Related Experiment Video
Updated: Jun 8, 2026
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
Automated segmentation method of white matter and gray matter regions with multiple sclerosis lesions in MR images
Taiki Magome1, Hidetaka Arimura, Shingo Kakeda
1Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka, 812-8582, Japan.
Abstract:
Our purpose in this study was to develop an automated method for segmentation of white matter (WM) and gray matter (GM) regions with multiple sclerosis (MS) lesions in magnetic resonance (MR) images. The brain parenchymal (BP) region was derived from a histogram analysis for a T1-weighted image. The WM regions were segmented by addition of MS candidate regions, which were detected by our computer-aided detection system for the MS lesions, and subtraction of a basal ganglia and thalamus template from "tentative" WM regions. The GM regions were obtained by subtraction of the WM regions from the BP region. We applied our proposed method to T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery images acquired from 7 MS patients and 7 control subjects on a 3.0 T MRI system. The average similarity indices between the specific regions obtained by our method and by neuroradiologists for the BP and WM regions were 95.5 ± 1.2 and 85.2 ± 4.3%, respectively, for MS patients. Moreover, they were 95.0 ± 2.0 and 85.9 ± 3.4%, respectively, for the control subjects. The proposed method might be feasible for segmentation of WM and GM regions in MS patients.
Insights
This study presents an automated method for segmenting white matter (WM) and gray matter (GM) in brain magnetic resonance (MR) images of multiple sclerosis (MS) patients. The novel approach accurately differentiates brain regions, aiding in MS lesion analysis.
Area of Science:
- Medical Imaging
- Neuroscience
- Biomedical Engineering
Background:
- Accurate segmentation of white matter (WM) and gray matter (GM) is crucial for diagnosing and monitoring neurological conditions like multiple sclerosis (MS).
- Current manual segmentation methods are time-consuming and prone to inter-observer variability.
- Automated segmentation techniques are needed to improve efficiency and consistency in analyzing brain magnetic resonance (MR) images.
Purpose of the Study:
- To develop and validate an automated method for segmenting WM and GM regions in MR images, specifically addressing the challenges posed by MS lesions.
- To derive the brain parenchymal (BP) region using histogram analysis of T1-weighted images.
- To refine WM segmentation by incorporating MS lesion candidates and excluding subcortical structures, and subsequently obtain GM by subtracting WM from BP.
Main Methods:
- An automated segmentation method was developed using T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery (FLAIR) MR images.
- Brain parenchymal (BP) region segmentation involved histogram analysis of T1-weighted images.
- White matter (WM) segmentation incorporated computer-aided detection (CAD) of MS lesions and subtraction of a basal ganglia/thalamus template from tentative WM regions.
- Gray matter (GM) segmentation was achieved by subtracting the segmented WM regions from the BP region.
Main Results:
- The automated method was applied to MR images from 7 MS patients and 7 control subjects acquired on a 3.0 T MRI system.
- Average similarity indices between automated and neuroradiologist segmentations were high: 95.5 ± 1.2% for BP and 85.2 ± 4.3% for WM in MS patients.
- Similar high similarity indices were observed in control subjects: 95.0 ± 2.0% for BP and 85.9 ± 3.4% for WM.
Conclusions:
- The proposed automated method demonstrates feasibility for segmenting WM and GM regions in the context of multiple sclerosis (MS).
- The high similarity indices suggest the method's potential for reliable and efficient analysis of brain structures in MS patients.
- This automated approach could significantly aid in the quantitative assessment and monitoring of MS progression.
