Related Experiment Video
Updated: May 20, 2026
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
Published on: February 19, 2021
Automatic lesion incidence estimation and detection in multiple sclerosis using multisequence longitudinal MRI
E M Sweeney1, R T Shinohara, C D Shea
1Department of Biostatistics, Johns Hopkins University, Baltimore, Maryland 21205, USA. emsweene@jhsph.edu
Background And Purpose:
Detecting incidence and enlargement of lesions is essential in monitoring the progression of MS. In clinical trials, lesion load is observed by manually segmenting and comparing serial MR images, which is time consuming, costly, and prone to inter- and intraobserver variability. Subtracting images from consecutive time points nulls stable lesions, leaving only new lesion activity. We propose SuBLIME, an automated method for segmenting incident lesion voxels.
Materials And Methods:
We used logistic regression models incorporating multiple MR imaging sequences and subtraction images from consecutive longitudinal studies to estimate voxel-level probabilities of lesion incidence. We used T1-weighted, T2-weighted, FLAIR, and PD volumes from a total of 110 MR imaging studies from 10 subjects.
Results:
To assess the performance of the model, we assigned 5 subjects to a training set and the remaining 5 to a validation set. With SuBLIME, lesion incidence is detected and delineated in the validation set with an AUC of 99% (95% CI [97%, 100%]) at the voxel level.
Conclusions:
This fully automated and computationally fast method allows sensitive and specific detection of lesion incidence that can be applied to large collections of images. Using the explicit form of the statistical model, SuBLIME can easily be adapted to cases when more or fewer imaging sequences are available.
Insights
We developed SuBLIME, an automated method for detecting new lesions in multiple sclerosis (MS) by analyzing MRI scans. This fast and accurate technique improves lesion detection in clinical trials.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Computational Medicine
Background:
- Monitoring multiple sclerosis (MS) progression requires detecting new and enlarged lesions.
- Manual segmentation of MRI scans for lesion load is time-consuming, expensive, and variable.
Purpose of the Study:
- To develop SuBLIME, an automated method for segmenting incident lesion voxels.
- To improve the efficiency and accuracy of MS lesion detection in clinical settings.
Main Methods:
- Utilized logistic regression models with multiple MRI sequences (T1-weighted, T2-weighted, FLAIR, PD).
- Employed subtraction images from consecutive time points to identify new lesion activity.
- Trained and validated the model on 110 MRI studies from 10 subjects.
Main Results:
- SuBLIME achieved 99% AUC for detecting lesion incidence at the voxel level in the validation set.
- The method demonstrated high sensitivity and specificity in delineating new lesions.
Conclusions:
- SuBLIME offers a fully automated, computationally fast, sensitive, and specific method for detecting lesion incidence.
- The statistical model is adaptable for varying numbers of imaging sequences, facilitating application to large datasets.
