Denoising Echocardiography with an Improved Diffusion Model

Echocardiography has been a crucial role in diagnosing cardiac disease. However, its effectiveness is often hindered by poor image clarity. Acoustic interference arises from multipath reflections caused by skin layers, subcutaneous fat, and intercostal muscle between the US transducer and the heart. Consequently, the appearance of noise and other artifacts presents a substantial obstacle to the accuracy of cardiac ultrasound imaging. Therefore, effective despeckling techniques are necessary to enhance the interpretability of ultrasound images and diagnostic results. Recently, diffusion approach has become a trending topic in computer vision. This paper proposes a diffusion model-based denoising method with an interpolation technique and a simple U-Net architecture to enhance ultrasound images' quality in an unsupervised manner. The proposed method generates the interim image by interpolating the initial noise-free image and its corresponding noisy image at each diffusion step. This method iteratively reduces the noise and preserves its texture to improve the quality of degraded images. The proposed approach was trained and then validated on two benchmarks. The experimental outcomes demonstrate that the proposed approach outperforms the other denoising approaches in clinically relevant qualitative and quantitative visual metrics. The source code will be made available at https://github.com/RPRO5/DiffUS.