Abstract #5146

QSM-RimDS: A highly sensitive paramagnetic rim lesion detection and segmentation tool for multiple sclerosis lesions

Ha Manh Luu¹, Ilhami Kovanlikaya¹, Tam Vu², Mert Sisman^1,3, Pascal Spincemaille¹, Yi Wang^1,4, Susan Gauthier⁵, and Thanh Nguyen¹

¹Department of Radiology, Weill Cornell Medicine, New York, NY, United States, ²Yale University, New Haven, CT, United States, ³Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY, United States, ⁴Department of Biomedical Engineering, Cornell University, Ithaca, NY, United States, ⁵Department of Neurology, Weill Cornell Medicine, New York, NY, United States

Synopsis

Keywords: Analysis/Processing, AI/ML Software, Paramagnetic rim lesions (PRLs), multiple sclerosis, QSM, deep learning, segmentation, detection

Motivation: Paramagnetic rim lesions (PRLs) are imaging biomarker of the innate immune response in MS lesions. QSM-RimNet can identify PRLs but requires precise QSM lesion mask and does not provide rim segmentation.

Goal(s): To develop QSM-RimDS algorithm to detect PRLs using the readily available FLAIR lesion mask and to provide rim segmentation for microglial quantification.

Approach: We trained an nnUNET for PRL rim segmentation and classified PRL status based on rim length relative to FLAIR lesion perimeter.

Results: QSM-RimDS achieved 90% detection sensitivity at 53.3% precision vs. 24.7% by QSM-RimNet. Compared to expert segmentation, 77% of PRLs have a DICE score greater than 0.5.

Impact: QSM-RimDS has the potential to replace human readers for the time-consuming PRL detection and segmentation task while improving reproducibility.

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.