DDNet: A Novel Network for Cerebral Artery Segmentation from MRA Images

Zhang, Yaxian; Chen, Li

doi:10.1109/cisp-bmei48845.2019.8965836

Cited by 8 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stember et al (2018) and Chen et al (2020b) proposed a U-Net architecture for the segmentation of the vessel dilations. Zhang and Chen (2019) , Dai et al (2020) , andZeng et al (2020) propose the DDNet, an RCNN, and a 2.5D architecture, respectively, all models showing improved detection statistics compared to the standard UNet. Patel et al (2020) directly compares the U-Net and DeepMedic architecture, with the latter showing slightly higher accuracy.…”

Section: Task 2: Aneurysm Segmentationmentioning

confidence: 99%

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

Ivantsits

Goubergrits

Kuhnigk

et al. 2022

Medical Image Analysis

View full text Add to dashboard Cite

Section: Task 2: Aneurysm Segmentationmentioning

confidence: 99%

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

Ivantsits

Goubergrits

Kuhnigk

et al. 2022

Medical Image Analysis

View full text Add to dashboard Cite

“…DL methods have been used in blood vessels segmentation for different human organs in various imaging modalities. [12][13][14] An additional approach that targets computational efficiency and reduction in model parameters was proposed by Zhang et al 15 This work showed improved results on several 3D model benchmarks using a dilated model. This approach, however efficient, combined uniform dilation on a nonuniformly scattered network of vessels; hence it is incompatible with this problem.…”

Section: Related Workmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

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 threedimensional (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.

show abstract

“…Kartali et al ( Kartali et al, 2018 ) compared three deep-learning approaches based on CNN and two conventional approaches for real-time emotion recognition of four basic emotions (happiness, sadness, anger, and fear) from facial images. Zhang et al proposed the Dense-Dilated Neural Network (DDNet) based on 3D UNet for the segmentation of cerebral arteries in TOF-MRA images, which got better performance than UNet, Vnet, and Uception ( Zhang and Chen, 2019 ). Zhu et al ( Zhu et al, 2019b ) compared the segmentation performance of V-NAS, 3D UNet, and VNet on the dataset of both normal organs (NIH Pancreas) and abnormal organs (MSD Lung tumors and MSD Pancreas tumors).…”

Section: Introductionmentioning

confidence: 99%

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

DDNet: A Novel Network for Cerebral Artery Segmentation from MRA Images

Cited by 8 publications

References 16 publications

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge

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

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

Contact Info

Product

Resources

About