eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2025-02-20 18 March Spl Edition 139 159 10.13005/bpj/3078 64164 article Swapna Katta 1 Prabhishek Singh 2 Deepak Garg 1 Manoj Diwakar 3 School of Computer Science and Artificial Intelligence, SR University, Warangal, Telangana, India School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India Department of CSE, Graphic Era Deemed to be University, Dehradun, Uttarakhand, India This paper introduces a new deep learning paradigm using the Denoising Convolutional-Neural Network (DnCNN) model for denoising Gaussian noise in Computed Tomography (CT) images. By nature, Gaussian noise is inherently random and additive, potentially obscuring vital diagnostic features and significantly reducing image quality, resulting difficulties in medical interpretation. Initially, the distorted images are sourced from addition of Gaussian noise with different intensity levels (σ = 5,10,15,20). The denoising process of DnCNN model employs a deep convolutional neural network that maps the noisy image to clean image, focusing on residual learning to prevent loss of detail. The CT images obtained after denoising are assessed using quantitative measures like Peak signal to noise ratio (PSNR), Signal to noise ratio (SNR), Structural similarity index measure (SSIM) and Entropy difference (ED). The proposed DnCNN model is evaluated using quantitative metrics, such as PSNR, SNR, SSIM, and ED, demonstrating better performance than standard denoising algorithms, including Total Variation, BM3D, Guided, Bilateral, and Anisotropic Diffusion filters. The experimental results show that the proposed DnCNN model outperforms conventional methods. The model achieves a PSNR of 35.66 dB, an SNR of 30.16 dB, SSIM of 0.91 and ED of 0.35. Additionally, zooming analysis and intensity profile evaluations confirms that the proposed method effectively suppresses noise while preserving sharper edges and finer anatomical structures. This ensures superior visual quality and greater efficacy compared to traditional methods. These experimental findings confirm that the proposed method is a robust denoising strategy in medical imaging for predicting accurate diagnostic outcomes. https://biomedpharmajournal.org/vol18marchspledition/an-efficient-gaussian-noise-denoising-in-ct-images-with-deep-convolutional-neural-networks/ CT image Deep learning Denoising DnCNN Gaussian noise