Automatic identification of subjects at risk of multiple sclerosis
Inventors
Sati, Pascal • Patil, Sunil Goraksha • Reich, Daniel
Assignees
Siemens Healthineers AG • US Department of Health and Human Services
Publication Number
US-11272843-B2
Publication Date
2022-03-15
Expiration Date
2039-01-23
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
A computer-implemented method for automatically identifying subjects at risk of Multiple Sclerosis (MS) includes acquiring a plurality of images of a subject's brain using a Magnetic Resonance Imaging (MRI) scanner. A contrast enhancement process is applied to each image to generate a plurality of contrast-enhanced images. An automated lesion detection algorithm is applied to detect one or more lesions present in the contrast-enhanced images. An automated central vein detection algorithm is applied to detect one or more central veins present in the contrast-enhanced images. An automated paramagnetic rim detection algorithm is applied to detect one or more paramagnetic rims present in the contrast-enhanced images. The patient's risk for MS may then be determined based on the one or more of the lesions, central veins, and paramagnetic rims present in the contrast-enhanced images.
Core Innovation
The invention provides methods, systems, and apparatuses for automatically identifying subjects at risk of multiple sclerosis (MS) using magnetic resonance imaging (MRI) data. These techniques employ MS-focused pulse sequences and contrast-enhancement procedures to generate images that facilitate the detection of biomarkers of brain lesions such as central veins and paramagnetic rims. Subsequently, a classification procedure is applied to quantify the patient's risk of MS based on these biomarkers.
The method involves acquiring a plurality of images of a subject's brain via MRI, applying contrast enhancement to generate enhanced images, and then using automated algorithms to detect lesions, central veins, and paramagnetic rims in these images. The patient's risk for MS is then determined based on the detected biomarkers. This approach may further include the use of trained machine learning models to assess risk from a combined analysis of multiple biomarkers.
The problem addressed by the invention stems from current limitations in MS diagnosis. MS diagnosis currently lacks a specific test and relies on clinical evaluation and biomarker dissemination assessment. Early diagnosis is critical for treatment, but misdiagnosis is common due to misuse of MRI criteria and low specificity of existing techniques. Conventional MRI cannot automatically detect important biomarkers like central veins and paramagnetic rims, and standard imaging sequences are inadequate for high-resolution whole-brain imaging in clinically feasible times. Thus, there is a need for methods and systems for early and accurate identification of patients at high risk of MS.
Claims Coverage
The patent includes three main independent claims detailing computer-implemented methods and a system for automatically identifying subjects at risk of MS with specific inventive features concerning MRI image acquisition, contrast enhancement, biomarker detection, and risk determination.
Computer-implemented method for automatic MS risk identification using MRI with specific contrast enhancement
Acquiring multiple brain images via MRI; applying contrast enhancement including phase unwrapping/filtering and gadolinium-based processes; automated detection algorithms applied for lesions, central veins, and paramagnetic rims; determining patient's MS risk based on these detected biomarkers.
Computer-implemented method using machine learning for combined biomarker risk assessment
Receiving MRI brain images with application of contrast-enhancement processes including phase unwrapping/filtering and gadolinium contrast; applying multiple image analysis algorithms to identify biomarkers; using a trained machine learning model to determine MS risk based on combined biomarker assessment.
System for automatic identification of MS risk incorporating MRI scanner and centralized control computer
An MRI scanner acquiring brain images; a central control computer applying contrast enhancement including phase unwrapping/filtering and gadolinium enhancement; automated lesion, central vein, and paramagnetic rim detection algorithms; risk assessment based on detected biomarkers; and displaying the patient's risk for MS.
The claims collectively cover various methods and a system that utilize multiple specialized MRI image acquisition sequences combined with diverse contrast enhancement techniques, followed by automated and machine-learning-based detection of key biomarkers to assess and report the risk of MS.
Stated Advantages
Allows for rapid and automatic identification of subjects at risk of MS.
Enhances detection of imaging biomarkers such as central veins and paramagnetic rims that assist clinicians in MS diagnosis.
Integrates fast high-resolution anatomical brain imaging with multi-contrast processing and automated biomarker detection.
Facilitates easy integration into existing neurology protocols by executing the workflow on the MRI scanner software.
Documented Applications
Early and accurate identification of patients at high risk of multiple sclerosis.
Diagnostic evaluation of subjects suspected of having MS.
Production of reports quantifying patient MS risk and detailing lesion load, central vein percentage, and paramagnetic rim percentage.
Interested in licensing this patent?