Abstract #4733

Towards reproducible perivascular space quantification: an open-source perivascular space segmentation benchmark

Merel M. van der Thiel^1,2, Eva M. van Heese^3,4, Britt T.J. van den Heuvel¹, Valery Molina⁵, Maria C. Jaramillo⁵, Jacobus F.A. Jansen^1,2,6, and Jose Bernal^7,8

¹Department of Radiology & Nuclear Medicine, Maastricht University Medical Center, Maastricht, Netherlands, ²Mental Health and Neuroscience Research Institute, Maastricht University, Maastricht, Netherlands, ³Department of Anatomy and Neurosciences, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, Netherlands, ⁴Amsterdam Neuroscience, Neurodegeneration, Amsterdam, Netherlands, ⁵Multimedia and Computer Vision Group, Universidad del Valle, Cali, Colombia, ⁶Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands, ⁷Institute of Cognitive Neurology and Dementia Research, Otto-von-Guericke University, Magdeburg, Germany, ⁸German Centre for Neurodegenerative Diseases (DZNE), Magdeburg, Germany

Synopsis

Keywords: Neurofluids, Segmentation, Reproducible science, Perivascular spaces

Motivation: The lack of open-source perivascular space (PVS) segmentation code hampers reproducible research, leading to redundant efforts, and hindering broader implementation of PVS segmentation.

Goal(s): To create an open-source PVS segmentation benchmark.

Approach:
Phase 1: We engaged the PVS research community to contribute code to our open-source repository. We are currently collecting, verifying, and containerizing code submissions.
Phase 2: We plan to compare submitted code against each other and a manually segmented ground truth benchmark. Our goal is to develop community guidelines based on input data.

Results: We have received several code contributions and have issued an open call for more submissions.

Impact: The efforts of the PVS repository team will establish an open-source platform for software code related to PVS quantification, minimizing duplicate development, enhancing reproducibility, and providing a benchmark for future development and comparison of segmentation methods.

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.