Meeting Banner
Abstract #4305

Multi-contrast deep-learning segmentation of the choroid plexus using self-configuring nnU-Net

Kabir Bagai1, Alexander Song1, Melanie Leguizamon1, Abigail Dubois1, Colin D. McKnight2, Ciaran M. Considine3, Paula Trujillo1, Daniel O. Claassen1, Manus J. Donahue1,3, and Kilian Hett1
1Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, United States, 2Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, United States, 3Department of Psychiatry and Behavioral Sciences, Vanderbilt University Medical Center, Nashville, TN, United States

Synopsis

Keywords: Segmentation, Multi-Contrast

Motivation: Recent studies have emphasized the relevance of accurate measures of the choroid plexus (ChP), which operates at the blood-cerebrospinal fluid (CSF) barrier and plays a fundamental role in CSF production, circulation, and neuro-immune surveillance.

Goal(s): To improve the existing ChP segmentation by leveraging the complementary nature of multi-contrast MRI together with a self-configuring deep-learning framework.

Approach: Multi-contrast segmentation is assessed by comparing a previous single-contrast implementation with the novel multi-contrast approach and gold-standard neuroradiologist manual segmentation.

Results: The Dice-Sørensen increased by 5.2 points using multi-contrast ChP segmentation, demonstrating that T1-weighted, T2-weighted, and T2-FLAIR can be used together to provide improved, complementary segmentation accuracy.

Impact: This study evaluates multi-contrast MRIs as inputs to a self-configuring deep learning framework to provide a new tool for segmentation of the choroid plexus, which has gained much recent interest as the most proximal structure in the neurofluid circuit.

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