Related Experiment Video
Updated: Nov 9, 2025
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
Published on: February 19, 2021
Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorders by multiparametric
Akifumi Hagiwara1, Yujiro Otsuka2, Christina Andica1
1Department of Radiology, Juntendo University School of Medicine, 1-2-1, Hongo, Bunkyo-ku, Tokyo 113-8421, Japan.
Abstract:
Multiple sclerosis and neuromyelitis optica spectrum disorders are both neuroinflammatory diseases and have overlapping clinical manifestations. We developed a convolutional neural network model that differentiates between the two based on magnetic resonance imaging data. Thirty-five patients with relapsing-remitting multiple sclerosis and eighteen age-, sex-, disease duration-, and Expanded Disease Status Scale-matched patients with anti-aquaporin-4 antibody-positive neuromyelitis optica spectrum disorders were included in this study. All patients were scanned on a 3-T scanner using a multi-dynamic multi-echo sequence that simultaneously measures R1 and R2 relaxation rates and proton density. R1, R2, and proton density maps were analyzed using our convolutional neural network model. To avoid overfitting on a small dataset, we aimed to separate features of images into those specific to an image and those common to the group, based on SqueezeNet. We used only common features for classification. Leave-one-out cross validation was performed to evaluate the performance of the model. The area under the receiver operating characteristic curve of the developed convolutional neural network model for differentiating between the two disorders was 0.859. The sensitivity to multiple sclerosis and neuromyelitis optica spectrum disorders, and accuracy were 80.0%, 83.3%, and 81.1%, respectively. In conclusion, we developed a convolutional neural network model that differentiates between multiple sclerosis and neuromyelitis optica spectrum disorders, and which is designed to avoid overfitting on small training datasets. Our proposed algorithm may facilitate a differential diagnosis of these diseases in clinical practice.
Insights
A new AI model accurately distinguishes between multiple sclerosis and neuromyelitis optica spectrum disorders using MRI scans. This tool aids in the differential diagnosis of these overlapping neuroinflammatory conditions.
Area of Science:
- Neuroimmunology
- Radiology
- Artificial Intelligence
Background:
- Multiple sclerosis (MS) and neuromyelitis optica spectrum disorders (NMOSD) are distinct neuroinflammatory diseases with overlapping clinical presentations.
- Accurate differentiation is crucial for appropriate treatment and management.
Purpose of the Study:
- To develop and validate a convolutional neural network (CNN) model for differentiating MS from anti-aquaporin-4 antibody-positive NMOSD using magnetic resonance imaging (MRI) data.
Main Methods:
- A CNN model, based on SqueezeNet architecture, was developed to analyze R1, R2 relaxation rates, and proton density maps from 3-T MRI scans.
- Features were separated into image-specific and group-common to prevent overfitting on a small dataset.
- Leave-one-out cross-validation was employed to assess model performance.
Main Results:
- The CNN model achieved an area under the receiver operating characteristic curve of 0.859 for differentiating between MS and NMOSD.
- The model demonstrated a sensitivity of 80.0% for MS, 83.3% for NMOSD, and an overall accuracy of 81.1%.
Conclusions:
- A CNN model effectively differentiates between MS and NMOSD using MRI data, with built-in mechanisms to mitigate overfitting.
- This AI-driven approach shows potential to assist clinicians in the differential diagnosis of these challenging neurological disorders.
