Despeckling of clinical ultrasound images using deep residual learning

Background and objective Ultrasound is the non-radioactive imaging modality used in the diagnosis of various diseases related to the internal organs of the body. The presence of speckle noise in ultrasound image (UI) is inevitable and may affect resolution and contrast of the image. Existence of the speckle noise degrades the visual evaluation of the image. The despeckling of UI is a desirable pre-processing step in computer-aided UI based diagnosis systems. Methods This paper proposes a novel method for despeckling UIs using pre-trained residual learning network (RLN). Initially, RLN is trained with pristine and its corresponding noisy images in order to achieve a better performance. The developed method chooses a pre-trained RLN for despeckling UIs with less computational resources. But the training procedure of RLN from scratch is computationally demanding. The pre-trained RLN is a blind despeckling approach and does not require any fine tuning and noise level estimation. The presented approach shows superiority in the removal of speckle noise as compared to the existing state-of-art methods. Results To highlight the effectiveness of the proposed method the pristine images from the Waterloo dataset has been considered. The proposed pre-trained RLN based UI despeckling method resulted in a better peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) at different speckle noise levels. The no-reference image quality approach is adopted to ensure robustness of the established method for real time UI. From results it is obvious that, the performance of the proposed method is superior than the existing methods in terms of naturalness image quality evaluator (NIQE). Conclusions From the experimental results, it is clear that the proposed method outperforms the existing despeckling methods in terms of both artificially added and naturally occurring speckle images.