Meeting Banner
Abstract #0956

VesselDigitizer: A deep learning-powered 3D Slicer extension for digitizing cerebral vasculature from 3D medical images

Zhensen Chen1,2, Lixin Liu1, Xiaoqian Chao1, Jian Wang3, Yujun Liao4,5, Xuesong Li6, and He Wang1,2
1Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China, 2MOE Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Fudan University, Shanghai, China, 3Department of Neurosurgery, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou Medical Center, Changzhou, China, 4Department of Neurosurgery, Fudan University Huashan Hospital, Shanghai, China, 5Clinical Medical Center of Neurosurgery, Shanghai Key Laboratory of Brain Function and Restoration and Neural Regeneration, Shanghai, China, 6School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China

Synopsis

Keywords: Software Tools, Vessels

Motivation: Accurate and fast digitization of the cerebral vasculature can facilitate research on cerebrovascular health, the development of novel imaging biomarkers, and clinical applications.

Goal(s): To develop a user-friendly tool with high flexibility and extensibility to segment, label, and quantify cerebral vasculature by taking advantage of deep learning.

Approach: The tool VesselDigitizer was developed as an extension of 3D Slicer to leverage its image processing and visualization capability. Deep-learning powered modules for segmentation, refinement, and labeling of the vasculature were developed.

Results: VesselDigitizer enables fast segmentation and vessel labeling and provides various handy tools to identify and correct incorrect segmentation and labeling.

Impact: VesselDigitizer makes large-scale analysis of cerebral vasculatures easier and more accurate.

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.

Keywords