Speckle Noise Reduction in Ultrasound Images using Denoising Auto-encoder with Skip Connection

TL;DR

The effectiveness of the deep learning method, auto-encoder with skip connection, in reducing speckle noise and preserving features in ultrasound images was demonstrated, leading to improved accuracy in diagnosis.

Abstract

Ultrasound is a widely used medical tool for non-invasive diagnosis, but its images often contain speckle noise which can lower their resolution and contrast-to-noise ratio. This can make it more difficult to extract, recognize, and analyze features in the images, as well as impair the accuracy of computer-assisted diagnostic techniques and the ability of doctors to interpret the images. Reducing speckle noise, therefore, is a crucial step in the preprocessing of ultrasound images. Researchers have proposed several speckle reduction methods, but no single method takes all relevant factors into account. In this paper, we compare seven such methods: Median, Gaussian, Bilateral, Average, Weiner, Anisotropic and Denoising auto-encoder without and with skip connections in terms of their ability to preserve features and edges while effectively reducing noise. In an experimental study, a convolutional noise-removing auto-encoder with skip connection, a deep learning method, was used to improve ultrasound images of breast cancer. This method involved adding speckle noise at various levels. The results of the deep learning method were compared to those of traditional image enhancement methods, and it was found that the proposed method was more effective. To assess the performance of these algorithms, we use three established evaluation metrics and present both filtered images and statistical data.

Figures (3)

• Figure 1: The Autoencoder Network with Skip Connection: The study presented an innovative autoencoder network, incorporating skip connections to remove speckle noise from ultrasound images. The network consisted of convolutional layers for feature extraction and reconstruction, and the addition of skip connections helped to preserve important information, resulting in improved performance compared to traditional filters and methods.
• Figure 2: Comparison of different denoising techniques applied to the original image. (a) Original Image. (b) Noise image with variance 0.7. (c) Auto-encoder without skip connection. (d) Auto-encoder with skip connection, (e) Median filtering (f) gaussian filtering (g) average filtering (h) bilateral filtering (i) Weiner filter and (j) anisotropic diffusion.
• Figure 3: Comparison of Structural Similarity Index Measure (SSIM) using various denoising techniques: Autoencoder with skip connection, Autoencoder without skip connection, Gaussian Blur, Average Blur, and Bilateral Filter. The x-axis represents different noise levels, while the y-axis represents the SSIM values.