CWAOA: CHRONOLOGICAL WALRUSES BEHAVIOR OPTIMIZATION AND DEEP LEARNING FOR MEDICAL IMAGE DENOISING

The medical images are considered an essential part of healthcare applications. The noise associated with the images can minimize the clearness of the image, which leads to the misidentification of the diseases. Hence, the denoising of images is an essential process in healthcare applications. In this work, a medical image denoising method based on chronological walrus behavior optimization (CWaOA) is proposed. The process begins by identifying the noisy pixels in the image, which is achieved using LeNet to detect the noisy pixel map. The CWaOA algorithm is used for removing the noise from the image. To enhance the image pixels, the vectorial total variation (VTV) norm is employed. Simultaneously, the input image undergoes transformation using the dual-tree complex wavelet transform (DTCWT) to process its low-frequency components. A Gaussian filter is applied for image filtering, and the denoised image is obtained by applying inverse DTCWT. Based on the image quality accessed metrics like natural image quality evaluator (NIQE), universal quality index (UQI), and structural similarity index (SSIM), the denoised image and pixel-enhanced image fusion is done at the final step. Additionally, the performance of the model is evaluated using the peak signal-to-noise ratio (PSNR), second derivative-like measure of enhancement (SDME), and SSIM metrics, yielding superior results with PSNR of 30.03 dB, SDME of 41.94 dB, and SSIM of 0.883. The source code of the article is available at “ https://github.com/Rashmita-S/CWaOA.git ”.