Key result
Faster R-CNN Inception v2 achieved 98.6% accuracy for detecting the aortic valve in echocardiography, while SSD Mobilenet v2 performed better in terms of speed.
Why the study?
Echocardiogram image quality is poor compared to CT and MRI, prompting the need for automated CNN-based real-time aortic valve detection during live examinations.
Do Convolutional Neural Networks accurately detect the aortic valve in real-time echocardiography?
Do Convolutional Neural Networks accurately detect the aortic valve in real-time echocardiography?
CNN models, particularly Faster R-CNN and SSD Mobilenet v2, can accurately and rapidly detect the aortic valve in real-time echocardiography.
AI aortic valve detection feasible on echocardiography; extends computer vision applications but leaves clinical validation open.
BACKGROUND: Valvular heart disease is a serious disease leading to mortality and increasing medical care cost. The aortic valve is the most common valve affected by this disease. Doctors rely on echocardiogram for diagnosing and evaluating valvular heart disease. However, the images from echocardiogram are poor in comparison to Computerized Tomography and Magnetic Resonance Imaging scan. This study proposes the development of Convolutional Neural Networks (CNN) that can function optimally during a live echocardiographic examination for detection of the aortic valve. An automated detection system in an echocardiogram will improve the accuracy of medical diagnosis and can provide further medical analysis from the resulting detection. METHODS: Two detection architectures, Single Shot Multibox Detector (SSD) and Faster Regional based Convolutional Neural Network (R-CNN) with various feature extractors were trained on echocardiography images from 33 patients. Thereafter, the models were tested on 10 echocardiography videos. RESULTS: Faster R-CNN Inception v2 had shown the highest accuracy (98.6%) followed closely by SSD Mobilenet v2. In terms of speed, SSD Mobilenet v2 resulted in a loss of 46.81% in framesper- second (fps) during real-time detection but managed to perform better than the other neural network models. Additionally, SSD Mobilenet v2 used the least amount of Graphic Processing Unit (GPU) but the Central Processing Unit (CPU) usage was relatively similar throughout all models. CONCLUSION: Our findings provide a foundation for implementing a convolutional detection system to echocardiography for medical purposes.
No takes yet. Share an insight, caveat, or question.
Nizar et al. (2019) studied Valvular heart disease (n=33). Convolutional Neural Networks (Faster R-CNN and SSD) was evaluated on Detection accuracy. Faster R-CNN Inception v2 achieved 98.6% accuracy for detecting the aortic valve in echocardiography, while SSD Mobilenet v2 performed better in terms of speed.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: