A fully automated method for quantifying and localizing white matter hyperintensities on MR images

Background: According to the Standards for Reporting Vascular Changes on Neuroimaging, White Matter Hyperintensities (WMHs) are cerebral white matter lesions that are characterized by abnormal tissues of variable sizes and appear hyperintense in T2-weighted Magnetic Resonance (MR) measurements without cavitation (i.e., their tissue signals differ from those of Cerebrospinal Fluid or CSF). Such abnormal tissue regions are typically observed in the MR images of brains of healthy older adults and are associated with a number of geriatric neurodegenerative diseases. Explanations of the exact causes and mechanisms of these diseases remain inconclusive. Moreover, WMHs are typically identified by visual assessment and manual examination, both of which require considerable time. This brings up a need of developing a method for detecting WMHs more objectively and enabling patients to be treated early. As a consequence, damages on nerve cells can be limited and the severity of patients’ conditions can be contained. Aims: This paper presents a computer-aided technique for automatically detecting and segmenting anomalies in MR images. Methods: The method has two steps: (1) a Band Expansion Process (BEP) to expand the dimensions of brain MR images nonlinearly and (2) anomaly detection algorithms to detect WMHs. Synthesized MR images provided by BrainWeb were used as benchmarks against which the detection performance of the algorithms was determined. Results: The most notable findings are as follows: Firstly, compared with the other anomaly detection algorithms and the Lesion Segmentation Tool (LST), BEP-anomaly detection is shown to be the most effective in detecting WMHs. Secondly, across all levels of background noise and inhomogeneity, the mean Similarity Index (SI) produced by our proposed algorithm is higher than that produced by LST, indicating that the algorithm is more effective than LST in segmenting WMHs from brain MR images. Conclusion: Experimental results demonstrated a significantly high accuracy of the BEP-K/R-RX method in detection of synthetic brain MS lesion data. In the meantime, it also effectively enhances the detection of brain lesions.

Download Full-text

Computerized evaluation method of white matter hyperintensities related to subcortical vascular dementia in brain MR images

10.1117/12.845229 ◽

2010 ◽

Author(s):

Hidetaka Arimura ◽

Yasuo Kawata ◽

Yasuo Yamashita ◽

Taiki Magome ◽

Masafumi Ohki ◽

...

Keyword(s):

White Matter ◽

Vascular Dementia ◽

White Matter Hyperintensities ◽

Evaluation Method ◽

Mr Images ◽

Subcortical Vascular Dementia ◽

Brain Mr Images

Download Full-text

Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images

NeuroImage ◽

10.1016/j.neuroimage.2018.07.005 ◽

2018 ◽

Vol 183 ◽

pp. 650-665 ◽

Cited By ~ 50

Author(s):

Hongwei Li ◽

Gongfa Jiang ◽

Jianguo Zhang ◽

Ruixuan Wang ◽

Zhaolei Wang ◽

...

Keyword(s):

White Matter ◽

White Matter Hyperintensities ◽

Mr Images ◽

Convolutional Network ◽

Fully Convolutional Network ◽

Network Ensembles

Download Full-text

Lighter U-net for segmenting white matter hyperintensities in MR images

Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services ◽

10.1145/3360774.3368203 ◽

2019 ◽

Author(s):

Jun Zhuang ◽

Mingchen Gao ◽

Mohammad AI Hasan

Keyword(s):

White Matter ◽

White Matter Hyperintensities ◽

Mr Images

Download Full-text

Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images

10.1101/2020.07.24.219485 ◽

2020 ◽

Author(s):

Vaanathi Sundaresan ◽

Giovanna Zamboni ◽

Peter M. Rothwell ◽

Mark Jenkinson ◽

Ludovica Griffanti

Keyword(s):

