Automatic Quantitative Coronary Analysis Based on Deep Learning

Liu, Xuqing; Wang, Xiaofei; Chen, Donghao; Zhang, Honggang

doi:10.3390/app13052975

Cited by 7 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the fact that the manual approach for quantitatively assessing the stenosis severity of coronary arteries is very tedious and is subject to the experience of cardiologists; therefore, developing automatic quantitative coronary analysis (QCA) is crucial. In order to address this concern, Liu et al [ 35 ] proposed the application of artificial-intelligent-based QCA also known as AI-QCA for the accurate and fast quantitative assessment of the severity of stenosis. The framework is designed according to three main units which include the boundary-aware segmentation on the coronary angiogram (CAG) images followed by the construction of the coronary artery tree which is enabled by AI and lastly the diameter fitting and detection of stenosis.…”

Section: Introductionmentioning

confidence: 99%

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

Kaba¹,

Hacı²,

Işın

et al. 2023

Diagnostics

View full text Add to dashboard Cite

In recent years, the prevalence of coronary artery disease (CAD) has become one of the leading causes of death around the world. Accurate stenosis detection of coronary arteries is crucial for timely treatment. Cardiologists use visual estimations when reading coronary angiography images to diagnose stenosis. As a result, they face various challenges which include high workloads, long processing times and human error. Computer-aided segmentation and classification of coronary arteries, as to whether stenosis is present or not, significantly reduces the workload of cardiologists and human errors caused by manual processes. Moreover, deep learning techniques have been shown to aid medical experts in diagnosing diseases using biomedical imaging. Thus, this study proposes the use of automatic segmentation of coronary arteries using U-Net, ResUNet-a, UNet++, models and classification using DenseNet201, EfficientNet-B0, Mobilenet-v2, ResNet101 and Xception models. In the case of segmentation, the comparative analysis of the three models has shown that U-Net achieved the highest score with a 0.8467 Dice score and 0.7454 Jaccard Index in comparison with UNet++ and ResUnet-a. Evaluation of the classification model’s performances has shown that DenseNet201 performed better than other pretrained models with 0.9000 accuracy, 0.9833 specificity, 0.9556 PPV, 0.7746 Cohen’s Kappa and 0.9694 Area Under the Curve (AUC).

show abstract

Section: Introductionmentioning

confidence: 99%

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

Kaba¹,

Hacı²,

Işın

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Zhao et al [ 8 ] classified the lesions by performing image segmentation of the vessel centerline, calculating vessel diameters, and measuring the degree of stenoses. Liu et al [ 9 ] performed vessel boundary-aware segmentation, branch node localization, coronary artery tree construction, and vessel diameter fitting, and ultimately accomplished stenosis detection. Algarni et al [ 10 ] employed image noise removal, contrast enhancement, and Otsu thresholding as pre-processing techniques and used attention-based nested U-Net and VGG-16 for vessel segmentation and lesion detection.…”

Section: Introductionmentioning

confidence: 99%

One-Stage Detection without Segmentation for Multi-Type Coronary Lesions in Angiography Images Using Deep Learning

Wu,

Zhao,

et al. 2023

Diagnostics

View full text Add to dashboard Cite

It is rare to use the one-stage model without segmentation for the automatic detection of coronary lesions. This study sequentially enrolled 200 patients with significant stenoses and occlusions of the right coronary and categorized their angiography images into two angle views: The CRA (cranial) view of 98 patients with 2453 images and the LAO (left anterior oblique) view of 176 patients with 3338 images. Randomization was performed at the patient level to the training set and test set using a 7:3 ratio. YOLOv5 was adopted as the key model for direct detection. Four types of lesions were studied: Local Stenosis (LS), Diffuse Stenosis (DS), Bifurcation Stenosis (BS), and Chronic Total Occlusion (CTO). At the image level, the precision, recall, mAP@0.1, and mAP@0.5 predicted by the model were 0.64, 0.68, 0.66, and 0.49 in the CRA view and 0.68, 0.73, 0.70, and 0.56 in the LAO view, respectively. At the patient level, the precision, recall, and F1scores predicted by the model were 0.52, 0.91, and 0.65 in the CRA view and 0.50, 0.94, and 0.64 in the LAO view, respectively. YOLOv5 performed the best for lesions of CTO and LS at both the image level and the patient level. In conclusion, the one-stage model without segmentation as YOLOv5 is feasible to be used in automatic coronary lesion detection, with the most suitable types of lesions as LS and CTO.

show abstract

“…Notwithstanding, fully automatic auto-QCA systems have been described, with reasonable correlation with state-of-the-art systems (Pearson's R = 0.765). 6 Other authors have created models capable of identifying lesions based on bounding boxes, with a percentage DS ≥70% as assessed by QCA or of any severity. 7 …”

mentioning

confidence: 99%

Old Habits Die Hard

Nobre Menezes,

Oliveira,

Silva

et al. 2024

JACC: Advances

View full text Add to dashboard Cite

Automatic Quantitative Coronary Analysis Based on Deep Learning

Cited by 7 publications

References 43 publications

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

One-Stage Detection without Segmentation for Multi-Type Coronary Lesions in Angiography Images Using Deep Learning

Old Habits Die Hard

Contact Info

Product

Resources

About