Deep Learning Based Detection of Enlarged Perivascular Spaces on Brain MRI

@article{Rashid2022DeepLB,
  title={Deep Learning Based Detection of Enlarged Perivascular Spaces on Brain MRI},
  author={Tanweer Rashid and Hangfan Liu and Jeffrey B. Ware and Karl Li and Jos{\'e} Rafael Romero and Elyas Fadaee and Ilya M. Nasrallah and Saima Hilal and Robert Nick Bryan and Timothy M. Hughes and Christos Davatzikos and Lenore Launer and Sudha Seshadri and Susan R. Heckbert and Mohamad Habes},
  journal={ArXiv},
  year={2022},
  volume={abs/2209.13727}
}
magnetic resonance imaging (MRI) sequences for deep learning-based detection of enlarged perivascular spaces (ePVS). To this end, we implemented an effective light-weight U-Net adapted for ePVS detection and comprehensively investigated different combinations of information from susceptibility weighted imaging (SWI), fluid-attenuated inversion recovery (FLAIR), T1-weighted (T1w) and T2-weighted (T2w) MRI sequences. We conclude that T2w MRI is the most important for accurate ePVS detection, and… 
1 Citations

Figures and Tables from this paper

A critical guide to the automated quantification of perivascular spaces in magnetic resonance imaging

The present review emphasizes that importance of voxel-wise evaluation of model performance, mainly with the Sørensen Dice similarity coefficient, if the goal is to assess volumetric or morphological measures of PVS.

References

SHOWING 1-10 OF 40 REFERENCES

DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI

The results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data (particularly QSM) can improve the Detection of CMB and non-hemorrhage iron deposits with sensitivity and precision that is compatible with use in large-scale research studies.

3D Segmentation of Perivascular Spaces on T1-Weighted 3 Tesla MR Images With a Convolutional Autoencoder and a U-Shaped Neural Network

A deep learning algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter and basal ganglia is implemented, based on an autoencoder and a U-shaped network, and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults.

Enhancement of Perivascular Spaces Using Densely Connected Deep Convolutional Neural Network

This paper introduces a deep-learning-based method, which can enhance a magnetic resonance (MR) image to better visualize the PVS and proposes a very deep 3D convolutional neural network that contains densely connected networks with skip connections.

Image processing approaches to enhance perivascular space visibility and quantification using MRI

The Enhanced PVS Contrast (EPC) was achieved by combining T1- and T2-weighted images that were adaptively filtered to remove non-structured high-frequency spatial noise and improves the conspicuity of the PVS and aid resolving a larger number of PVS.

MR Imaging-based Multimodal Autoidentification of Perivascular Spaces (mMAPS): Automated Morphologic Segmentation of Enlarged Perivascular Spaces at Clinical Field Strength.

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.

Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering

A segmentation technique based on the 3D Frangi filtering for extraction of PVS from MRI correlated well with neuroradiological assessments and demonstrated the robustness and generalisability of the proposed method.

Structured Learning for 3-D Perivascular Space Segmentation Using Vascular Features

Instead of manual annotation, the proposed structured-learning-based segmentation framework provides an automatic way for PVS segmentation and can be potentially used for other vascular structure segmentation because of its data-driven property.

Multi-instance Deep Learning with Graph Convolutional Neural Networks for Diagnosis of Kidney Diseases Using Ultrasound Imaging

A novel multi- instance deep learning method to build a robust classifier by treating multiple 2D US images of each individual subject as multiple instances of one bag, with better performance than alternative state-of-the-art multi-instance deep learning methods.

Enlarged perivascular spaces and cerebral small vessel disease

  • G. PotterF. Doubal J. Wardlaw
  • Medicine, Psychology
    International journal of stroke : official journal of the International Stroke Society
  • 2015
Enlarged perivascular spaces are associated with age, lacunar stroke subtype and white matter lesions and should be considered as another magnetic resonance imaging marker of cerebral small vessel disease.

Cerebral Perivascular Spaces Visible on Magnetic Resonance Imaging: Development of a Qualitative Rating Scale and its Observer Reliability

A more inclusive and robust visual PVS rating scale allowing rating of all grades of PVS severity on structural brain imaging is developed and tested, which has good observer reliability for basal ganglia and centrum semiovale PVS, and moderate reliability for midbrain PVS.