Automatic artery/vein classification in 2D-DSA images of stroke patients

Asperen, Vivian van; Berg, Josefien van den; Lycklama, Fleur; Marting, Victoria; Cornelissen, Sandra; Zwam, Wim van; Hofmeijer, Jeanette; Lugt, Aad van der; Walsum, Theo van; Sluijs, Matthijs van der; Su, Ruisheng

doi:10.1117/12.2606412

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frangi+K-means Traditional methods can be applied to this task. In this work, we implemented a recently proposed conventional two-step artery-vein classification method which combines Frangi filter and K-means unsupervised learning [1]. First, Frangi filter is applied on the static minimum intensity map (MinIP) of an input DSA series, followed by fixed thresholding to obtain a binary vessel mask.…”

Section: Baseline Methodsmentioning

confidence: 99%

Spatio-Temporal U-Net for Cerebral Artery and Vein Segmentation in Digital Subtraction Angiography

Su¹,

Sluijs²,

Cornelissen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

X-ray digital subtraction angiography (DSA) is widely used for vessel and/or flow visualization and interventional guidance during endovascular treatment of patients with a stroke or aneurysm. To assist in peri-operative decision making as well as post-operative prognosis, automatic DSA analysis algorithms are being developed to obtain relevant image-based information. Such analyses include detection of vascular disease, evaluation of perfusion based on time intensity curves (TIC), and quantitative biomarker extraction for automated treatment evaluation in endovascular thrombectomy. Methodologically, such vessel-based analysis tasks may be facilitated by automatic and accurate artery-vein segmentation algorithms. The present work describes to the best of our knowledge the first study that addresses automatic artery-vein segmentation in DSA using deep learning. We propose a novel spatio-temporal U-Net (ST U-Net) architecture which integrates convolutional gated recurrent units (ConvGRU) in the contracting branch of U-Net. The network encodes a 2D+t DSA series of variable length and decodes it into a 2D segmentation image. On a multi-center routinely acquired dataset, the proposed method significantly outperformed U-Net (P<0.001) and traditional Frangi-based K-means clustering (P<0.001). Particularly in artery-vein segmentation, ST U-Net achieved a Dice coefficient of 0.794, surpassing the existing state-of-the-art methods by a margin of 12%-20%. Code will be made publicly available upon acceptance.

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Spatio-Temporal U-Net for Cerebral Artery and Vein Segmentation in Digital Subtraction Angiography

Su¹,

Sluijs²,

Cornelissen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…12 Deep learning approaches have recently been applied on DSA for intracranial aneurysm detection, 13 phase classification, 12 TICI classification, 14 vessel perforation detection, 15 image generation, [16][17][18][19] thrombus classification, 20 vessel segmentation, [21][22][23] and artery/vein separation. 24 Nevertheless, most existing studies do not quantitatively assess cerebral hemodynamics.…”

Section: Introductionmentioning

confidence: 99%

Towards quantitative digital subtraction perfusion angiography: An animal study

Sluijs

Bobi

et al. 2023

Medical Physics

Self Cite

View full text Add to dashboard Cite

Background: X-ray digital subtraction angiography (DSA) is the imaging modality for peri-procedural guidance and treatment evaluation in (neuro-) vascular interventions. Perfusion image construction from DSA, as a means of quantitatively depicting cerebral hemodynamics, has been shown feasible. However, the quantitative property of perfusion DSA has not been well studied. Purpose: To comparatively study the independence of deconvolution-based perfusion DSA with respect to varying injection protocols,as well as its sensitivity to alterations in brain conditions. Methods: We developed a deconvolution-based algorithm to compute perfusion parametric images from DSA, including cerebral blood volume (CBV DSA ), cerebral blood flow (CBF DSA ), time to maximum (Tmax), and mean transit time (MTT DSA ) and applied it to DSA sequences obtained from two swine models. We also extracted the time intensity curve (TIC)-derived parameters,that is,area under the curve (AUC), peak concentration of the curve, and the time to peak (TTP) from these sequences. Deconvolution-based parameters were quantitatively compared to TIC-derived parameters in terms of consistency upon variations in injection profile and time resolution of DSA, as well as sensitivity to alterations of cerebral condition. Results: Comparing to TIC-derived parameters, the standard deviation (SD) of deconvolution-based parameters (normalized with respect to the mean) are two to five times smaller, indicating that they are more consistent across different injection protocols and time resolutions. Upon ischemic stroke induced in a swine model, the sensitivities of deconvolution-based parameters are equal to, if not higher than, those of TIC-derived parameters. Conclusions: In comparison to TIC-derived parameters, deconvolution-based perfusion imaging in DSA shows significantly higher quantitative reliability against variations in injection protocols across different time resolutions, and is sensitive to alterations in cerebral hemodynamics. The quantitative nature of perfusion angiography may allow for objective treatment assessment in neurovascular interventions.

show abstract