Performance evaluation of 67 denoising filters in ultrasound images: A systematic comparison analysis

Abstract

Noise corrupts ultrasound images and degrades spatial and contrast resolutions. Hence, it is challenging to characterize the lesions precisely using ultrasound images. The present study aims to evaluate 67 denoising filters and select the best one for ultrasound image denoising. Seven test images were synthesized to evaluate the performance of filters at three different noise levels. Eleven full‐reference quantitative image quality metrics (IQMs) were employed to evaluate the performance of the filters. A new filter evaluation method, Rank Analysis, was introduced and utilized at each noise level. The ten best filters with the smallest mean rank in all noise levels were defined for further analysis on real ultrasound images. The Rank Analysis was also employed for real ultrasound images, and filters were evaluated based on 14 IQMs (11 full‐reference and three no‐reference). Finally, the best filter was defined using the repeated measures analysis statistical test. According to the Rank Analysis results, the Spatial correlation (SCorr) filter obtained the best results with the mean rank scores±SD of 1 ± 0, which was significantly better than the other nine filters (p < 0.001). The second‐best results were achieved by three filters, Bitonic, most homogeneous neighborhood, and Lee diffusion (p < 0.05). We concluded that SCorr is the best filter for ultrasound image denoising. It can be used in the pre‐processing step before segmentation and diagnostic procedures. In addition, a new filter evaluation method, Rank Analysis, was introduced in this study, which is easy to use, fast, and provides reliable results. So, it can be used to evaluate newly developed filters in the future studies.

AdaRes: A deep learning‐based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies

“…The results of four IQMs at different three noise levels for natural images are shown in Figure S2 at a glance (see Supplementary material). In addition, to compare the performance of our proposed denoising filter with other models, the best traditional filter, SCorr, 27 and two DL‐based filters (DnCNN 37 and Approx 38,39 ) were defined as a baseline. The hyperparameters of these filters are available in the Supplementary material.…”

“…In other words, it was better to compare DL filters with the best traditional ones rather than other traditional filters. In this study, we compared the performance of our filter with the best traditional filter, SCorr, 27 along with other DL‐based filters and showed its superiority.…”

“…In addition, to compare the performance of our proposed denoising filter with other models, the best traditional filter, SCorr, 27 and two DL-based filters (DnCNN 37 and Approx 38,39 ) were defined as a baseline. The hyperparameters of these filters are available in the Supplementary material.…”

“…In this study, we aim to address the existing limitations in the literature by developing a DL‐based filter for ultrasound image denoising. The contribution of this study can be summarized as follows: Developing a DL filter based on adaptive residual (AdaRes) learning to remove both Gaussian and speckle noises from ultrasound images. Comparing the performance of the AdaRes filter with the best traditional filter, spatial correlation (SCorr), 27 to provide the best comparison results between the two categories. Performance evaluation of filters based on preserving radiomics features after denoising. Evaluating the effect of the AdaRes filter on deep CAD systems in benign and malignant lesions classification. Investigating the effect of the AdaRes filter on the performance of radiologists in lesions characterization. …”

“…2. Comparing the performance of the AdaRes filter with the best traditional filter, spatial correlation (SCorr), 27 to provide the best comparison results between the two categories.…”