A comparison of different automated methods for the detection of white matter lesions in MRI data

Klöppel, Stefan; Abdulkadir, Ahmed; Hadjidemetriou, Stathis; Issleib, Sabine; Frings, Lars; Thanh, Thao Nguyen; Mader, Irina; Teipel, Stefan J.; Hüll, Michael; Ronneberger, Olaf

doi:10.1016/j.neuroimage.2011.04.053

Cited by 51 publications

(64 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…21 Combinations of multiple sequences have proved to largely remove the artifactual confound. 30,31 The study also has limitations. Despite the fact that visual assessment and categorization of PVWMH in "borderline" cases were discussed and agreed on between the 2 observers, the distinction from 1 category to another was not clear in some cases.…”

Section: Discussionmentioning

confidence: 98%

Morphologic, Distributional, Volumetric, and Intensity Characterization of Periventricular Hyperintensities

Hernández

Piper²,

Bastin

et al. 2013

AJNR Am J Neuroradiol

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 98%

Morphologic, Distributional, Volumetric, and Intensity Characterization of Periventricular Hyperintensities

Hernández

Piper²,

Bastin

et al. 2013

AJNR Am J Neuroradiol

View full text Add to dashboard Cite

show abstract

“…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%

“…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]. Lastly, 125 MR image's grey scale values and 1875 response values from Gabor filter (i.e., 32 filters from 4 directions and 4 magnitudes) are extracted from 5 × 5 × 5 3D ROIs and used as features as in study done by Klöppel et al [3]. The use of all these features is discussed in Section 4.1.…”

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-3S contains greyscale colour values and Gabor filter extracted features from T2-FLAIR and T1-weighted that is used in [3]. The feature vector size is 4000.…”

mentioning

confidence: 99%

See 2 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

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

A comparison of different automated methods for the detection of white matter lesions in MRI data

Cited by 51 publications

References 27 publications

Morphologic, Distributional, Volumetric, and Intensity Characterization of Periventricular Hyperintensities

Morphologic, Distributional, Volumetric, and Intensity Characterization of Periventricular Hyperintensities

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

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