Abstract #0022

Temporal Dynamics-Driven Automatic Segmentation of Parasagittal Dural Space and Meningeal Lymphatic Vessels in DCE-MRI Using VQ-VAE

Joon Jang^1,2, Junhyeok Lee^2,3, Hyeonjin Kim^1,4,5, Won-Jin Moon⁶, and Kyu Sung Choi^2,4,7

¹Department of Biomedical Sciences, Seoul National University, Seoul, Korea, Republic of, ²Artificial Intelligence Collaborative Network, Department of Radiology, Seoul National University Hospital, Seoul, Korea, Republic of, ³Interdisciplinary Programs in Cancer Biology Major, Seoul National University College of Medicine, Seoul, Korea, Republic of, ⁴Department of Radiology, Seoul National University Hospital, Seoul, Korea, Republic of, ⁵Department of Medical Sciences, Seoul National University College of Medicine, Seoul, Korea, Republic of, ⁶Department of Radiology, Konkuk University Medical Center, Seoul, Korea, Republic of, ⁷Department of Radiology, Seoul National University College of Medicine, Seoul, Korea, Republic of

Synopsis

Keywords: Neurofluids, Neurofluids, Segmentation, Perfusion, Glymphatics

Motivation: Manual delineation of meningeal lymphatic vessels (mLVs) in the parasagittal dural space (PSD) from adjacent structures in DCE-MRI is challenging due to low spatial resolution and partial volume effects.

Goal(s): Our goal was to develop an automated method for segmenting the PSD and mLVs using the temporal dynamics of DCE-MRI.

Approach: We used continuous wavelet transform and employed a vector-quantized variational autoencoder (VQ-VAE) for the automatic segmentation of the PSD and mLVs using the temporal dynamics of DCE-MRI.

Results: Semi-quantitative parameters obtained from mLVs differed from those of adjacent structures, which may be used for more accurate assessment of glymphatic clearance capacity.

Impact: Our proposed method may enable automatic segmentation of the PSD and mLVs in cases of highly limited spatial resolution, where manual segmentation may be impractical.

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.