Medical Image Denoising Using a Novel Multilevel Convolutional Optimized Visual Attention Network in Diverse Dataset

Image denoising is essential for medical image analysis due to noise introduced by various acquisition methods and efforts to reduce radiation exposure. Noise in medical imaging from equipment, patient variability and environmental factors requires effective denoising to improve image quality and diagnostics. To address these challenges, a Multilevel Convolutional Neural Network with an optimized Visual Attention Network (MCVAN) is developed specifically for image denoising to enhance the Peak Signal-to-Noise Ratio (PSNR). Leopard Seal Optimization (LSO) is fine-tuning the parameters of the network, enhancing denoising performance. The motivation is to address the critical need for effective image denoising in medical imaging. The innovation of this research lies in the development of a MCVAN, developed for image denoising. The LSO to fine-tune parameters further enhances the denoising performance. This architecture effectively adapts to varying noise levels in input images, aiming to significantly reduce noise in medical images for improved diagnostic accuracy and visual clarity. Experimental results show an average PSNR of 43.79dB and a Structural Similarity Index Measure (SSIM) of 0.863 and the MCVAN achieves accuracy (99.9%), precision (99.9%), recall (99.9%) and F1-score (99.9%). Overall, the MCVAN demonstrates superior effectiveness in image denoising, surpassing existing techniques in both quality and efficiency.