Computational fluid dynamics based hemodynamics in the management of intracranial aneurysms: state-of-the-art

Hu, Bin; Shi, Zhengyi; Schoepf, U. Joseph; Varga-Szemes, Ákos; Few, W. Evans; Zhang, Long Jiang

doi:10.1007/s42058-021-00081-3

Cited by 1 publication

(2 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies have shown that morphological metrics derived based on 3D information are more accurate and consistent than 2D manual measurement ( Ma et al, 2004 ; Ryu et al, 2011 ; Rajabzadeh-Oghaz et al, 2018 ). However, recent studies have revealed that the morphology metrics alone may not be sufficient for predicting the rupture risks of IA, especially in small unruptured IAs ( Abboud et al, 2017 ; Korja et al, 2017 ; Longo et al, 2017 ; Hu et al, 2021 ; Ren et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

“…In addition to morphological evaluation, hemodynamics’ role in IA rupture has drawn growing attention. Imaging-based patient-specific computational fluid dynamics (CFD) simulations have been regarded as a powerful tool for investigating the hemodynamics in the IAs ( Xiang et al, 2011 ; Takao et al, 2012 ; Liang et al, 2016 ; Xu et al, 2018 ; Zhu et al, 2019a ; Medero et al, 2020 ; Hu et al, 2021 ; Le, 2021 ; Li et al, 2022 ). Several quantitative hemodynamics metrics, such as average wall shear stress (WSS), maximum intra-aneurysmal WSS, low WSS area, average oscillatory shear index, and relative resident time, were identified to play a vital role in the pathologies of IA rupture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based recognition and segmentation of intracranial aneurysms under small sample size

et al. 2022

View full text Add to dashboard Cite

The manual identification and segmentation of intracranial aneurysms (IAs) involved in the 3D reconstruction procedure are labor-intensive and prone to human errors. To meet the demands for routine clinical management and large cohort studies of IAs, fast and accurate patient-specific IA reconstruction becomes a research Frontier. In this study, a deep-learning-based framework for IA identification and segmentation was developed, and the impacts of image pre-processing and convolutional neural network (CNN) architectures on the framework’s performance were investigated. Three-dimensional (3D) segmentation-dedicated architectures, including 3D UNet, VNet, and 3D Res-UNet were evaluated. The dataset used in this study included 101 sets of anonymized cranial computed tomography angiography (CTA) images with 140 IA cases. After the labeling and image pre-processing, a training set and test set containing 112 and 28 IA lesions were used to train and evaluate the convolutional neural network mentioned above. The performances of three convolutional neural networks were compared in terms of training performance, segmentation performance, and segmentation efficiency using multiple quantitative metrics. All the convolutional neural networks showed a non-zero voxel-wise recall (V-Recall) at the case level. Among them, 3D UNet exhibited a better overall segmentation performance under the relatively small sample size. The automatic segmentation results based on 3D UNet reached an average V-Recall of 0.797 ± 0.140 (3.5% and 17.3% higher than that of VNet and 3D Res-UNet), as well as an average dice similarity coefficient (DSC) of 0.818 ± 0.100, which was 4.1%, and 11.7% higher than VNet and 3D Res-UNet. Moreover, the average Hausdorff distance (HD) of the 3D UNet was 3.323 ± 3.212 voxels, which was 8.3% and 17.3% lower than that of VNet and 3D Res-UNet. The three-dimensional deviation analysis results also showed that the segmentations of 3D UNet had the smallest deviation with a max distance of +1.4760/−2.3854 mm, an average distance of 0.3480 mm, a standard deviation (STD) of 0.5978 mm, a root mean square (RMS) of 0.7269 mm. In addition, the average segmentation time (AST) of the 3D UNet was 0.053s, equal to that of 3D Res-UNet and 8.62% shorter than VNet. The results from this study suggested that the proposed deep learning framework integrated with 3D UNet can provide fast and accurate IA identification and segmentation.

show abstract