2017
DOI: 10.3389/fneur.2017.00327
|View full text |Cite
|
Sign up to set email alerts
|

Application of Texture Analysis to Study Small Vessel Disease and Blood–Brain Barrier Integrity

Abstract: ObjectivesWe evaluate the alternative use of texture analysis for evaluating the role of blood–brain barrier (BBB) in small vessel disease (SVD).MethodsWe used brain magnetic resonance imaging from 204 stroke patients, acquired before and 20 min after intravenous gadolinium administration. We segmented tissues, white matter hyperintensities (WMH) and applied validated visual scores. We measured textural features in all tissues pre- and post-contrast and used ANCOVA to evaluate the effect of SVD indicators on t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
26
0
1

Year Published

2019
2019
2021
2021

Publication Types

Select...
4
2
1

Relationship

1
6

Authors

Journals

citations
Cited by 31 publications
(30 citation statements)
references
References 56 publications
3
26
0
1
Order By: Relevance
“…As the training sample size increases in future research, it is crucial to develop automatic or semi-automatic image selection and ROI determination algorithms to improve the research feasibility and to reduce inter-operator variability. Forth, along with age growth, a series of physiological changes in the brain also affect the texture features (47). Although there was no statistically significant difference in age ratios between the two groups, we did not achieve a complete 1:1 match, so the effects of this incomplete match on the research results cannot be completely excluded.…”
Section: Discussionmentioning
confidence: 79%
“…As the training sample size increases in future research, it is crucial to develop automatic or semi-automatic image selection and ROI determination algorithms to improve the research feasibility and to reduce inter-operator variability. Forth, along with age growth, a series of physiological changes in the brain also affect the texture features (47). Although there was no statistically significant difference in age ratios between the two groups, we did not achieve a complete 1:1 match, so the effects of this incomplete match on the research results cannot be completely excluded.…”
Section: Discussionmentioning
confidence: 79%
“…In particular, we utilised Fazekas [2], basal ganglia perivascular spaces (BGPVS) [10], and total SVD [12] scores to account for the location, presence and size of WMH, the existence of enlarged PVS on the basal ganglia, and the burden of four MRI features of the SVD (lacunes, microbleeds, PVS, and WMH). We summed up periventricular and deep WM scores to obtain a total Fazekas score that ranged from zero to six [4,14]. A senior and experienced neuroradiologist generated all visual scores.…”
Section: Subjects and Clinical Scoresmentioning
confidence: 99%
“…(FIMC and SIMC) derived from the GLCM, which quantify the linear dependency or correlation between intensities, thus representing homogeneity but adding some desirable properties that are not represented by the original correlation descriptor extracted from the GLCM [87]. A previous study by Valdés-Hernández et al that evaluated the use of texture analysis as an alternative for characterizing SVD and assessing possible blood brain barrier leakage [123] reported differences in the texture outcome of the FLAIR deep gray matter between post-acute lacunar and cortical stroke patients, but only with borderline significance. This study reported that the texture pattern in the deep gray matter was more homogeneous in patients with recent lacunar stroke compared to those who had a cortical type.…”
Section: Discussionmentioning
confidence: 99%
“…Brain Primary brain tumors Classification of benign and malign tumors; Grading of gliomas [103], [104], [117], [118] Brain Brain metastases Differentiation from radiation necrosis; Identification of the primary cancer [106], [107] Brain Dementia Identification of Alzheimer's disease [58], [119] Brain Multiple sclerosis Early diagnosis [120], [121] Brain Ischemic Stroke Prediction of hemorrhagic transformation; Evaluation of small vessel disease [122], [123] Brain Mild traumatic brain injury Effect of trauma in cerebral tissue [57] Heart Myocardial infarction Differentiation between acute and chronic [124] Heart Arrhythmias Classification of low and high-risk patients [125] Breast Breast cancer Classification of benign and malign lesions; Classification of cancer molecular subtypes [60], [61], [126] Prostate Prostate cancer Detection of cancerous tissue [127], [128] Kidney Autosomal dominant polycystic disease Prediction of renal function decline [129] Liver Liver fibrosis Assessment of the disease [130] Knee Knee osteoarthritis Quantification of subchondral bone architecture; Identification of bone marrow lesions [131], [132] Data analysis with machine learning…”
Section: Organ Lesion / Disease Objectives Referencesmentioning
confidence: 99%
See 1 more Smart Citation