Abstract #5112

Machine Learning Detects Symptomatic Plaques on 3D high-resolution MR vessel wall images

Jie Chen¹, Wenwen He², Long Yang¹, Qian Li¹, Xiong Yang³, Liwen Wan¹, Ye Li^1,4,5, Dong Liang^1,4,5, Xin Liu^1,4,5, Hairong Zheng^1,4,5, Shanshan Lu², and Na Zhang^1,4,5

¹Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, ²Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China, ³Department of Image Advanced Analysis of HSW BU, Shanghai United Imaging Healthcare Co., Ltd, Shanghai, 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: Diagnosis/Prediction, Vessel Wall

Motivation: Reliable assessment of plaque vulnerability is crucial for identifying high-risk plaques and preventing stroke.

Goal(s): To develop and validate a high-risk intracranial plaque classification model using a combination of morphological and signal features from Three-dimensional high-resolution magnetic resonance vessel wall imaging (3D HR-MRVWI) and machine learning.

Approach: Using 3D HR-MRVWI, we extracted morphological and signal features, which were then input into support vector classifier (SVC) and logistic regression models to classify plaques as symptomatic or asymptomatic.

Results: Adding signal features resulted in a notable increase in The Area Under the Curve(AUC) and accuracy compared to models using morphological features alone.

Impact: This study validated the importance of signal features, such as enhancement degree, in identifying high-risk plaques, providing data support for future radiomic research. This approach aids in early screening and targeted preventive measures, potentially reducing the incidence of stroke.

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.