Existing works for automated echocardiography view classification are designed under the assumption that the classes (views) in the testing set must be similar to those appeared in the training set (closed world classification). This assumption may be too strict for real-world environments that are open and often have unseen examples (views), thereby drastically weakening the robustness of the classical classification approaches. In this work, we developed an open world active learning approach for echocardiography view classification, where the network classifies images of known views into their respective classes and identifies images of unknown views. Then, a clustering approach is used to cluster the unknown views into various groups to be labeled by an echocardiologist. Finally, the new labeled samples are added to the initial set of known views and used to update the classification network. This process of actively labeling unknown clusters and integrating them into the classification model significantly increases the efficiency of data labeling and the robustness of the classifier. Our results using an echocardiography dataset containing known and unknown views showed the superiority of the proposed approach as compared to the closed world view classification approaches.
Doppler echocardiography is valuable for the diagnosis and management of several cardiovascular diseases. Automated analysis of Doppler images can significantly assist in decreasing the known variability of manual measurements and the burdensome of manual delineation and calculation. We propose a novel and fully automated method to detect and analyze spectral Doppler waves used for assessment of diastolic function from mitral inflow [MV] (peak E and A wave velocity), mitral annulus [MA] (peak E' and A' wave velocity), and pulmonary pressure (peak tricuspid regurgitation [TR] velocity). We used the Faster R-CNN deep learning-based method for Doppler, ECG, and anatomical ROIs localization. We then used ECG to segment Doppler signals into individual beats followed by assessing the quality of these beats using density-based method and Structural Similarity Index (SSIM). To segment the spectral envelope for each beat, we used a novel combination of k-means clustering algorithm and Gradient Vector Flow (GVF) snake algorithm. We used 701 Doppler images, collected from 100 patients acquired in the Clinical Center at the National Institutes of Health, to evaluate the performance of the proposed method against expert manual peak velocity estimation. The experimental results demonstrate the efficiency and robustness of the proposed framework in estimating peak velocity, and thus making it a viable candidate for use in clinical settings.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.