Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

BV-GAN: 3D time-of-flight magnetic resonance angiography cerebrovascular vessel segmentation using adversarial CNNs

BV-GAN: 3D time-of-flight magnetic resonance angiography cerebrovascular vessel segmentation... Abstract.Purpose: Cerebrovascular vessel segmentation is a key step in the detection of vessel pathology. Brain time-of-flight magnetic resonance angiography (TOF-MRA) is a main method used clinically for imaging of blood vessels using magnetic resonance imaging. This method is primarily used to detect narrowing, blockage of the arteries, and aneurysms. Despite its importance, TOF-MRA interpretation relies mostly on visual, subjective assessment performed by a neuroradiologist and is mostly based on maximum intensity projections reconstruction of the three-dimensional (3D) scan, thus reducing the acquired spatial resolution. Works tackling the central problem of automatically segmenting brain blood vessels typically suffer from memory and imbalance related issues. To address these issues, the spatial context of the segmentation consider by neural networks is typically restricted (e.g., by resolution reduction or analysis of environments of lower dimensions). Although efficient, such solutions hinder the ability of the neural networks to understand the complex 3D structures typical of the cerebrovascular system and to leverage this understanding for decision making.Approach: We propose a brain-vessels generative-adversarial-network (BV-GAN) segmentation model, that better considers connectivity and structural integrity, using prior based attention and adversarial learning techniques.Results: For evaluations, fivefold cross-validation experiments were performed on two datasets. BV-GAN demonstrates consistent improvement of up to 10% in vessel Dice score with each additive designed component to the baseline state-of-the-art models.Conclusions: Potentially, this automated 3D-approach could shorten analysis time, allow for quantitative characterization of vascular structures, and reduce the need to decrease resolution, overall improving diagnosis cerebrovascular vessel disorders. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

BV-GAN: 3D time-of-flight magnetic resonance angiography cerebrovascular vessel segmentation using adversarial CNNs

Download PDF
18 pages

Loading next page...
 
/lp/spie/bv-gan-3d-time-of-flight-magnetic-resonance-angiography-TgnZRfqPr0
Publisher
SPIE
Copyright
© 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.jmi.9.4.044503
Publisher site
See Article on Publisher Site

Abstract

Abstract.Purpose: Cerebrovascular vessel segmentation is a key step in the detection of vessel pathology. Brain time-of-flight magnetic resonance angiography (TOF-MRA) is a main method used clinically for imaging of blood vessels using magnetic resonance imaging. This method is primarily used to detect narrowing, blockage of the arteries, and aneurysms. Despite its importance, TOF-MRA interpretation relies mostly on visual, subjective assessment performed by a neuroradiologist and is mostly based on maximum intensity projections reconstruction of the three-dimensional (3D) scan, thus reducing the acquired spatial resolution. Works tackling the central problem of automatically segmenting brain blood vessels typically suffer from memory and imbalance related issues. To address these issues, the spatial context of the segmentation consider by neural networks is typically restricted (e.g., by resolution reduction or analysis of environments of lower dimensions). Although efficient, such solutions hinder the ability of the neural networks to understand the complex 3D structures typical of the cerebrovascular system and to leverage this understanding for decision making.Approach: We propose a brain-vessels generative-adversarial-network (BV-GAN) segmentation model, that better considers connectivity and structural integrity, using prior based attention and adversarial learning techniques.Results: For evaluations, fivefold cross-validation experiments were performed on two datasets. BV-GAN demonstrates consistent improvement of up to 10% in vessel Dice score with each additive designed component to the baseline state-of-the-art models.Conclusions: Potentially, this automated 3D-approach could shorten analysis time, allow for quantitative characterization of vascular structures, and reduce the need to decrease resolution, overall improving diagnosis cerebrovascular vessel disorders.

Journal

Journal of Medical Imaging – SPIE

Published: Jul 1, 2022

Keywords: anatomical attention; deep learning; segmentation; time-of-flight MR angiography; vessel

References

  • The top 10 causes of death
  • Magnetic resonance angiography in evaluation of acute intracranial steno-occlusive arterial disease
    Radwan, M. E.; Aboshaera, K. O.
  • The AAPM/RSNA physics tutorial for residents. An introduction to MR angiography
    Saloner, D.
  • Artifacts in maximum-intensity-projection display of MR angiograms
    Anderson, C. M.
  • A systematic study of the class imbalance problem in convolutional neural networks
    Buda, M.; Maki, A.; Mazurowski, M. A.
  • 3D U-Net: learning dense volumetric segmentation from sparse annotation
    Cicek, O.
  • Uception-3D medical image segmentation with CNN
    Sanches, P.
  • A review on the cerebrovascular segmentation methods
    Taher, F.
  • A fast and fully automatic method for cerebrovascular segmentation on time-of-flight (TOF) MRA image
    Gao, X.
  • A novel statistical cerebrovascular segmentation algorithm with particle swarm optimization
    Wen, L.
  • Vascular segmentation of neuroimages based on a prior shape and local statistics
    Tian, Y.; Liu, Z.; Zhao, S.
  • Segmenting retinal blood vessels with deep neural networks
    Liskowski, P.; Krawiec, K.
  • VesselNet: a deep convolutional neural network with multi pathways for robust hepatic vessel segmentation
    Kitrungrotsakul, T.
  • Cerebral artery and vein segmentation in four-dimensional CT angiography using convolutional neural networks
    Meijs, M.
  • DDNet: a novel network for cerebral artery segmentation from MRA IMAGES
    Zhang, Y.; Chen, L.
  • Deformable convolutional networks
    Dai, J.
  • Spatial transformer networks
    Jaderberg, M.; Simonyan, K.; Zisserman, A.
  • DUNet: a deformable network for retinal vessel segmentation
    Jin, Q.
  • OBELISK-Net: fewer layers to solve 3D multi-organ segmentation with sparse deformable convolutions
    Heinrich, M.; Oktay, O.; Bouteldja, N.
  • Generative adversarial networks in brain imaging: a narrative review
    Laino, M. E.
  • Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks
    Subramaniam, P.
  • Vessel tortuosity and brain tumor malignancy: a blinded study
    Bullitt, E.
  • Segmentation, registration and analysis of tubular structures in images
    Tube, T. K.
  • SPM12
    Friston, K.
  • SimpleElastix: a user-friendly, multi-lingual library for medical image registration
    Marstal, K.
  • The inner diameter of arteries of the circle of Willis regarding gender and age on MRA
    Mujagic, S.
  • Anatomical attention guided deep networks for ROI segmentation of brain MR images
    Sun, L.
  • SegAN: adversarial network with multi-scale L1 loss for medical image segmentation
    Xue, Y.
  • Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations
    Sudre, C.
  • clDice: a topology-preserving loss function for tubular structure segmentation
    Shit, S.
  • Cerebrovascular network segmentation on MRA images with deep learning
    Sanches, P.