Novel Brain MRI Technique Helps Identify Multiple Sclerosis Lesions
|
By MedImaging International staff writers Posted on 25 Apr 2022 |

In patients with multiple sclerosis (MS), the immune system attacks the insulating layer that protects nerves. The disruption or loss of these layers results in lesions, which show up as white spots on MRI brain scans—the main tool for diagnosing the condition. But MS is not the only condition that can cause white spots to appear on an MRI and migraines are the most common cause of non-MS white spots on MRIs. As a result, patients who are misdiagnosed with MS are needlessly prescribed costly immune-modifying treatments that can increase risk for infection, cause organ damage and decrease the effectiveness of vaccines. Now, researchers are using advanced techniques for imaging the brain and eyes, along with new biomarkers, to present a clearer picture of MS. Their work could lead to improved diagnosis and treatment of the disease.
A team of physician and scientists in the Department of Neurology at Cedars-Sinai (Los Angeles, CA, USA) has identified biological sign called “central vein sign” that could help physicians determine whether white spots on a patient’s MRI are caused by MS or by something else, ultimately reducing misdiagnosis. MS lesions tend to form around tiny veins through which immune cells enter and attack brain tissue, so most lesions caused by MS have a vein in the middle. New MRI techniques pioneered by the researchers make central vein sign visible.
Ongoing studies at Cedars-Sinai and 10 other MS centers in North America are using the new technique to image 400 patients at risk of developing MS - the final step in scientifically validating central vein sign as a way to diagnose MS. Importantly, the new imaging technique can be used with widely available MRI scanners and performed quickly enough to fit the workflow of the typical radiology center. The team is also developing a machine learning algorithm to make evaluation of the imaging results easier for physicians. The central vein sign could also help doctors determine how well a patient is responding to treatment by confirming that any new lesions that develop are caused by MS and not something else.
The researchers are also focusing on imaging of the retina - the layer of tissue at the back of the eye - and the optic nerve that can also help improve MS diagnosis. Using a technology called optical coherence tomography (OCT), which functions like an MRI for the retina and optic nerve, the team has shown it can detect MS lesions that an MRI can miss. Optical coherence tomography captures 3D images of patients’ retinal layers, including the ganglion cell layer, which sends visual information to the brain. Retinal imaging could also help indicate how well a patient is responding to treatment. The team is continuing to study the role of OCT, along with a related technique called optical coherence tomography angiography (OCTA), as a way to understand how MS affects the blood vessels in the retina. While ocular nerve and retinal imaging is important to evaluate in MS patients, it is not yet widely available in practice. The team hopes their research will help change the standard of diagnostic care.
“Current MRI images don’t give us the whole picture, which is why we developed MRI sequences that improve image quality so that we can see very small veins, called veinules, in the brain,” said Pascal Sati, PhD, director of the Neuroimaging Program in the Department of Neurology and associate professor of Neurology at Cedars-Sinai, who pioneered the MRI technique. “We superimpose that over a conventional MRI image of the lesions so that it is clear which brain lesions have a central vein and are likely caused by MS.”
“Once the image is taken, our deep learning algorithm can analyze it very quickly and tell the clinician how many lesions show the central vein sign,” added Sati. “The number of lesions with the central vein sign can indicate whether or not the patient has MS.”
“The optic nerves are very small and difficult to image. Detecting lesions there can help us clinch an MS diagnosis, especially in patients who are relatively early on in their disease course,” said neurologist Omar Al-Louzi, MD, director of the Visual Outcomes Laboratory at Cedars-Sinai, whose research seeks to use the eye as a window to produce better outcomes for patients. “Shrinking of the ganglion cell layer often mirrors overall brain degeneration, and occurs in 70% to 80% of MS patients. This is why ganglion imaging could also help us improve diagnosis.”
