Effectiveness of generative adversarial networks in denoising medical imaging (CT/MRI images)

For clinical analysis or medical intrusion, imaging technology is a potent tool for producing visual images of a body's inside. However, several existing methods include restricted access to high-quality and diverse datasets, overfitting, a lack of interpretability, high computational costs, varying medical imaging data, and ethical issues concerning patient privacy, consent, and bias. To overcome these issues, the effectiveness of generative adversarial networks in denoising medical imaging (CT/MRI images) is proposed. The input CT images are first gathered and preprocessed to reduce undesired noise using Altered Phase Preserving Dynamic Range Compression (APPDRC). The General Adversarial Network (GAN) is then given these preprocessed images to cope with the noisy areas of CT/MRI while also complying with maintaining image structures such as boundary details while preventing over-smoothing, and the weight parameters for the GAN are optimized using the Golden Eagle Optimization (GEO) technique. General Adversarial Network (GAN) has piqued the interest of academics studying medical image-denoising mechanisms and developing sophisticated medical image-denoising algorithms based on deep learning. In light of reducing the difficulty in feature learning and improving final diagnosis accuracy, data preprocessing is necessary and crucial in gan-based medical image denoising methods. This work focuses on GAN-based effective denoising approaches in CT/MRI. The potential challenges and research objectives are in the context of data preprocessing in medical image denoising. Because of how CT/MRI images are acquired, it was observed that noise in CT/MRI data follows the distribution. Generative Adversarial Networks (GANs) for denoising medical imaging, mainly CT and MRI images, have yielded promising results of 99% accuracy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.