Enhancing Microscopic Image Quality With DiffusionFormer and Crow Search Optimization.
Authors
Affiliations (6)
Affiliations (6)
- School of Computing Science and Engineering, VIT Bhopal University, Bhopal, India.
- Department of Information Science and Engineering, Mangalore Institute of Technology and Engineering, Mangaluru, India.
- Department of ECE, JNTU-GV College of Engineering, Vizianagaram, India.
- Department of Computer Science, St. Joseph College (Autonomous), Trichy, India.
- School of Computing, Mohan Babu University, Tirupati, India.
- Department of Computer Science and Engineering, Panimalar Engineering College, Chennai, India.
Abstract
Medical Image plays a vital role in diagnosis, but noise in patient scans severely affects the accuracy and quality of images. Denoising methods are important to increase the clarity of these images, particularly in low-resource settings where current diagnostic roles are inaccessible. Pneumonia is a widespread disease that presents significant diagnostic challenges due to the high similarity between its various types and the lack of medical images for emerging variants. This study introduces a novel Diffusion with swin transformer-based Optimized Crow Search algorithm to increase the image's quality and reliability. This technique utilizes four datasets such as brain tumor MRI dataset, chest X-ray image, chest CT-scan image, and BUSI. The preprocessing steps involve conversion to grayscale, resizing, and normalization to improve image quality in medical image (MI) datasets. Gaussian noise is introduced to further enhance image quality. The method incorporates a diffusion process, swin transformer networks, and optimized crow search algorithm to improve the denoising of medical images. The diffusion process reduces noise by iteratively refining images while swin transformer captures complex image features that help differentiate between noise and essential diagnostic information. The crow search optimization algorithm fine-tunes the hyperparameters, which minimizes the fitness function for optimal denoising performance. The method is tested across four datasets, indicating its optimal effectiveness against other techniques. The proposed method achieves a peak signal-to-noise ratio of 38.47 dB, a structural similarity index measure of 98.14%, a mean squared error of 0.55, and a feature similarity index measure of 0.980, which outperforms existing techniques. These outcomes reflect that the proposed approach effectively enhances the quality of images, resulting in precise and dependable diagnoses.