Next Article in Journal / Special Issue
Restoration of Bi-Contrast MRI Data for Intensity Uniformity with Bayesian Coring of Co-Occurrence Statistics
Previous Article in Journal
Small Angle Scattering in Neutron Imaging—A Review
Previous Article in Special Issue
Mereotopological Correction of Segmentation Errors in Histological Imaging
Article

Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology

1
School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, UK
2
Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh EH16 4SB, UK
*
Authors to whom correspondence should be addressed.
This paper is an extended version of a conference paper: Rachmadi, M.; Komura, T.; Valdes Hernandez, M.; Agan, M. Evaluation of Four Supervised Learning Schemes in White Matter Hyperintensities Segmentation in Absence or Mild Presence of Vascular Pathology. In Communications in Computer and Information Science, Proceedings of the Medical Image Understanding and Analysis. (MIUA), Edinburgh, UK, 11–13 July 2017; Valdés Hernández, M., González-Castro, V., Eds.; Springer: Cham, Switzerland, 2017; Volume 723, pp. 482–493
Received: 7 November 2017 / Revised: 7 December 2017 / Accepted: 12 December 2017 / Published: 14 December 2017
(This article belongs to the Special Issue Selected Papers from “MIUA 2017”)
In the wake of the use of deep learning algorithms in medical image analysis, we compared performance of deep learning algorithms, namely the deep Boltzmann machine (DBM), convolutional encoder network (CEN) and patch-wise convolutional neural network (patch-CNN), with two conventional machine learning schemes: Support vector machine (SVM) and random forest (RF), for white matter hyperintensities (WMH) segmentation on brain MRI with mild or no vascular pathology. We also compared all these approaches with a method in the Lesion Segmentation Tool public toolbox named lesion growth algorithm (LGA). We used a dataset comprised of 60 MRI data from 20 subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, each scanned once every year during three consecutive years. Spatial agreement score, receiver operating characteristic and precision-recall performance curves, volume disagreement score, agreement with intra-/inter-observer reliability measurements and visual evaluation were used to find the best configuration of each learning algorithm for WMH segmentation. By using optimum threshold values for the probabilistic output from each algorithm to produce binary masks of WMH, we found that SVM and RF produced good results for medium to very large WMH burden but deep learning algorithms performed generally better than conventional ones in most evaluations. View Full-Text
Keywords: Alzheimer’s Disease; brain MRI; conventional machine learning; deep learning; dementia; white matter hyperintensities; segmentation; machine learning; medical image analysis Alzheimer’s Disease; brain MRI; conventional machine learning; deep learning; dementia; white matter hyperintensities; segmentation; machine learning; medical image analysis
Show Figures

Figure 1

MDPI and ACS Style

Rachmadi, M.F.; Valdés-Hernández, M.D.C.; Agan, M.L.F.; Komura, T. Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology. J. Imaging 2017, 3, 66. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging3040066

AMA Style

Rachmadi MF, Valdés-Hernández MDC, Agan MLF, Komura T. Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology. Journal of Imaging. 2017; 3(4):66. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging3040066

Chicago/Turabian Style

Rachmadi, Muhammad F.; Valdés-Hernández, Maria D.C.; Agan, Maria L.F.; Komura, Taku. 2017. "Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology" J. Imaging 3, no. 4: 66. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging3040066

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop