Clinical Topics

Algorithm Proposed to Improve Detection of MS Lesions

by U.S. Medicine

September 4, 2018

PHILADELPHIA—Magnetic resonance imaging (MRI) is considered crucial for in vivo detection and characterization of white matter lesions (WMLs) in multiple sclerosis.

Despite research on WMLs for at least the last 20 years using MRI, a report in the Journal of Neuroimaging noted that automated segmentation remains challenging.

“Although the majority of statistical techniques for the automated segmentation of WMLs are based on single imaging modalities, recent advances have used multimodal techniques for identifying WMLs,” wrote study authors led by University of Pennsylvania Perelman School of Medicine researchers and including participation from the Henry M. Jackson Foundation for the Advancement of Military Medicine. “Complementary modalities emphasize different tissue properties, which help identify interrelated features of lesions.

The study team proposed the Method for Inter-Modal Segmentation Analysis (MIMoSA), a fully automatic lesion segmentation algorithm that utilizes novel covariance features from intermodal coupling regression in addition to mean structure to model the probability lesion is contained in each voxel.

Using two datasets, the MIMoSA algorithm was validated by comparison with both expert manual and other automated segmentation methods. In the first at Johns Hopkins Hospital, in two datasets, bootstrap cross-validation was used to compare the performance of MIMoSA against OASIS and LesionTOADS, two popular automatic segmentation approaches, in 98 subjects. Publicly-available data from a segmentation challenge were used for performance benchmarking as a secondary validation, the authors stated.

Results of the Johns Hopkins study indicated that MIMoSA yielded average Sørensen-Dice coefficient (DSC) of 0.57 and partial AUC of 0.68 calculated with false positive rates up to 1%. In addition to being superior to performance using OASIS and LesionTOADS, the proposed method also performed competitively in the segmentation challenge dataset, researchers wrote.

“MIMoSA resulted in statistically significant improvements in lesion segmentation performance compared with LesionTOADS and OASIS and performed competitively in an additional validation study,” study authors concluded.

1. Valcarcel AM, Linn KA, Vandekar SN, Satterthwaite TD, Muschelli J, Calabresi PA, Pham DL, Martin ML, Shinohara RT. MIMoSA: An Automated Method for Intermodal Segmentation Analysis of Multiple Sclerosis Brain Lesions. J Neuroimaging. 2018 Jul;28(4):389-398. doi: 10.1111/jon.12506. Epub 2018 Mar 8. PubMed PMID: 29516669; PubMed Central PMCID: PMC6030441.

Related Articles

“Coming together is a beginning. Keeping together is progress. Working together is success.” — Henry Ford (1863-1947)

October is Operation Bushmaster season for Uniformed Services University (USU) medical and nursing students.

NASA Partners with Academia for CVD Prediction Tool in Younger Adults

Federal medicine played a crucial role in the development of a new online tool to better predict which middle-aged adults are at the greatest risk of having acute myocardial infarction or stroke over the next decade.

U.S. Medicine Recommends

More From neurology


Rural Veterans With MS Benefit from Clinical Video Telehealth Rehabilitation

Of the more than 28,000 veterans with multiple sclerosis (MS) who receive care at the VHA, almost 45% of them live in rural or highly rural areas, a recent conference presentation pointed out.


Many Survey Respondents Say Marijuana Is Good for MS

Despite insufficient evidence regarding its risks and benefits, marijuana is increasingly available and aggressively marketed to the public, according to a new study which sought to understand the public's views on the risks and benefits of marijuana use.


Even Mild TBI Can Dramatically Increase Risk of Developing Parkinson's Disease

Mild traumatic brain injury, commonly known as concussion, appears to increase a patient's risk of developing Parkinson's disease by as much as 56%, a new veterans study found.


Even mild TBI increases veterans' dementia risk

The risk of dementia is increased even in veterans who suffer mild traumatic brain injury (TBI) without loss of consciousness.


Deep brain simulation extends Parkinson's survival

Deep brain stimulation (DBS) not only improves motor function in patients with Parkinson’s disease, as demonstrated in earlier studies, it also appears to extend life, according to new VA research.

Facebook Comment

Subscribe to U.S. Medicine Print Magazine

U.S. Medicine is mailed free each month to physicians, pharmacists, nurse practitioners, physician assistants and administrators working for Veterans Affairs, Department of Defense and U.S. Public Health Service.

Subscribe Now

Receive Our Email Newsletter

Stay informed about federal medical news, clinical updates and reports on government topics for the federal healthcare professional.

Sign Up