Phase Unwrapping of Color Doppler Echocardiography using Deep Learning

• Published in: IEEE transactions on ultrasonics, ferroelectrics, and frequency control Vol. 70; no. 8; p. 1
• Main Authors: Ling, Hang Jung, Bernard, Olivier, Ducros, Nicolas, Garcia, Damien
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-08-2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Aliasing; Artificial Intelligence; Blood flow; Cardiology and cardiovascular system; Color; Color Doppler; Computer Science; Dealiasing; Deep learning; Deep unfolding; Doppler effect; Echocardiography; Flow imaging; Human health and pathology; Image color analysis; Image segmentation; Imaging; Inverse problems; Life Sciences; Machine Learning; Medical Imaging; Phase unwrapping; Primal-dual; Quantitative analysis; Transformer; Transformers; U-Net; Wrapping; Deep learning; Phase unwrapping; Transformer; Echocardiography; Color Doppler; U-Net; Primal-dual; Flow imaging; Deep unfolding; Dealiasing
• ISSN: 0885-3010; 1525-8955
• DOI: 10.1109/TUFFC.2023.3289621

Color Doppler echocardiography is a widely used non-invasive imaging modality that provides real-time information about the intracardiac blood flow. In an apical long-axis view of the left ventricle, color Doppler is subject to phase wrapping, or aliasing, especially during cardiac filling and ejection. When setting up quantitative methods based on color Doppler, it is necessary to correct this wrapping artifact. We developed an unfolded primal-dual network to unwrap (dealias) color Doppler echocardiographic images and compared its effectiveness against two state-of-the-art segmentation approaches based on nnU-Net and transformer models. We trained and evaluated the performance of each method on an in-house dataset and found that the nnU-Net-based method provided the best dealiased results, followed by the primal-dual approach and the transformer-based technique. Noteworthy, the primal-dual network, which had significantly fewer trainable parameters, performed competitively with respect to the other two methods, demonstrating the high potential of deep unfolding methods. Our results suggest that deep learning-based methods can effectively remove aliasing artifacts in color Doppler echocardiographic images, outperforming DeAN, a state-of-the-art semi-automatic technique. Overall, our results show that deep learning-based methods have the potential to effectively preprocess color Doppler images for downstream quantitative analysis.