Coronary Artery Vascular Segmentation on Limited Data via Pseudo-Precise Label

Zhai, Mo; Du, Tao; Yang, Ruolin; Zhang, Honggang

doi:10.1109/embc.2019.8856682

Cited by 11 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, real-time analysis in the catheterization room could help guide and optimize the stent selection and implantation process beyond error-prone visual assessment (Shah et al, 2017). Automatic lesion detection integrated with segment identification (Zhai et al, 2019) would facilitate the diagnosis of multivessel disease with the calculation of the SYNTAX score (Cavalcante et al, 2017). Machine learning applications using lesion morphology for the prediction of fractional flow reserve could be accelerated (Cho et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

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%

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

“…The settings of the grid search are shown in Table 2. [20], [20,10], [20,20,10], [30,30,20,10], [30,20,20], [30,20,20,10] The overall workflow of the designed artery graph generation and semantic labeling algorithm is shown in Algorithm 1.…”

Section: Artery Feature Extraction and Segment Label Assignmentmentioning

confidence: 99%

“…The inter-class difference of pixel features between the arterial segments is difficult to be distinguished. Thus, the common deep learning models for nature image semantic segmentation tasks cannot achieve satisfying performance on artery semantic segmentation [10]. Xian et al proposed a robust method for main coronary artery segmentation using four fully convolutional networks [11].…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation to Extract Coronary Arteries in Invasive Coronary Angiograms

Zhao

Bober

Tang

et al. 2022

J. Adv. App. Comput. Math.

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

“…In the evaluation of segmentation results, the Dice coefficient was adopted to reflect the closeness between the result of the image pixel-level classification and the actual result, which could be expressed as (14). In the equation, Υ and ϑ represented two samples, and the result range of Dice was in [0, 1].…”

Section: Scientific Programmingmentioning

confidence: 99%

“…e segmentation of medical images belongs to the category of semantic segmentation in deep learning, which essentially classifies every pixel. In recent years, semantic segmentation has made great progress [14][15][16]. For instance, fully convolutional neural networks (FCNN) are a pioneering change.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Coronary Angiography in Diagnosis of Myocardial Ischemia

Shu

2021

Scientific Programming

View full text Add to dashboard Cite

Objective. This study was to explore the diagnostic effect of the coronary angiography (CAG) based on the fully convolutional neural network (FCNN) algorithm for patients with coronary heart disease (CHD) and suspected (not diagnosed) myocardial ischemia. Methods. In this study, 150 patients with undiagnosed CHD with myocardial ischemia in hospital were selected as the research objects. They were divided into an observation group and a control group by random number method. The patients in observation group were examined with CAG with the assistance of convolutional neural network (CNN) algorithm, while patients in the control group received conventional CAG. Results. The Dice coefficient of the segmentation effect evaluation index was 0.89, which showed that the image processing effect of the algorithm was good. There was no statistical difference in positive rates of single/double-vessel lesions between the two groups ( P > 0.05 ), and the positive rates of multivessel lesions and total lesions in the observation group were higher than those in the control group, showing statistically obvious difference ( P < 0.05 ). The examination sensitivity, specificity, accuracy, and Kappa value of the observation group were −90.9%, −60%, −82.7%, and −0.72, which were all higher in contrast to those of the control group. The proportion of positive myocardial ischemia and coronary artery stenosis (CAS) (82%) was higher than other cases (18%), and the comparison was statistically significant ( P < 0.05 ). Conclusion. CAG based on the deep learning algorithm showed a good detection effect and can better display the coronary lesions and reflect the good development prospects of deep learning technology in medical imaging.

show abstract

Coronary Artery Vascular Segmentation on Limited Data via Pseudo-Precise Label

Cited by 11 publications

References 3 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

Semantic Segmentation to Extract Coronary Arteries in Invasive Coronary Angiograms

Deep Learning Based Coronary Angiography in Diagnosis of Myocardial Ischemia

Contact Info

Product

Resources

About