Level Set Framework of Multi Labels Fusion for Multiple Sclerosis Lesion Segmentation
ACM International Conference Proceeding Series
Association for Computing Machinery
New York, NY
First page number:
Last page number:
Multiple sclerosis (MS) lesion segmentation is important in estimating the progress of the disease and measuring the impact of new clinical treatments. In this paper, we present a multi-label fusion embedded level set method for White Matter (WM) lesion segmentation from Multiple Sclerosis (MS) patient images. Specifically we focus on the validation of the variational level set method. Lesion segmentation is achieved by extending the level set contour which consists of a label fusion term, an image data term and a regularization term. Labels are obtained from the fuzzy C-means model and embedded into the label fusion term. To compare the performance of our method with other state-of-the-art methods, we evaluated the methods with 20 MRI datasets of MS patients. Our approach exhibits a significantly higher accuracy on segmention of WM lesions over other evaluated methods. © 2018 Association for Computing Machinery.
Multiple sclerosis lesion; Multi-atlas; Level set; Fuzzy C-means; MRI
Analytical, Diagnostic and Therapeutic Techniques and Equipment
Level Set Framework of Multi Labels Fusion for Multiple Sclerosis Lesion Segmentation.
ACM International Conference Proceeding Series, 2018
New York, NY: Association for Computing Machinery.