Sequential vessel segmentation via deep channel attention network

Hao, Dongdong; Ding, Song; Qiu, Linwei; Lv, Yisong; Fei, Baowei; Zhang, Donghui; Qin, Binjie

doi:10.1016/j.neunet.2020.05.005

Cited by 45 publications

(15 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After vessel extraction, the binary vessel mask can be segmented by a traditional threshold method such as Otsu [96] to achieve a vessel segmentation result for vesssel segmentation performance evaluation. Therefore, we can evaluate the performance of vessel segmentation by comparing our method with advanced segmentation algorithms such as Frangi's [97], Coye's [98], SVS-net [93] and CS 2 -net [99]. Generally, the overall performance of all methods is consistent with and slightly better than that demonstrated in our previous work [32], since the dataset adopted in this work is refined for performance optimization, i.e., the violently disturbed frames have been removed from the training dataset used in our previous work [32].…”

Section: Comparison Methodsmentioning

confidence: 99%

“…Meanwhile, there is a great deal of feature variability between different XCA sequences acquired from heterogeneous environments. Global processing over entire XCA images may lead the neural networks to be biased in favour of majority features in different XCA sequences with class imbalance problems [93].…”

Section: Patch-recurrent Processing Strategymentioning

confidence: 99%

“…The supervised deep learning-based SVS-net [93] and CS 2 -net [99] achieve better performance. The SVS-net segments the major vessels accurately without introducing background impurity.…”

Section: Visual Evaluation Of Vessel Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Working memory inspired hierarchical video decomposition with transformative representations

Qin¹,

Mao²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Video decomposition is very important to extract moving foreground objects from complex backgrounds in computer vision, machine learning, and medical imaging, e.g., extracting moving contrast-filled vessels from the complex and noisy backgrounds of X-ray coronary angiography (XCA). However, the challenges caused by dynamic backgrounds, overlapping heterogeneous environments and complex noises still exist in video decomposition. To solve these challenges, this study is the first to introduce a flexible visual working memory model in video decomposition to provide interpretable and high-performance hierarchical deep learning architecture, integrating the transformative representations between sensory and control layers from the perspective of visual and cognitive neuroscience. Specifically, robust PCA unrolling networks acting as a structure-regularized sensor layer decompose XCA into sparse/low-rank structured representations to separate moving contrast-filled vessels from noisy and complex backgrounds. Then, patch recurrent convolutional LSTM networks with a backprojection superresolution module embody unstructured random representations of the control layer in working memory, recurrently projecting spatiotemporally decomposed nonlocal patches into orthogonal subspaces for heterogeneous vessel retrieval and interference suppression. This video decomposition architecture effectively restores the heterogeneous profiles of intensity and geometry of moving objects against the complex background interferences. Experiments show that the proposed method significantly outperforms state-of-the-art methods in accurate moving contrast-filled vessel extraction with excellent flexibility and computational efficiency.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

Section: Patch-recurrent Processing Strategymentioning

confidence: 99%

See 1 more Smart Citation

Working memory inspired hierarchical video decomposition with transformative representations

Qin¹,

Mao²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…CS-Net [8] integrates channel attention and spatial attention into U-Net for 2D and 3D vessel segmentation. Hao et.al [9] exploits contextual frames of sequential images in a sliding window centered at the current frame and equipped with a channel attention mechanism in the decoder stage. Li et.al [10] proposes an attention gate to highlight salient features that are passed through the skip connections.…”

Section: Attention Networkmentioning

confidence: 99%

Dual Attention Multiscale Network for Vessel Segmentation in Fundus Photography

Yin

Fang

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Automatic vessel structure segmentation is an essential step towards an automatic disease diagnosis system. The task is challenging due to the variance shapes and sizes of vessels across populations.Methods: A multiscale network with dual attention is proposed to segment vessels in different sizes. The network injects spatial attention module and channel attention module on feature map which size is 1 8 of the input size. The network also uses multiscale input to receive multi-level information, and the network uses the multiscale output to gain more supervision. Results: The proposed method is tested on two publicly available datasets: DRIVE and CHASEDB1. The accuracy, AUC, sensitivity, specificity on DRIVE dataset is 0.9615, 0.9866, 0.7693, and 0.9851, respectively. On the CHASEDB1 dataset, the metrics are 0.9797, 0.9895, 0.8432, and 0.9863 respectively. The ablative study further shows effectiveness for each part of the network. Conclusions: Multiscale and dual attention mechanism both improves the performance. The proposed architecture is simple and effective. The inference time is 12ms on a GPU and has potential for real-world applications. The code will be made publicly available.

show abstract

“…Deep learning-based automated ventricle segmentation methods are summarized in the research [14]. Authors [15] developed a novel encoder-decoder deep network algorithm to exploit 2D + t sequential images' contextual information in a sliding window. The encoder extracts the temporalspatial features.…”

Section: Introductionmentioning

confidence: 99%

Coronary Vessel Segmentation by Coarse-to-Fine Strategy Using U-nets

Thuy

Dat

Anh

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Each level of the coronary artery has different sizes and properties. The primary coronary arteries usually have high contrast to the background, while the secondary coronary arteries have low contrast to the background and thin structures. Furthermore, several small vessels are disconnected or broken up vascular segments. It is a challenging task to use a single model to segment all coronary artery sizes. To overcome this problem, we propose a novel segmenting method for coronary artery extraction from angiograms based on the primary and secondary coronary artery. Our method is a coarse-to-fine strategic approach for extracting coronary arteries in many different sizes. We construct the first U-net model to segment the main coronary artery extraction and build a new algorithm to determine the junctions of the main coronary artery with the secondary coronary artery. Using these junctions, we determine regions of the secondary coronary arteries (rectangular regions) for a secondary coronary artery-extracted segment with the second U-net model. The experiment result is 76.40% in terms of Dice coefficient on coronary X-ray datasets. The proposed approach presents its potential in coronary vessel segmentation.

show abstract

Sequential vessel segmentation via deep channel attention network

Cited by 45 publications

References 91 publications

Working memory inspired hierarchical video decomposition with transformative representations

Working memory inspired hierarchical video decomposition with transformative representations

Dual Attention Multiscale Network for Vessel Segmentation in Fundus Photography

Coronary Vessel Segmentation by Coarse-to-Fine Strategy Using U-nets

Contact Info

Product

Resources

About