Related Links:
Cedars-Sinai
Latest MRI News
- Cardiac MRI Detects Hidden Heart Dysfunction After Heart Attack
- AI Tool Reveals Cortical Lesions on Standard MRI in Multiple Sclerosis
- AI Reconstruction Tool Speeds Dynamic Breast MRI and Improves Cancer Detection
- International Study Assesses AI for Prostate Cancer MRI Interpretation
- AI Approach Could Shorten Advanced Brain MRI Scans by Up to 90%
- Cardiac MRI Measure Improves Risk Prediction in Tricuspid Regurgitation
- AI System Improves Accuracy of Cardiac MRI Interpretation
- Deep Learning Model Predicts Alzheimer’s Disease Outcomes from Baseline MRI
- Blood-Brain Barrier Imaging Adds Risk Insight to Standard Stroke MRI
- AI Body Composition MRI Analysis Predicts Cardiometabolic Disease Risk
- AI MRI Tool Quantifies Muscle Fat to Assess Cardiometabolic Risk
- Advanced MRI Visualizes CSF Motion Changes After Mild Traumatic Brain Injury
- MRI Tool Enables Long-Term Tracking of Transplanted Cardiac Cells
- MRI-Based AI Tool Supports Differentiation of Parkinsonian Syndromes
- MRI-Derived Biomarker Improves Risk Stratification in Glioblastoma
- Combined Imaging Approach Identifies Cause of Heart Attack without Coronary Blockage
Channels
Radiography
view channel
AI Tool Predicts Five-Year Breast Cancer Risk from Mammograms
Breast cancer risk assessment during routine screening is difficult because many women who develop the disease have no known genetic mutations or family history. Static risk tools provide limited discrimination... Read more
AI Mammography Tools Detect Early Breast Cancer Signs Years Before Diagnosis
Breast cancer screening aims to detect tumors before symptoms develop, but subtle mammographic changes can appear years before diagnosis and may be missed during routine reads. Delayed detection can lead... Read moreUltrasound
view channel
Simple 2D Ultrasound Tool Accurately Estimates Placental Volume
Stillbirth remains a major cause of perinatal loss, with about 21,000 cases annually in the United States. Although placental abnormalities are linked to adverse pregnancy outcomes, routine monitoring... Read more
Portable 3D Ultrasound System Enables Reproducible Breast Cancer Monitoring
Breast cancer can develop between annual mammograms, and these interval cancers account for 20% to 30% of cases and tend to be more aggressive. The challenge is pronounced in people with dense breast tissue.... Read moreNuclear Medicine
view channel
Radiotherapy Professionals Embrace AI as a Clinical Support Tool
Radiotherapy planning requires precise identification of organs at risk near a tumor, but manual contouring is repetitive and time-consuming, often delaying plan completion and straining specialist capacity.... Read more
Second PSMA PET Identifies Disease in More Than Half of Negative Cases
Biochemical recurrence of prostate cancer after prostatectomy or radiation can be difficult to localize when imaging is negative. Uncertain disease sites may delay salvage therapy and expose patients to... Read moreGeneral/Advanced Imaging
view channel
Virtual Staining Technique Creates Histology Images from CT Data
Pulmonary hypertension, a disorder marked by pathological remodeling of the pulmonary vessels, often requires detailed histologic assessment. Yet routine pathology remains anchored in labor‑intensive,... Read more
CT-Derived Biomarker Predicts Outcomes in Gastric Cancer
Gastric cancer, also known as stomach cancer, is the fifth most common malignancy worldwide and often shows heterogeneous outcomes even within the same stage. Prognostic estimates typically rely on tumor-centric... Read more
AI Tool Enhances Response Assessment and Survival Prediction in Pleural Mesothelioma
Pleural mesothelioma, a cancer that grows as a thin, irregular layer along the lung wall, is difficult to measure on imaging. Clinicians rely on diameter-based Response Evaluation Criteria in Solid Tumors... Read moreImaging IT
view channel
Ambient AI Reporting Platform Streamlines Radiology Reporting
Radiology departments face growing imaging volumes and staffing shortages, creating reporting bottlenecks and pressure to maintain turnaround times. Conventional dictation tools document findings after... Read more
Interactive AI Tool Supports Explainable Lung Nodule Assessment
Lung cancer is a leading cause of cancer mortality, and timely characterization of pulmonary nodules on chest computed tomography (CT) is essential for directing care. Interpreting nodule morphology demands... Read more
Breast Imaging Software Enhances Visualization and Tissue Characterization in Challenging Cases
Breast imaging can be particularly challenging in cases involving small breasts or implants, where image reconstruction and tissue characterization may be limited. Clinicians also need reproducible analysis... Read moreIndustry News
view channel
GE HealthCare Showcases AI-Enabled Nuclear Medicine Portfolio at SNMMI 2026
Nuclear medicine is expanding rapidly as health systems adopt theranostics and broaden access to radiopharmaceuticals, increasing demand for scalable operations and consistent diagnostic confidence.... Read more
GE HealthCare Highlights AI-Supported Radiation Therapy Tools at ESTRO 2026
At the European Society for Radiotherapy and Oncology (ESTRO) 2026 Congress in Stockholm, GE HealthCare is highlighting Intelligent Radiation Therapy (iRT), MIM Software innovations, and BK Medical surgical... Read more