White Matter ◽

White Matter Hyperintensities ◽

Training Data ◽

Periventricular White Matter ◽

Mr Images ◽

Comparable Performance ◽

Brain Mr Images ◽

Reliable Quantification ◽

Anatomical Information ◽

Better Than

AbstractWhite matter hyperintensities (WMHs) have been associated with various cerebrovascular and neurodegenerative diseases. Reliable quantification of WMHs is essential for understanding their clinical impact in normal and pathological populations. Automated segmentation of WMHs is highly challenging due to heterogeneity in WMH characteristics between deep and periventricular white matter, presence of artefacts and differences in the pathology and demographics of populations. In this work, we propose an ensemble triplanar network that combines the predictions from three different planes of brain MR images to provide an accurate WMH segmentation. Also, the network uses anatomical information regarding WMH spatial distribution in loss functions for improving the efficiency of segmentation and to overcome the contrast variations between deep and periventricular WMHs. We evaluated our method on 5 datasets, of which 3 are part of a publicly available dataset (training data for MICCAI WMH Segmentation Challenge 2017 - MWSC 2017) consisting of subjects from three different cohorts. On evaluating our method separately in deep and periventricular regions, we observed robust and comparable performance in both regions. Our method performed better than most of the existing methods, including FSL BIANCA, and on par with the top ranking deep learning method of MWSC 2017.

Download Full-text

White matter hyperintensities segmentation: a new semi-automated method

Frontiers in Aging Neuroscience ◽

10.3389/fnagi.2013.00076 ◽

2013 ◽

Vol 5 ◽

Cited By ~ 37

Author(s):

Mariangela Iorio ◽

Gianfranco Spalletta ◽

Chiara Chiapponi ◽

Giacomo Luccichenti ◽

Claudia Cacciari ◽

...

Keyword(s):

White Matter ◽

White Matter Hyperintensities ◽

Automated Method

Download Full-text

Fully automatic segmentation of white matter hyperintensities in MR images of the elderly

NeuroImage ◽

10.1016/j.neuroimage.2005.06.061 ◽

2005 ◽

Vol 28 (3) ◽

pp. 607-617 ◽

Cited By ~ 164

Author(s):

F. Admiraal-Behloul ◽

D.M.J. van den Heuvel ◽

H. Olofsen ◽

M.J.P. van Osch ◽

J. van der Grond ◽

...

Keyword(s):

White Matter ◽

White Matter Hyperintensities ◽

Automatic Segmentation ◽

The Elderly ◽

Mr Images ◽

Fully Automatic

Download Full-text

An incomplete Circle of Willis is not a risk factor for white matter hyperintensities: The Tromsø Study

10.1101/2020.09.25.20183756 ◽

2020 ◽

Author(s):

Lars B Hindenes ◽

Asta Kristine Håberg ◽

Ellisiv B Mathiesen ◽

Torgil R Vangberg

Keyword(s):

Risk Factors ◽

Blood Pressure ◽

Risk Factor ◽

White Matter ◽

White Matter Hyperintensities ◽

Population Sample ◽

Circle Of Willis ◽

Cross Sectional ◽

Automated Method ◽

Fluid Attenuated Inversion Recovery

Objective The Circle of Willis (CoW) is often underdeveloped or incomplete, leading to suboptimal blood supply to the brain. As hypoperfusion is thought to play a role in the aetiology of white matter hyperintensities (WMH), the objective of this study was to assess whether incomplete CoW variants were associated with increased WMH volumes compared to the complete CoW. Methods In a cross-sectional population sample of 1864 people (age 40 - 84 years, 46.4% men), we used an automated method to segment WMH using T1-weighted and T2-weighted fluid-attenuated inversion recovery image obtained at 3T. CoW variants were classified from time-of-flight scans, also at 3T. WMH risk factors, including age, sex, smoking and blood pressure, were obtained from questionnaires and clinical examinations. We used linear regression to examine whether people with incomplete CoW variants had greater volumes of deep WMH (DWMH) and periventricular WMH (PWMH) compared to people with the complete CoW, correcting for WMH risk factors. Results Participants with incomplete CoW variants did not have significantly higher DWMH or PWMH volumes than those with complete CoW when accounting for risk factors. Age, pack-years smoking, and systolic blood pressure were risk factors for increased DWMH and PWMH volume. Diabetes was a unique risk factor for increased PWMH volume. Conclusion Incomplete CoW variants do not appear to be risk factors for WMH in the general population.

Download Full-text