Related Experiment Video
Updated: Oct 1, 2025
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
Published on: February 19, 2021
QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative
Hang Zhang1, Thanh D Nguyen2, Jinwei Zhang3
1Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA; Department of Radiology, Weill Cornell Medicine, New York, NY, USA.
Background And Purpose:
Chronic active multiple sclerosis (MS) lesions are characterized by a paramagnetic rim at the edge of the lesion and are associated with increased disability in patients. Quantitative susceptibility mapping (QSM) is an MRI technique that is sensitive to chronic active lesions, termed rim + lesions on the QSM. We present QSMRim-Net, a data imbalance-aware deep neural network that fuses lesion-level radiomic and convolutional image features for automated identification of rim + lesions on QSM.
Methods:
QSM and T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI of the brain were collected at 3 T for 172 MS patients. Rim + lesions were manually annotated by two human experts, followed by consensus from a third expert, for a total of 177 rim + and 3986 rim negative (rim-) lesions. Our automated rim + detection algorithm, QSMRim-Net, consists of a two-branch feature extraction network and a synthetic minority oversampling network to classify rim + lesions. The first network branch is for image feature extraction from the QSM and T2-FLAIR, and the second network branch is a fully connected network for QSM lesion-level radiomic feature extraction. The oversampling network is designed to increase classification performance with imbalanced data.
Results:
On a lesion-level, in a five-fold cross validation framework, the proposed QSMRim-Net detected rim + lesions with a partial area under the receiver operating characteristic curve (pROC AUC) of 0.760, where clinically relevant false positive rates of less than 0.1 were considered. The method attained an area under the precision recall curve (PR AUC) of 0.704. QSMRim-Net out-performed other state-of-the-art methods applied to the QSM on both pROC AUC and PR AUC. On a subject-level, comparing the predicted rim + lesion count and the human expert annotated count, QSMRim-Net achieved the lowest mean square error of 0.98 and the highest correlation of 0.89 (95% CI: 0.86, 0.92).
Conclusion:
This study develops a novel automated deep neural network for rim + MS lesion identification using T2-FLAIR and QSM images.
Insights
A new deep neural network, QSMRim-Net, accurately identifies chronic active multiple sclerosis (MS) lesions using quantitative susceptibility mapping (QSM) and T2-FLAIR MRI. This automated method aids in detecting rim-positive lesions, improving MS patient assessment.
Area of Science:
- Neuroimaging
- Artificial Intelligence in Medicine
- Radiology
Background:
- Chronic active multiple sclerosis (MS) lesions, characterized by a paramagnetic rim, correlate with patient disability.
- Quantitative Susceptibility Mapping (QSM) is an MRI technique sensitive to these rim-positive (rim+) lesions.
- Automated detection of rim+ lesions is crucial for MS management.
Purpose of the Study:
- To develop and validate QSMRim-Net, a deep neural network for automated identification of rim+ MS lesions on QSM.
- To fuse radiomic and image features for enhanced lesion detection.
- To address data imbalance in MS lesion detection.
Main Methods:
- Utilized QSM and T2-FLAIR MRI data from 172 MS patients.
- Developed QSMRim-Net, a two-branch neural network integrating image and radiomic features.
- Employed a synthetic minority oversampling network to handle imbalanced datasets (177 rim+ vs. 3986 rim- lesions).
Main Results:
- QSMRim-Net achieved a partial AUC of 0.760 and PR AUC of 0.704 on a lesion-level, outperforming existing methods.
- On a subject-level, the model demonstrated high accuracy with a mean square error of 0.98 and correlation of 0.89.
- The algorithm effectively identified rim+ lesions in a cross-validation framework.
Conclusions:
- QSMRim-Net represents a novel automated deep learning approach for rim+ MS lesion identification.
- The method shows significant potential for improving the assessment and monitoring of MS.
- Integration of QSM and T2-FLAIR MRI data enhances diagnostic capabilities.
More Related Videos
10:25Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
12:50Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
Published on: April 14, 2014