abstract #3356

A Hybrid Deep Learning and Graphics method for Vessel Centerline Extraction and Vessel Segment Labeling to Assist Plaque Detection and Evaluation

Long Yang¹, Xiong Yang², Yufei Mao², Guanxun Cheng³, Ye Li^1,4,5, Dong Liang^1,4,5, Xin Liu^1,4,5, Hairong Zheng^1,4,5, and Na Zhang^1,4,5

¹Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shen Zhen, China, ²Department of Image Advanced Analysis of HSW BU, Shanghai United Imaging Healthcare Co., Ltd., Shanghai, China, ³Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, China, ⁴Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, Shenzhen, China, ⁵United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China

Synopsis

Keywords: Vessel Wall, Blood vessels

Motivation: Manual centerline Extraction based on black-blood Magnetic resonance vessel wall imaging is a difficult and time-consuming but important step for further analysis of plaques.

Goal(s): To propose a method for quickly, automatically and accurately extracting the centerline and label the segments of the target arteries.

Approach: This study proposes a method that combines deep learning and traditional graphics method for the automatic and accurate centerline extraction and even segments labeling, which is applicable to flexible MR sequences (only black-blood images, only bright-blood images, or both).

Results: Compared with the ground truth, the proposed method achieved excellent completeness and accuracy in a short time.

Impact: This study introduces a flexible (MRVWI or/and TOF-MRI), swift, and precise approach for extracting and labeling the centerline of target vessel. With this method, radiologists can more conveniently and efficiently observe potential abnormal areas around vessel and diagnose vessel-related diseases.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.