A Method Noise-Based Convolutional Neural Network Technique for CT Image Denoising

Abstract

Medical imaging is a complex process that capitulates images created by X-rays, ultrasound imaging, angiography, etc. During the imaging process, it also captures image noise during image acquisition, some of which are extremely corrosive, creating a disturbance that results in image degradation. The proposed work addresses the challenge to eliminate the corrosive Gaussian additive white noise from computed tomography (CT) images while preserving the fine details. The proposed approach is synthesized by amalgamating the concept of method noise with a deep learning-based framework of a convolutional neural network (CNN). The corrupted images are obtained by explicit addition of Gaussian additive white noise at multiple noise variance levels (σ = 10, 15, 20, 25). The denoised images obtained are then evaluated according to their visual quality and quantitative metrics, such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). These metrics for denoised CT images are then compared with their respective values for the reference CT image. The average PSNR value of the proposed method is 25.82, the average SSIM value is 0.85, and the average computational time is 2.8760. To better understand the proposed approach’s effectiveness, an intensity profile of denoised and original medical images is plotted and compared. To further test the performance of the proposed methodology, the results obtained are also compared with that of other non-traditional methods. The critical analysis of the results shows the commendable efficiency of the proposed methodology in denoising the medical CT images corrupted by Gaussian noise. This approach can be utilized in multiple pragmatic areas of application in the field of medical image processing.

Design and development of artificial intelligence‐based application programming interface for early detection and diagnosis of colorectal cancer from wireless capsule endoscopy images

“…The performance of our proposed Padded U‐Net model was compared with other architectures worked on segmentation of polyp using Kvasir dataset, proposed in the literature during recent years (2020–2023) 44–54 . The performance metrics of our model were evaluated and compared with the performance metrics reported in existing literature, as presented in Table 5.…”

“…In clinical settings, various noises may be present in the images obtained by different imaging modalities 51 . For instance, speckle noise in ultrasound images, Rician noise in MRI images and gaussian noise in CT images may be present 52 . This emphasizes that the model should also be trained with images that consist of noises to improve the generalizability of the model thereby adapting to wide variety of unseen data.…”

“…51 For instance, speckle noise in ultrasound images, Rician noise in MRI images and gaussian noise in CT images may be present. 52 This emphasizes that the model should also be trained with images that consist of noises to improve the generalizability of the model thereby adapting to wide variety of unseen data. Taking this into account, we provided an option of augmenting the images by application of noises [47][48][49][50] Photometric transformation Photometric transformation involves changing the visual aspects of an image especially the light illumination and colour without affecting the semantic contents.…”

“…The performance of our proposed Padded U-Net model was compared with other architectures worked on segmentation of polyp using Kvasir dataset, proposed in the literature during recent years (2020-2023). [44][45][46][47][48][49][50][51][52][53][54] The performance metrics of our model were evaluated and compared with the performance metrics reported in existing literature, as presented in Table 5. It can be deduced that our model achieved optimal performance in all metrics, with the exception of accuracy, where it demonstrated marginal performance.…”

An Overview of Biomedical Imaging and Image Processing that Mirror Breakthroughs in Medical Science

“…Biomedical imaging provides exact tracing of metabolites that can be utilized as biomarkers for disease recognition, improvement and treatment response. CT scan is extremely important equipment in medical imaging to additive X-rays and medical USG or ultrasonography [3]. In recent days, biomedical imaging is improving immensely.…”