Dataset Information

Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images.

ABSTRACT: Accurate segmentation of perivascular spaces (PVSs) is an important step for quantitative study of PVS morphology. However, since PVSs are the thin tubular structures with relatively low contrast and also the number of PVSs is often large, it is challenging and time-consuming for manual delineation of PVSs. Although several automatic/semi-automatic methods, especially the traditional learning-based approaches, have been proposed for segmentation of 3D PVSs, their performance often depends on the hand-crafted image features, as well as sophisticated preprocessing operations prior to segmentation (e.g., specially defined regions-of-interest (ROIs)). In this paper, a novel fully convolutional neural network (FCN) with no requirement of any specified hand-crafted features and ROIs is proposed for efficient segmentation of PVSs. Particularly, the original T2-weighted 7T magnetic resonance (MR) images are first filtered via a non-local Haar-transform-based line singularity representation method to enhance the thin tubular structures. Both the original and enhanced MR images are used as multi-channel inputs to complementarily provide detailed image information and enhanced tubular structural information for the localization of PVSs. Multi-scale features are then automatically learned to characterize the spatial associations between PVSs and adjacent brain tissues. Finally, the produced PVS probability maps are recursively loaded into the network as an additional channel of inputs to provide the auxiliary contextual information for further refining the segmentation results. The proposed multi-channel multi-scale FCN has been evaluated on the 7T brain MR images scanned from 20 subjects. The experimental results show its superior performance compared with several state-of-the-art methods.

SUBMITTER: Lian C

PROVIDER: S-EPMC6430123 | biostudies-literature | 2018 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images.

Lian Chunfeng C Zhang Jun J Liu Mingxia M Liu Mingxia M Zong Xiaopeng X Hung Sheng-Che SC Lin Weili W Shen Dinggang D

Medical image analysis 20180227

Accurate segmentation of perivascular spaces (PVSs) is an important step for quantitative study of PVS morphology. However, since PVSs are the thin tubular structures with relatively low contrast and also the number of PVSs is often large, it is challenging and time-consuming for manual delineation of PVSs. Although several automatic/semi-automatic methods, especially the traditional learning-based approaches, have been proposed for segmentation of 3D PVSs, their performance often depends on the ...[more]

PMID: 29518675

Similar Datasets

Project description:Purpose To describe a fully automated segmentation method that yields object-based morphologic estimates of enlarged perivascular spaces (ePVSs) in clinical-field-strength (3.0-T) magnetic resonance (MR) imaging data. Materials and Methods In this HIPAA-compliant study, MR imaging data were obtained with a 3.0-T MR imager in research participants without dementia (mean age, 85.3 years; range, 70.4-101.2 years) who had given written informed consent. This method is built on (a) relative normalized white matter, ventricular and cortical signal intensities within T1-weighted, fluid-attenuated inversion recovery, T2-weighted, and proton density data and (b) morphologic (width, volume, linearity) characterization of each resultant cluster. Visual rating was performed by three raters, including one neuroradiologist, after established single-section guidelines. Correlations between visual counts and automated counts, as well session-to-session correlation of counts within each participant, were assessed with the Pearson correlation coefficient r. Results There was a significant correlation between counts by visual raters and automated detection of ePVSs in the same section (r = 0.65, P < .001; r = 0.69, P < .001; and r = 0.54, P < .01 for raters 1, 2, and 3, respectively). With regard to visual ratings and whole-brain count consistency, average visual rating scores were highly correlated with automated detection of total burden volume (r = 0.58, P < .01) and total ePVS number (r = 0.76, P < .01). Morphology of clusters across 28 data sets was consistent with published radiographic estimates of ePVS; mean width of clusters segmented was 3.12 mm (range, 1.7-13.5 mm). Conclusion This MR imaging-based method for multimodal autoidentification of perivascular spaces yields individual whole-brain morphologic characterization of ePVS in clinical MR imaging data and is an important tool in the detailed assessment of these features. © RSNA, 2017 Online supplemental material is available for this article.

Project description:Objective Virchow-Robin-Spaces (VRS) are cerebrospinal fluid (CSF)-containing perivascular spaces encompassing brain vessels while coursing through the parenchyma. VRS can enlarge and become visible in magnetic resonance imaging (MRI). While dilatated VRS are mostly incidental findings, they were associated with degenerative brain disease in humans. This study aimed to evaluate their occurrence and MRI morphology within the ventral forebrain of structurally normal canine and feline brains and physiological cerebrospinal fluid analysis. Sample Retro- and prospective, observational study reviewing medical records of client-owned dogs and cats which underwent MRI brain scans for unrelated reasons between 2011 and 2021. We comprised studies with various magnetic field strengths (1 Tesla/3 Tesla). Out of 2500 brain scans, three hundred thirty-five patients (293 dogs, 42 cats) presented with absent intracranial pathology and physiological CSF analysis and were included. Procedure The ventral forebrain of the included animals was assessed for bi- or unilateral CSF-isointense foci in the transverse plane. Statistical correlations were evaluated between dilated VRS presence, field strength, age, gender, weight, and cranium conformation. Additionally, a post-mortem histopathologic analysis of one dog and one cat showing dilated VRS on MRI was performed to confirm perforating arteries in the gray matter of the ventral forebrain. Results 57% of patients presented dilated VRS (N = 191: 170 dogs, 21 cats). 43% did not display dilated VRS (control group; N = 144: 123 dogs, 21 cats). A significant relation between increased magnetic field strength and detection of dilated VRS was observed in dogs; there was a 2.4 increase (p = 0.0001) in detection using 3 Tesla vs. 1 Tesla. There was a 2.4-fold increase in dilated VRS occurrence in male dogs compared to female dogs. Detection also increased with the rise of body weight. We detected no statistically significant difference between dilated VRS and the control group in age, species or cranium conformation. Conclusion and Clinical Relevance Dilated VRS can be seen within the ventral forebrain at the level of the rostral commissure on transverse MR images as symmetrical or unilateral, dot-like, CSF-isointense areas. Understanding their signal intensity features and localization prevents misinterpretation and helps differentiate them from various pathological conditions.

Dataset Information

Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images.

Publications

Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets