Automatic coronary artery segmentation and diagnosis of stenosis by deep learning based on computed tomographic coronary angiography

Li, Yiming; Wu, Yu; He, Jingjing; Jiang, Weili; Wang, Jianyong; Peng, Yong; Jia, Yixin; Xiong, Tian-Yuan; Jia, Kaiyu; Zhang, Yi; Chen, Mao

doi:10.1007/s00330-022-08761-z

Cited by 15 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tables 4 and 5 show that the Bannerjee et al model produces low accuracy and F1-measure. The proposed model achieved a better outcome than the recent image classification [11][12][13][14][15][16][17][18]. The feature extraction technique supplied the practical features to support the proposed model and generate better insights from the CCTA images.…”

Section: Discussionmentioning

confidence: 93%

See 1 more Smart Citation

Developing a Deep-Learning-Based Coronary Artery Disease Detection Technique Using Computer Tomography Images

Sait

Dutta

2023

Diagnostics

View full text Add to dashboard Cite

Coronary artery disease (CAD) is one of the major causes of fatalities across the globe. The recent developments in convolutional neural networks (CNN) allow researchers to detect CAD from computed tomography (CT) images. The CAD detection model assists physicians in identifying cardiac disease at earlier stages. The recent CAD detection models demand a high computational cost and a more significant number of images. Therefore, this study intends to develop a CNN-based CAD detection model. The researchers apply an image enhancement technique to improve the CT image quality. The authors employed You look only once (YOLO) V7 for extracting the features. Aquila optimization is used for optimizing the hyperparameters of the UNet++ model to predict CAD. The proposed feature extraction technique and hyperparameter tuning approach reduces the computational costs and improves the performance of the UNet++ model. Two datasets are utilized for evaluating the performance of the proposed CAD detection model. The experimental outcomes suggest that the proposed method achieves an accuracy, recall, precision, F1-score, Matthews correlation coefficient, and Kappa of 99.4, 98.5, 98.65, 98.6, 95.35, and 95 and 99.5, 98.95, 98.95, 98.95, 96.35, and 96.25 for datasets 1 and 2, respectively. In addition, the proposed model outperforms the recent techniques by obtaining the area under the receiver operating characteristic and precision-recall curve of 0.97 and 0.95, and 0.96 and 0.94 for datasets 1 and 2, respectively. Moreover, the proposed model obtained a better confidence interval and standard deviation of [98.64–98.72] and 0.0014, and [97.41–97.49] and 0.0019 for datasets 1 and 2, respectively. The study’s findings suggest that the proposed model can support physicians in identifying CAD with limited resources.

show abstract

Section: Discussionmentioning

confidence: 93%

“…Both economically developed and underdeveloped nations are experiencing significant surges in the number of deaths from CVD [ 10 ]. Early CAD identification can save lives and lower healthcare costs [ 11 , 12 , 13 , 14 , 15 , 16 ]. Developing a reliable and non-invasive approach for early CAD identification is desirable.…”

Section: Introductionmentioning

confidence: 99%

Developing a Deep-Learning-Based Coronary Artery Disease Detection Technique Using Computer Tomography Images

Sait

Dutta

2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…For automatic coronary artery segmentation using CCTA, a 3D attention fully convolution network (FCN) was developed by Lei et al [23]. From the CCTA image, the end-to-end coronary artery segmentation was performed using FCN.…”

Section: Related Prior Workmentioning

confidence: 99%

Efficient Hybrid Deep Learning Network Model for Segmentation and Classification of Heart Angiographic Images

Devi,

Ramaswami

2024

Nano Biomedicine and Engineering

View full text Add to dashboard Cite

Heart angiography is a test that allows the treating physician to identify heart vessel abnormalities. The concerned doctor must spend a lot of time on this diagnosis. The heart vessels' targeted areas are segmented, and the blood vessel types are classified in the proposed approach. The heart angiography segmentation and classification provide essential information for the patient and the doctor. In contrast, the charge for cardiac angiography is a risky, mentally challenging task for the doctor (a heart specialist). Improved transparency and faster detection of heart diseases can result from automated segmentation and categorization of representations of heart blood vessels. Since accuracy is critical in classification, computer vision researchers are introducing several techniques; however, achieving high accuracy remains challenging when classifying heart diseases. This research proposes a multi-class ensemble classification mechanism-based computer-aided hybrid deep learning (DL) network model for localizing human blood vessels inside heart coronary computed tomography (CT) angiography images. First, the modified U-Net model is used to segment the heart blood vessels, and the self-attention network (SAT-Net) model is used to extract various features from the segmented blood vessel images. In segmented human heart blood vessels, low-level features are retrieved, including geometrical, statistical, and texture features. The enhanced elman spike neural network (EESNN) model has been used to finally classify cardiac blood vessels into four distinct groups: blood flow-reduced, narrow, block, and regular vessels. The suggested strategy has produced the best results, creating a conducive environment for cardiologists to diagnose heart-related disorders that is quick, simple, accurate, and time-saving.

show abstract

“…Several methods are available for coronary segmentation; however, they require manual segmentation processes to generate an accurate 3D model of coronary arteries, which induces intra- and inter- observer variability [ 11 – 13 ]. To overcome laborious manual segmentation processes, several CCTA studies recently utilized deep learning algorithms, particularly concerning coronary artery segmentation [ 14 – 16 ].…”

Section: Introductionmentioning

confidence: 99%

A comparative analysis of deep learning-based location-adaptive threshold method software against other commercially available software

Park,

Jeong

et al. 2024

Int J Cardiovasc Imaging

View full text Add to dashboard Cite

Automatic segmentation of the coronary artery using coronary computed tomography angiography (CCTA) images can facilitate several analyses related to coronary artery disease (CAD). Accurate segmentation of the lumen or plaque region is one of the most important factors. This study aimed to analyze the performance of the coronary artery segmentation of a software platform with a deep learning-based location-adaptive threshold method (DL-LATM) against commercially available software platforms using CCTA. The dataset from intravascular ultrasound (IVUS) of 26 vessel segments from 19 patients was used as the gold standard to evaluate the performance of each software platform. Statistical analyses (Pearson correlation coefficient [PCC], intraclass correlation coefficient [ICC], and Bland-Altman plot) were conducted for the lumen or plaque parameters by comparing the dataset of each software platform with IVUS. The software platform with DL-LATM showed the bias closest to zero for detecting lumen volume (mean difference = -9.1 mm3, 95% confidence interval [CI] = -18.6 to 0.4 mm3) or area (mean difference = -0.72 mm2, 95% CI = -0.80 to -0.64 mm2) with the highest PCC and ICC. Moreover, lumen or plaque area in the stenotic region was analyzed. The software platform with DL-LATM showed the bias closest to zero for detecting lumen (mean difference = -0.07 mm2, 95% CI = -0.16 to 0.02 mm2) or plaque area (mean difference = 1.70 mm2, 95% CI = 1.37 to 2.03 mm2) in the stenotic region with significantly higher correlation coefficient than other commercially available software platforms (p < 0.001). The result shows that the software platform with DL-LATM has the potential to serve as an aiding system for CAD evaluation.

show abstract

Automatic coronary artery segmentation and diagnosis of stenosis by deep learning based on computed tomographic coronary angiography

Cited by 15 publications

References 21 publications

Developing a Deep-Learning-Based Coronary Artery Disease Detection Technique Using Computer Tomography Images

Developing a Deep-Learning-Based Coronary Artery Disease Detection Technique Using Computer Tomography Images

Efficient Hybrid Deep Learning Network Model for Segmentation and Classification of Heart Angiographic Images

A comparative analysis of deep learning-based location-adaptive threshold method software against other commercially available software

Contact Info

Product

Resources

About