You are here
Echo Doppler Flow Classification and Goodness Assessment with Convolutional Neural Networks.
Doppler Echocardiography is critical for measuring abnormal cardiac function and diagnosing valvular stenosis and regurgitation. The current practice for assessing and interpreting Doppler echo images is time-consuming and depends highly on the experience of the operator. The limitations of this practice canbe mitigatedusing fullyautomatedintelligent systems.Essential ﬁrst steps toward comprehensive computer-assisted Doppler echocardiographic interpretation include automatic classiﬁcation into view/ﬂow categories and goodness assessment of these ﬂows. In this paper, we propose a deep learning-based method for Doppler ﬂow classiﬁcation and goodness assessment. The method has been trained on labeled images representing a wide range of real-world clinical variation. Our method, when evaluated on unseen data, achieved overall accuracies of 91.6% and 88.9% for ﬂow classiﬁcation and goodness assessment, respectively. While further research is needed, these results are encouraging and prove the feasibility of using fully automated intelligent systems for analyzing and interpreting Doppler echo images.