Title |
Two Time Point MS Lesion Segmentation in Brain MRI: An Expectation-Maximization Framework
|
---|---|
Published in |
Frontiers in Neuroscience, December 2016
|
DOI | 10.3389/fnins.2016.00576 |
Pubmed ID | |
Authors |
Saurabh Jain, Annemie Ribbens, Diana M. Sima, Melissa Cambron, Jacques De Keyser, Chenyu Wang, Michael H. Barnett, Sabine Van Huffel, Frederik Maes, Dirk Smeets |
Abstract |
Purpose: Lesion volume is a meaningful measure in multiple sclerosis (MS) prognosis. Manual lesion segmentation for computing volume in a single or multiple time points is time consuming and suffers from intra and inter-observer variability. Methods: In this paper, we present MSmetrix-long: a joint expectation-maximization (EM) framework for two time point white matter (WM) lesion segmentation. MSmetrix-long takes as input a 3D T1-weighted and a 3D FLAIR MR image and segments lesions in three steps: (1) cross-sectional lesion segmentation of the two time points; (2) creation of difference image, which is used to model the lesion evolution; (3) a joint EM lesion segmentation framework that uses output of step (1) and step (2) to provide the final lesion segmentation. The accuracy (Dice score) and reproducibility (absolute lesion volume difference) of MSmetrix-long is evaluated using two datasets. Results: On the first dataset, the median Dice score between MSmetrix-long and expert lesion segmentation was 0.63 and the Pearson correlation coefficient (PCC) was equal to 0.96. On the second dataset, the median absolute volume difference was 0.11 ml. Conclusions: MSmetrix-long is accurate and consistent in segmenting MS lesions. Also, MSmetrix-long compares favorably with the publicly available longitudinal MS lesion segmentation algorithm of Lesion Segmentation Toolbox. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Belgium | 5 | 31% |
United States | 3 | 19% |
France | 2 | 13% |
Switzerland | 1 | 6% |
Spain | 1 | 6% |
United Kingdom | 1 | 6% |
Unknown | 3 | 19% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 14 | 88% |
Practitioners (doctors, other healthcare professionals) | 1 | 6% |
Scientists | 1 | 6% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 73 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 16 | 22% |
Researcher | 15 | 21% |
Student > Master | 9 | 12% |
Student > Doctoral Student | 5 | 7% |
Student > Bachelor | 3 | 4% |
Other | 12 | 16% |
Unknown | 13 | 18% |
Readers by discipline | Count | As % |
---|---|---|
Neuroscience | 16 | 22% |
Engineering | 12 | 16% |
Medicine and Dentistry | 10 | 14% |
Computer Science | 8 | 11% |
Mathematics | 2 | 3% |
Other | 6 | 8% |
Unknown | 19 | 26% |