A level set method for multiple sclerosis lesion segmentation
Yue Zhao1, Shuxu Guo1, Min Luo2
1School of Electronic Engineering, Jilin University, Changchun, Jilin, China.
Abstract:
In this paper, we present a level set method for multiple sclerosis (MS) lesion segmentation from FLAIR images in the presence of intensity inhomogeneities. We use a three-phase level set formulation of segmentation and bias field estimation to segment MS lesions and normal tissue region (including GM and WM) and CSF and the background from FLAIR images. To save computational load, we derive a two-phase formulation from the original multi-phase level set formulation to segment the MS lesions and normal tissue regions. The derived method inherits the desirable ability to precisely locate object boundaries of the original level set method, which simultaneously performs segmentation and estimation of the bias field to deal with intensity inhomogeneity. Experimental results demonstrate the advantages of our method over other state-of-the-art methods in terms of segmentation accuracy.
Insights
This study introduces a novel level set method for segmenting multiple sclerosis (MS) lesions in FLAIR images. The method accurately identifies lesions despite image intensity variations, improving segmentation accuracy.
Area of Science:
- Medical imaging analysis
- Computational neuroscience
- Biomedical image processing
Background:
- Accurate segmentation of multiple sclerosis (MS) lesions is crucial for diagnosis and monitoring.
- FLAIR images are commonly used for MS lesion detection but are susceptible to intensity inhomogeneities.
- Existing segmentation methods struggle with bias field correction, impacting accuracy.
Purpose of the Study:
- To develop an advanced level set method for robust MS lesion segmentation from FLAIR images.
- To address challenges posed by intensity inhomogeneities and bias fields in medical scans.
- To improve the precision and computational efficiency of MS lesion segmentation.
Main Methods:
- A three-phase level set formulation for simultaneous segmentation and bias field estimation was initially proposed.
- A computationally efficient two-phase level set formulation was derived for segmenting MS lesions and normal tissue.
- The method precisely delineates object boundaries while correcting for intensity variations.
Main Results:
- The proposed two-phase level set method demonstrated superior segmentation accuracy compared to existing state-of-the-art techniques.
- The method effectively handles intensity inhomogeneities, leading to more reliable lesion identification.
- Experimental results validated the method's advantages in segmenting MS lesions and normal tissue regions.
Conclusions:
- The developed level set method offers a significant advancement in MS lesion segmentation from FLAIR images.
- The approach provides accurate and robust segmentation, even in the presence of challenging image artifacts.
- This method holds promise for improved clinical assessment and research in multiple sclerosis.
