Projects per year
Abstract
We investigated the performance of four popular supervised learning algorithms in medical image analysis for white matter hyperintensities segmentation in brain MRI with mild or no vascular pathology. The algorithms evaluated in this study are support vector machine (SVM), random forest (RF), deep Boltzmann machine (DBM) and convolution encoder network (CEN). We compared these algorithms with two methods in the Lesion Segmentation Tool (LST) public toolbox which are lesion growth algorithm (LGA) and lesion prediction algorithm
(LPA). We used a dataset comprised of 60 MRI data from 20 subjects from the ADNI database, each scanned once in three consecutive years. In this study, CEN produced the best Dice similarity coefficient (DSC): mean value 0.44. All algorithms struggled to produce good DSC due to the very small WMH burden (i.e., smaller than 1,500 mm3). LST-LGA, LST-LPA, SVM, RF and DBM produced mean DSC scores ranging from 0.17 to 0.34.
(LPA). We used a dataset comprised of 60 MRI data from 20 subjects from the ADNI database, each scanned once in three consecutive years. In this study, CEN produced the best Dice similarity coefficient (DSC): mean value 0.44. All algorithms struggled to produce good DSC due to the very small WMH burden (i.e., smaller than 1,500 mm3). LST-LGA, LST-LPA, SVM, RF and DBM produced mean DSC scores ranging from 0.17 to 0.34.
Original language | English |
---|---|
Title of host publication | Medical Image Understanding and Analysis (MIUA 2017) |
Publisher | Springer |
Pages | 482-493 |
Number of pages | 12 |
ISBN (Electronic) | 978-3-319-60964-5 |
ISBN (Print) | 978-3-319-60963-8 |
DOIs | |
Publication status | Published - 22 Jun 2017 |
Event | Medical Image Understanding and Analysis (MIUA 2017) - Edinburgh, United Kingdom Duration: 11 Jul 2017 → 13 Jul 2017 |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Publisher | Springer, Cham |
Volume | 723 |
ISSN (Print) | 1865-0929 |
Conference
Conference | Medical Image Understanding and Analysis (MIUA 2017) |
---|---|
Country/Territory | United Kingdom |
City | Edinburgh |
Period | 11/07/17 → 13/07/17 |
Keywords / Materials (for Non-textual outputs)
- brain MRI
- white matter hyperintensity
- image segmentation
- supervised learning
- Deep neural network
Fingerprint
Dive into the research topics of 'Evaluation of Four Supervised Learning Schemes in White Matter Hyperintensities Segmentation in Absence or Mild Presence of Vascular Pathology'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Quantification of vascular disease burden to stratify dementia for diagnosis and care management
Valdes Hernandez, M. & Wardlaw, J.
1/04/15 → 31/03/17
Project: Research Collaboration with external organisation