Automatic extraction and stenosis evaluation of coronary arteries in invasive coronary angiograms

Zhao, Chen; Vij, Aviral; Malhotra, Saurabh; Tang, Jian; Tang, Haipeng; Pienta, Drew; Xu, Zhihui; Zhou, Weihua

doi:10.1016/j.compbiomed.2021.104667

Cited by 67 publications

(26 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Internal validation of CNN performance on 1000 ICA images demonstrated F1 scores between 0.80 and 0.85. Other studies performed classification on the degree of stenosis (mild, moderate, severe), or elements of SYNTAX, such as the presence and type (blunt/tapered stump) of total occlusion with moderate to good results (Table 1) [42][43][44].…”

Section: Lesion Detection Localization and Classificationmentioning

confidence: 99%

Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease

et al. 2022

View full text Add to dashboard Cite

Purpose of Review Artificial intelligence (AI) applications in (interventional) cardiology continue to emerge. This review summarizes the current state and future perspectives of AI for automated imaging analysis in invasive coronary angiography (ICA). Recent Findings Recently, 12 studies on AI for automated imaging analysis In ICA have been published. In these studies, machine learning (ML) models have been developed for frame selection, segmentation, lesion assessment, and functional assessment of coronary flow. These ML models have been developed on monocenter datasets (in range 31–14,509 patients) and showed moderate to good performance. However, only three ML models were externally validated. Summary Given the current pace of AI developments for the analysis of ICA, less-invasive, objective, and automated diagnosis of CAD can be expected in the near future. Further research on this technology in the catheterization laboratory may assist and improve treatment allocation, risk stratification, and cath lab logistics by integrating ICA analysis with other clinical characteristics.

show abstract

Section: Lesion Detection Localization and Classificationmentioning

confidence: 99%

Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In U-Net++, the skip connections are modified by using nested and dense connections [15]. In our latest paper [9], the multi-scale technique is improved by feature pyramids, which are built upon image pyramids and form a fundamental solution for utilizing features from different scales. To leverage the pyramid features of the hierarchy decoder in U-Net++, we resize the feature maps extracted from different layers and integrate them to generate the final feature map.…”

Section: Artery Tree Segmentationmentioning

confidence: 99%

“…where 𝑦 is the ground truth for one pixel of the ICA and 𝑦 ̂ is the model prediction. Our artery tree segmentation model achieved an average Dice score of 0.8899 [9]. Results from this binary segmentation model are used to generate the vascular centerline for coronary artery segment separation and semantic labeling.…”

Section: Artery Tree Segmentationmentioning

confidence: 99%

“…The AngioNet employed the DeepLabV3+ network as the backend for coronary artery segmentation and achieved a Dice score of 0.864 [8]. Our recent published network [9], feature pyramid U-Net++, was developed based on U-Net++ and integrated the feature pyramids to capture feature maps from different scales; the proposed network achieved a Dice score of 0.8899 on our dataset with 314 annotated coronary arteries.…”

Section: Introductionmentioning

confidence: 99%

“…The focus of this work is on the classification of the major and branch arterial segments into LMA, LAD, LCX, diagonal branch (D1), obtuse marginal branch (OM1), and ramus intermedius branch (RI). We first extract the entire vascular tree from the ICAs using our previously designed feature pyramid U-Net++ (FP-U-Net++) [9]. After that, we generate the centerline of the whole vascular tree and find the key points to generate the vessel graph.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Semantic Segmentation to Extract Coronary Arteries in Invasive Coronary Angiograms

Zhao

Bober

Tang

et al. 2022

J. Adv. App. Comput. Math.

Self Cite

View full text Add to dashboard Cite

Accurate semantic segmentation of each coronary artery using invasive coronary angiography (ICA) is important for stenosis assessment and coronary artery disease (CAD) diagnosis. In this paper, we propose a multi-step semantic segmentation algorithm based on analyzing arterial segments extracted from ICAs. The proposed algorithm firstly extracts the entire arterial binary mask (binary vascular tree) using a deep learning-based method. Then we extract the centerline of the binary vascular tree and separate it into different arterial segments. Finally, by extracting the underlying arterial topology, position, and pixel features, we construct a powerful coronary artery segment classifier based on a support vector machine. Each arterial segment is classified into the left coronary artery (LCA), left anterior descending (LAD), and other types of arterial segments. The proposed method was tested on a dataset with 225 ICAs and achieved a mean accuracy of 70.33% for the multi-class artery classification and a mean intersection over union of 0.6868 for semantic segmentation of arteries. The experimental results show the effectiveness of the proposed algorithm, which provides impressive performance for analyzing the individual arteries in ICAs.

show abstract

LightAWNet: Lightweight adaptive weighting network based on dynamic convolutions for medical image segmentation

Wang,

Yu,

Zhang

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

PurposeThe complexity of convolutional neural networks (CNNs) can lead to improved segmentation accuracy in medical image analysis but also results in increased network complexity and training challenges, especially under resource limitations. Conversely, lightweight models offer efficiency but often sacrifice accuracy. This paper addresses the challenge of balancing efficiency and accuracy by proposing LightAWNet, a lightweight adaptive weighting neural network for medical image segmentation.MethodsWe designed LightAWNet with an efficient inverted bottleneck encoder block optimized by spatial attention. A two‐branch strategy is employed to separately extract detailed and spatial features for fusion, enhancing the reusability of model feature maps. Additionally, a lightweight optimized up‐sampling operation replaces traditional transposed convolution, and channel attention is utilized in the decoder to produce more accurate outputs efficiently.ResultsExperimental results on the LiTS2017, MM‐WHS, ISIC2018, and Kvasir‐SEG datasets demonstrate that LightAWNet achieves state‐of‐the‐art performance with only 2.83 million parameters. Our model significantly outperforms existing methods in terms of segmentation accuracy, highlighting its effectiveness in maintaining high performance with reduced complexity.ConclusionsLightAWNet successfully balances efficiency and accuracy in medical image segmentation. The innovative use of spatial attention, dual‐branch feature extraction, and optimized up‐sampling operations contribute to its superior performance. These findings offer valuable insights for the development of resource‐efficient yet highly accurate segmentation models in medical imaging. The code will be made available at https://github.com/zjmiaprojects/lightawnet upon acceptance for publication.

show abstract

Automatic extraction and stenosis evaluation of coronary arteries in invasive coronary angiograms

Cited by 67 publications

References 18 publications

Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease

Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease

Semantic Segmentation to Extract Coronary Arteries in Invasive Coronary Angiograms

LightAWNet: Lightweight adaptive weighting network based on dynamic convolutions for medical image segmentation

Contact Info

Product

Resources

About