Extracting and summarizing white matter hyperintensities using supervised segmentation methods in Alzheimer's disease risk and aging studies

Ithapu, Vamsi Krishna; Singh, Vikas; Lindner, Christopher; Austin, Benjamin; Hinrichs, Chris; Carlsson, Cynthia M.; Bendlin, Barbara B.; Johnson, Sterling C.

doi:10.1002/hbm.22472

Cited by 84 publications

(77 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two algorithms are commonly used in segmentation and classification tasks. For reproducibility and repeatability reasons, and also to make comparison easier, we modified a public toolbox: W2MHS [5,31], which uses RF for WMH segmentation. We retrained the RF model using the following parameters: 300 trees, 2 minimum samples in a leaf and 4 minimum samples before splitting.…”

Section: Support Vector Machine and Random Forestmentioning

confidence: 99%

“…In many cases, ones have to test several different feature extraction methods before finding suitable features for the task. For this study, three different sets of features from three different studies by Klöppel et al [3], Leite et al [4] and Ithapu et al [5] are used for segmenting WMH using conventional machine learning algorithms. We use the same set of features that proved relevant for this task in previous studies and are implemented in publicly available tools, such as the W2MHS toolbox.…”

Section: Feature Extraction For Conventional Machine Learning Algorithmsmentioning

confidence: 99%

“…Firstly, we use 125 MR image's grey scale values and 1875 response values from a filter bank comprised by a low pass filter, a high pass filter, a band pass filter and an edge filter, on 5 × 5 × 5 3D ROIs, which is the standard pipeline of the W2MHS toolbox (please see the complete study done by Ithapu et al [5] for further explanation). Secondly, we automatically extract 44 first-and second-order statistical measures out of the intensity values from 5 × 5 2D ROIs by using histogram analysis (i.e., mean, variance, skewness, kurtosis and 1%, 10%, 50%, 90% and 99% percentiles), grey-level co-occurrence matrix or GLCM (i.e., using 0 • , 45 • , 90 • and 135 • orientations and distance of 1 and 2 of neighbouring voxels), grey-level run-length matrix or GLRLM (i.e., using 0 • , 45 • , 90 • and 135 • orientations) and statistical analysis of gradient (i.e., mean, variance, skewness, kurtosis and percentage of voxels with non gradient) as in study done by Leite et al [4].…”

Section: Feature Extraction For Conventional Machine Learning Algorithmsmentioning

confidence: 99%

“…Before the emergence of deep learning algorithms, most of the works were based on support vector machine (SVM) and random forests (RF) for which some image features need to be extracted first. Some notable works were done by Klöppel et al [3,4] and Leite et al [5] where several feature extraction methods and learning algorithms were evaluated to find the best possible combination for WMH segmentation. However, these studies cannot be compared to each other directly because they use different feature extraction methods and MRI datasets.…”

Section: Introductionmentioning

confidence: 99%

“…SET-1 contains greyscale colour values and texton-based feature extraction from T2-FLAIR that is used in [5]. The feature vector size is 2000.…”

mentioning

confidence: 99%

See 4 more Smart Citations

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

et al. 2017

View full text Add to dashboard Cite

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.

show abstract

Section: Support Vector Machine and Random Forestmentioning

confidence: 99%

Section: Feature Extraction For Conventional Machine Learning Algorithmsmentioning

confidence: 99%

Section: Feature Extraction For Conventional Machine Learning Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…SET-1 contains greyscale colour values and texton-based feature extraction from T2-FLAIR that is used in [5]. The feature vector size is 2000.…”

mentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2017

View full text Add to dashboard Cite

show abstract

Socioeconomic Status Mediates Racial Differences Seen Using theAT(N)Framework

Meeker

Wisch

Hudson

et al. 2020

Annals of Neurology

View full text Add to dashboard Cite

Objectives African Americans are at greater risk for developing Alzheimer's disease (AD) dementia than non‐Hispanic whites. In addition to biological considerations (eg, genetic influences and comorbid disorders), social and environmental factors may increase the risk of AD dementia. This paper (1) assesses neuroimaging biomarkers of amyloid (A), tau (T), and neurodegeneration (N) for potential racial differences and (2) considers mediating effects of socioeconomic status (SES) and measures of small vessel and cardiovascular disease on observed race differences. Methods Imaging measures of AT(N) (amyloid and tau positron emission tomography [PET]) structural magnetic resonance imaging (MRI), and resting state functional connectivity (rs‐fc) were collected from African American (n = 131) and white (n = 685) cognitively normal participants age 45 years and older. Measures of small vessel and cardiovascular disease (white matter hyperintensities [WMHs] on MRI, blood pressure, and body mass index [BMI]) and area‐based SES were included in mediation analyses. Results Compared to white participants, African American participants had greater neurodegeneration, as measured by decreased cortical volumes (Cohen's f2 = 0.05, p < 0.001). SES mediated the relationship between race and cortical volumes. There were no significant race effects for amyloid, tau, or rs‐fc signature. Interpretation Modifiable factors, such as differences in social contexts and resources, particularly area‐level SES, may contribute to observed racial differences in AD. Future studies should emphasize collection of relevant psychosocial factors in addition to the development of intentional diversity and inclusion efforts to improve the racial/ethnic and socioeconomic representativeness of AD studies. ANN NEUROL 2021;89:254–265

show abstract

Rationale, design and methodology of the image analysis protocol for studies of patients with cerebral small vessel disease and mild stroke

et al. 2015

View full text Add to dashboard Cite

RationaleCerebral small vessel disease (SVD) is common in ageing and patients with dementia and stroke. Its manifestations on magnetic resonance imaging (MRI) include white matter hyperintensities, lacunes, microbleeds, perivascular spaces, small subcortical infarcts, and brain atrophy. Many studies focus only on one of these manifestations. A protocol for the differential assessment of all these features is, therefore, needed.AimsTo identify ways of quantifying imaging markers in research of patients with SVD and operationalize the recommendations from the STandards for ReportIng Vascular changes on nEuroimaging guidelines. Here, we report the rationale, design, and methodology of a brain image analysis protocol based on our experience from observational longitudinal studies of patients with nondisabling stroke.DesignThe MRI analysis protocol is designed to provide quantitative and qualitative measures of disease evolution including: acute and old stroke lesions, lacunes, tissue loss due to stroke, perivascular spaces, microbleeds, macrohemorrhages, iron deposition in basal ganglia, substantia nigra and brain stem, brain atrophy, and white matter hyperintensities, with the latter separated into intense and less intense. Quantitative measures of tissue integrity such as diffusion fractional anisotropy, mean diffusivity, and the longitudinal relaxation time are assessed in regions of interest manually placed in anatomically and functionally relevant locations, and in others derived from feature extraction pipelines and tissue segmentation methods. Morphological changes that relate to cognitive deficits after stroke, analyzed through shape models of subcortical structures, complete the multiparametric image analysis protocol.OutcomesFinal outcomes include guidance for identifying ways to minimize bias and confounds in the assessment of SVD and stroke imaging biomarkers. It is intended that this information will inform the design of studies to examine the underlying pathophysiology of SVD and stroke, and to provide reliable, quantitative outcomes in trials of new therapies and preventative strategies.

show abstract

Extracting and summarizing white matter hyperintensities using supervised segmentation methods in Alzheimer's disease risk and aging studies

Cited by 84 publications

References 50 publications

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

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

Socioeconomic Status Mediates Racial Differences Seen Using theAT(N)Framework

Rationale, design and methodology of the image analysis protocol for studies of patients with cerebral small vessel disease and mild stroke

Contact Info

Product

Resources

About