Spatio-Temporal Constrained Online Layer Separation for Vascular Enhancement in X-Ray Angiographic Image Sequence

Song, Shuang; Du, Chenbing; Ai, Danni; Huang, Yong; Song, Hong; Wang, Yongtian; Yang, Jian

doi:10.1109/tcsvt.2019.2941659

Cited by 11 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A set of image sequences ( i.e ., X-ray) has been considered for cardiovascular enhancement ( Song et al, 2020 ). For that, the spatio-temporal constrained online layer separation (STOLS) method was presented to achieve X-ray angiogram (XRA) image sequences.…”

Section: Related Studiesmentioning

confidence: 99%

Multi-constraints based deep learning model for automated segmentation and diagnosis of coronary artery disease in X-ray angiographic images

Algarni

Al-Rezqi

Saeed

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Background The detection of coronary artery disease (CAD) from the X-ray coronary angiography is a crucial process which is hindered by various issues such as presence of noise, insufficient contrast of the input images along with the uncertainties caused by the motion due to respiration and variation of angles of vessels. Methods In this article, an Automated Segmentation and Diagnosis of Coronary Artery Disease (ASCARIS) model is proposed in order to overcome the prevailing challenges in detection of CAD from the X-ray images. Initially, the preprocessing of the input images was carried out by using the modified wiener filter for the removal of both internal and external noise pixels from the images. Then, the enhancement of contrast was carried out by utilizing the optimized maximum principal curvature to preserve the edge information thereby contributing to increasing the segmentation accuracy. Further, the binarization of enhanced images was executed by the means of OTSU thresholding. The segmentation of coronary arteries was performed by implementing the Attention-based Nested U-Net, in which the attention estimator was incorporated to overcome the difficulties caused by intersections and overlapped arteries. The increased segmentation accuracy was achieved by performing angle estimation. Finally, the VGG-16 based architecture was implemented to extract threefold features from the segmented image to perform classification of X-ray images into normal and abnormal classes. Results The experimentation of the proposed ASCARIS model was carried out in the MATLAB R2020a simulation tool and the evaluation of the proposed model was compared with several existing approaches in terms of accuracy, sensitivity, specificity, revised contrast to noise ratio, mean square error, dice coefficient, Jaccard similarity, Hausdorff distance, Peak signal-to-noise ratio (PSNR), segmentation accuracy and ROC curve. Discussion The results obtained conclude that the proposed model outperforms the existing approaches in all the evaluation metrics thereby achieving optimized classification of CAD. The proposed method removes the large number of background artifacts and obtains a better vascular structure.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Multi-constraints based deep learning model for automated segmentation and diagnosis of coronary artery disease in X-ray angiographic images

Algarni

Al-Rezqi

Saeed

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Integrating spatiotemporally-regularized representations for low-rank backgrounds and sparse foregrounds into the RPCA loss function can ensure the uniqueness of the decomposition solution with high foreground/background separation performance. Instead of applying the l 1 -norm [3], [5], [20] and l 1/2 -norm [34], [35] to globally select sparse foreground features, recent studies have investigated the structured sparsity over groups of spatiotemporally neighbouring pixels, such as graph-based regularization [36], superpixel-based clustering [5], Gaussian mixture distribution [37], [38], Markov random field constraint [39], treestructured regularization [40], kinematic regularization [41], and total variation norm [3], [35], [42], while alternative strategies have used higher-order tensor instead of matrix representation of video data for tensor RPCA (or robust tensor decomposition) [43], [44] by specifying different tensor rank definitions and corresponding low-rank regularizations to explore an intrinsic spatiotemporal structure underlying multidimensional tensor data.…”

Section: Rpca-based Foreground/background Separationmentioning

confidence: 99%

“…However, most vessel extraction algorithms are built upon grey value or tubular feature representation, which overlap with the interferences of complex noises and dynamic background artefacts. Re- cently, assuming D = L + S, where D, L, S ∈ R m×n are the original video sequence, low-rank backgrounds, and sparsely distributed foreground objects, respectively, robust principal component analysis (RPCA) [17], [18] has proven to successfully separate moving contrast-filled vessels from complex and dynamic backgrounds [3], [4], [5], [19], [20]. When only a subset of the entries of D is observed, RPCA becomes the robust low-rank matrix (or tensor) completion that has been explored to complete the background layer of the XCA sequence for accurate vessel extraction [21].…”

Section: Introductionmentioning

confidence: 99%

Working memory inspired hierarchical video decomposition with transformative representations

Qin¹,

Mao²,

Zhang³

et al. 2022

Preprint

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

“…Most 3D vessel segmentation methods exploit vessel prior knowledge as tubular structures to enhance the vessels and obtain the vesselness map (Ai et al 2016, Song et al 2019a, 2019b. One of the most classic enhancement methods was introduced by Frangi et al (1998).…”

Section: Introductionmentioning

confidence: 99%

Local-global active contour model based on tensor-based representation for 3D ultrasound vessel segmentation

Dong¹,

Ai²,

Fan³

et al. 2021

Phys. Med. Biol.

Self Cite

View full text Add to dashboard Cite

Three-dimensional (3D) vessel segmentation can provide full spatial information about an anatomic structure to help physicians gain increased understanding of vascular structures, which plays an utmost role in many medical image-processing and analysis applications. The purpose of this paper aims to develop a 3D vessel-segmentation method that can improve segmentation accuracy in 3D ultrasound (US) images. We propose a 3D tensor-based active contour model method for accurate 3D vessel segmentation. With our method, the contrast-independent multiscale bottom-hat tensor representation and local-global information are captured. This strategy ensures the effective extraction of the boundaries of vessels from inhomogeneous and homogeneous regions without being affected by the noise and low-contrast of the 3D US images. Experimental results in clinical 3D US and public 3D Multiphoton Microscopy datasets are used for quantitative and qualitative comparison with several state-of-the-art vessel segmentation methods. Clinical experiments demonstrate that our method can achieve a smoother and more accurate boundary of the vessel object than competing methods. The mean SE, SP and ACC of the proposed method are: 0.7768 ± 0.0597, 0.9978 ± 0.0013 and 0.9971 ± 0.0015 respectively. Experiments on the public dataset show that our method can segment complex vessels in different medical images with noise and low- contrast.

show abstract

Spatio-Temporal Constrained Online Layer Separation for Vascular Enhancement in X-Ray Angiographic Image Sequence

Cited by 11 publications

References 33 publications

Multi-constraints based deep learning model for automated segmentation and diagnosis of coronary artery disease in X-ray angiographic images

Multi-constraints based deep learning model for automated segmentation and diagnosis of coronary artery disease in X-ray angiographic images

Working memory inspired hierarchical video decomposition with transformative representations

Local-global active contour model based on tensor-based representation for 3D ultrasound vessel segmentation

Contact Info

Product

Resources

About