Stenosis Detection in X-ray Coronary Angiography with Deep Neural Networks Leveraged by Attention Mechanisms
See where this sits in the topic map →Summary AI-generated
- TL;DR
- This research evaluates deep learning-based object detection methods to automatically identify coronary artery stenosis in X-ray angiographies, aiding in the diagnosis of coronary heart disease.
- Problem
- Coronary artery disease is caused by atherosclerotic plaques that narrow the coronary arteries and make the heart work harder, risking failure. Automatic detection of this stenosis is important for diagnosis, but clinically challenging.
- Method
- The study trained and tested three object detectors leveraging attention mechanisms—EfficientDet, RetinaNet ResNet-50-FPN, and Faster R-CNN ResNet-101—using clinical angiography data from 438 patients.
- Results
- EfficientDet outperformed the alternative approaches, achieving a mean average precision of 0.67 in detecting stenosis in X-ray angiographies.
- Contributions
- Not specified in the abstract.
- Limitations
- Not specified in the abstract.
- Takeaways
- The findings demonstrate that attention mechanisms improve the performance of convolutional neural networks in medical imaging tasks.
- Applications
- Automated identification of stenosis can serve as a triage tool or a second reader in clinical practice, assisting cardiologists.
- Topics
- Stenosis Detection; X-ray Coronary Angiography; Deep Learning; Attention Mechanisms
- For industry
- Healthcare and clinical decision support.
- Why it matters
- Advances automated medical imaging tools that could assist cardiologists and improve clinical workflows for heart disease diagnosis.
Abstract
Coronary artery disease (CAD) is one of the most prevalent causes of death worldwide. The automatic detection of coronary artery stenosis on X-ray images is important in coronary heart disease diagnosis. Coronary artery disease is caused by atherosclerotic plaques with subsequent stenosis (e.g. narrowing) of the coronary arteries. This makes the heart work harder, risking failure. Automated identification of stenosis may be used for triage or as a second reader in clinical practice, providing a valuable tool for cardiologists. In this paper, we evaluate the detection of stenosis in X-ray coronary angiography images with novel object detection methods based on deep neural networks. We trained and tested three promising object detectors based on different neural network architectures leveraging attention mechanisms (EfficientDet, RetinaNet ResNet-50- FPN, and Faster R-CNN ResNet-101) using clinical angiography data of 438 patients. The metrics obtained on this dataset, have shown an advantage of EfficientDet over alternative approaches, achieving a mean average precision of 0.67 in the task of detecting stenosis in X-Ray angiographies. This result provides evidence that attention mechanisms improve the performance of convolutional neural networks in a medical imaging context.