Coronary artery segmentation in angiographic videos utilizing spatial-temporal information

Wang, Lu; Liang, Dongxue; Yin, Xiaolei; Qiu, Jing; Yang, Zhiyun; Xing, Junhui; Dong, Jianzeng; Ma, Zhaoyuan

doi:10.1186/s12880-020-00509-9

Cited by 20 publications

(22 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently updated deep learning studies for the segmentation of the entire coronary tree exhibited DSCs of 86.4% –88% using a dataset of <1,000 patients (Iyer et al, 2021; Zhao et al, 2018). Despite the detailed capture of vascular structures, entire vessel segmentation could suffer from small branches (Wang et al, 2020). Because the segmentation criteria and the database may vary between studies (Iyer et al, 2021; Wang et al, 2020; Zhao et al, 2018), the interpretation of evaluation metrics should be made with careful consideration.…”

Section: Discussionmentioning

confidence: 99%

“…Despite the detailed capture of vascular structures, entire vessel segmentation could suffer from small branches (Wang et al, 2020). Because the segmentation criteria and the database may vary between studies (Iyer et al, 2021; Wang et al, 2020; Zhao et al, 2018), the interpretation of evaluation metrics should be made with careful consideration.…”

Section: Discussionmentioning

confidence: 99%

“…Real-time segmentation to capture the dynamic motion of coronary arteries could be performed using one-shot video object segmentation (Zhao et al, 2018). Recently, multi-view approaches using ICA sequences have been actively conducted (Liang et al, 2020; Wan et al, 2021; Wang et al, 2020). In a study by Zhang et al (2020), discriminative information on the ICA images acquired from different projection angles was trained by adopting intra-view hierarchical attentive blocks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

Park

Kweon

Bark

et al. 2021

Preprint

View full text Add to dashboard Cite

Invasive coronary angiography is a primary imaging modality that visualizes the lumen area of coronary arteries for the diagnosis of coronary artery diseases and guidance for interventional devices. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction; this limits their application in the catheterization room. For a more automated QCA, it is necessary to minimize operator intervention through robust segmentation methods with improved predictability. In this study, we introduced two selective ensemble methods that integrated the weighted ensemble approach with per-image quality estimation. In our selective ensemble methods, the segmentation outcomes from five base models with different loss functions were ranked by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranking. The ranking criteria based on mask morphology were determined empirically to avoid frequent types of segmentation errors, whereas the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner. In the assessment with 7,426 frames from 2,924 patients, the selective ensemble methods improved segmentation performance with DSCs of up to 93.11\% and provided a better delineation of lumen boundaries near the coronary lesion with local DSCs of up to 94.04\%, outperforming all individual models and hard voting ensembles. The probability of mask disconnection at the most narrowed region could be minimized to <1\%. The robustness of the proposed methods was evident in the external validation. Inference time for major vessel segmentation was approximately one-third, indicating that our selective ensemble methods may allow the real-time application of QCA-based diagnostic methods in routine clinical settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

Park

Kweon

Bark

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Fan et al [ 47 ] modified U-Net so that the proposed structure can receive both the target and registered background images before dye release as inputs for generating segmentation masks. The network structure proposed by [ 48 ] receives multi-channel inputs by adding a 3D convolution layer to the U-Net encoder, exploiting the temporal information using three consecutive frames from angiographic image sequences to produce a segmentation mask for the middle frame. Zhu et al [ 49 ] applied the Pyramid Scene Parsing Network, a network proposed by [ 50 ], for coronary vessel segmentation.…”

Section: Introductionmentioning

confidence: 99%

Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background Automated segmentation of coronary arteries is a crucial step for computer-aided coronary artery disease (CAD) diagnosis and treatment planning. Correct delineation of the coronary artery is challenging in X-ray coronary angiography (XCA) due to the low signal-to-noise ratio and confounding background structures. Methods A novel ensemble framework for coronary artery segmentation in XCA images is proposed, which utilizes deep learning and filter-based features to construct models using the gradient boosting decision tree (GBDT) and deep forest classifiers. The proposed method was trained and tested on 130 XCA images. For each pixel of interest in the XCA images, a 37-dimensional feature vector was constructed based on (1) the statistics of multi-scale filtering responses in the morphological, spatial, and frequency domains; and (2) the feature maps obtained from trained deep neural networks. The performance of these models was compared with those of common deep neural networks on metrics including precision, sensitivity, specificity, F1 score, AUROC (the area under the receiver operating characteristic curve), and IoU (intersection over union). Results With hybrid under-sampling methods, the best performing GBDT model achieved a mean F1 score of 0.874, AUROC of 0.947, sensitivity of 0.902, and specificity of 0.992; while the best performing deep forest model obtained a mean F1 score of 0.867, AUROC of 0.95, sensitivity of 0.867, and specificity of 0.993. Compared with the evaluated deep neural networks, both models had better or comparable performance for all evaluated metrics with lower standard deviations over the test images. Conclusions The proposed feature-based ensemble method outperformed common deep convolutional neural networks in most performance metrics while yielding more consistent results. Such a method can be used to facilitate the assessment of stenosis and improve the quality of care in patients with CAD.

show abstract

“…Furthermore, in 3D BVS, there are many kinds of research using U-Net as the baseline. First, there are approaches using the 2D U-Net family which processes a single plane image at a time [11,12]. Although it is generally applied to 2D BVS regarding optical imaging modalities (e.g., color fundus photography, fluorescein angiography), there is a report that 2D U-Net outperforms the graph cut method-a representative traditional image segmentation method-when segmenting intracranial artery [11].…”

Section: Introductionmentioning

confidence: 99%

Spider U-Net: Incorporating Inter-Slice Connectivity Using LSTM for 3D Blood Vessel Segmentation

et al. 2021

View full text Add to dashboard Cite

Blood vessel segmentation (BVS) of 3D medical imaging such as computed tomography and magnetic resonance angiography (MRA) is an essential task in the clinical field. Automation of 3D BVS using deep supervised learning is being researched, and U-Net-based approaches, which are considered as standard for medical image segmentation, are proposed a lot. However, the inherent characteristics of blood vessels, e.g., they are complex and narrow, as well as the resolution and sensitivity of the imaging modalities increases the difficulty of 3D BVS. We propose a novel U-Net-based model named Spider U-Net for 3D BVS that considers the connectivity of the blood vessels between the axial slices. To achieve this, long short-term memory (LSTM), which can capture the context of the consecutive data, is inserted into the baseline model. We also propose a data feeding strategy that augments data and makes Spider U-Net stable. Spider U-Net outperformed 2D U-Net, 3D U-Net, and the fully convolutional network-recurrent neural network (FCN-RNN) in dice coefficient score (DSC) by 0.048, 0.077, and 0.041, respectively, for our in-house brain MRA dataset and also achieved the highest DSC for two public datasets. The results imply that considering inter-slice connectivity with LSTM improves model performance in the 3D BVS task.

show abstract

Coronary artery segmentation in angiographic videos utilizing spatial-temporal information

Cited by 20 publications

References 24 publications

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features

Spider U-Net: Incorporating Inter-Slice Connectivity Using LSTM for 3D Blood Vessel Segmentation

Contact Info

Product

Resources

About