A New Method to Segment Multiple Sclerosis Lesions Using Multispectral Magnetic Resonance Images / 生物医学工程学杂志
Journal of Biomedical Engineering
;
(6): 330-335, 2015.
Article
in Chinese
| WPRIM
| ID: wpr-266676
ABSTRACT
Magnetic resonance (MR) images can be used to detect lesions in the brains of patients with multiple sclerosis (MS). An automatic method is presented for segmentation of MS lesions using multispectral MR images in this paper. Firstly, a Pd-w image is subtracted from its corresponding T1-w images to get an image in which the cerebral spinal fluid (CSF) is enhanced. Secondly, based on kernel fuzzy c-means clustering (KFCM) algorithm, the enhanced image and the corresponding T2-w image are segmented respectively to extract the CSF region and the CSF-MS lesions combinatoin region. A raw MS lesions image is obtained by subtracting the CSF region from CSF-MS region. Thirdly, based on applying median filter and thresholding to the raw image, the MS lesions were detected finally. Results were tested on BrainWeb images and evaluated with Dice similarity coefficient (DSC), sensitivity (Sens), specificity (Spec) and accuracy (Acc). The testing results were satisfactory.
Full text:
Available
Index:
WPRIM (Western Pacific)
Main subject:
Pathology
/
Algorithms
/
Brain
/
Magnetic Resonance Imaging
/
Image Enhancement
/
Sensitivity and Specificity
/
Diagnosis
/
Multiple Sclerosis
Type of study:
Diagnostic study
Limits:
Humans
Language:
Chinese
Journal:
Journal of Biomedical Engineering
Year:
2015
Type:
Article
Similar
MEDLINE
...
LILACS
LIS