Denoising of magnetic resonance imaging using Bayes shrinkage based fused wavelet transform and autoencoder based deep learning approach

Juneja, Mamta; Saini, Sumindar Kaur; Kaul, Sambhav; Acharjee, Rajarshi; Thakur, Niharika; Jindal, Prashant

doi:10.1016/j.bspc.2021.102844

Cited by 28 publications

(11 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Introductionsupporting

confidence: 56%

“…These processes greatly improve the image quality for diagnosis and staging of malignancies using advanced CAD techniques like segmentation and classification. Similar studies performed by researchers using image denoising and restoration to improve the image quality for segmentation and classification are given by Juneja et al, 6 Garg et al, 7 Thakur et al, 8 and Kaur et al 9 Complex imaging modality such as CT is one of the most comprehensive imaging tests used by clinicians to identify pancreatic cancer. This technique uses X-rays to get a detailed Three-dimensional (3D) image of the target organ.…”

mentioning

confidence: 63%

See 1 more Smart Citation

Denoising of computed tomography using bilateral median based autoencoder network

Juneja

Joshi

Singla

et al. 2021

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

Denoising of Computed tomography (CT) images is a critical aspect of image processing that is expected to improve the performance of Computer‐aided diagnosis (CAD) systems. However, the use of complex imaging modalities such as CT imaging to ascertain pancreatic cancer is vulnerable to gaussian and poisson noises, making image denoising an imperative step for the accurate performance of CAD systems. This paper presents a Bilateral median based autoencoder network (BMAuto‐Net) constructed with intermediate batch normalization layers and dropout factors to eliminate gaussian noise from the CT images. The skip connections adjoining the network, prevent performance degradation that generally occurs in most autoencoder architectures. Based on the presented study, BMAuto‐Net is reckoned to outperform other traditional filters and autoencoders. The performance measurement of the proposed architecture is performed using the peak signal‐to‐noise ratio (PSNR), mean squared error (MSE), and structured similarity index (SSIM) metric values. The Cancer imaging archive (TCIA) dataset consisting of 19 000 CT images is used to validate the performance of the architecture with average PSNR values of 30.01, 30.53, and 30.52, MSE values of 98.23, 98.87, and 98.94, and SSIM of values of 0.67, 0.60, and 0.57 for noise factors (NFs) of 0.1, 0.3, and 0.5 respectively.

show abstract

Section: Introductionsupporting

confidence: 56%

mentioning

confidence: 63%

Denoising of computed tomography using bilateral median based autoencoder network

Juneja

Joshi

Singla

et al. 2021

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…The software platform is Intel E8200 CPU 2.5 GHz, RAM 8G, windows 10 and MATLAB 2016a. Bayes shrink threshold function(BSTF) [4] , traditional adaptive threshold function(TATF) [29] , multi-layer threshold function(MLTF) [30] , improved symbolic threshold function(ISTF) [31] , soft threshold function (STF) [24] , hard threshold function(HTF) [24] and paper method(wavelet transform combined with improved PSO,WTPSO) are used for early CT image, advanced CT image and suspected cases of asymptomatic COVID-19 with different variance noise. Different Gaussian noise variance values (

) are added to the image, and different decomposition levels n are selected at the same time.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Therefore, an effective image denoising method is very important. Wavelet transform can adjust the sampling length of different frequencies in time domain, and it has the characteristic of multi-resolution for Gaussian noise [4] , [5] . However, the traditional wavelet transform has some problems of constant deviation and discontinuous threshold.…”

Section: Introductionmentioning

confidence: 99%

Asymptomatic COVID-19 CT image denoising method based on wavelet transform combined with improved PSO

Guo-wei

Guo

Han

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…CMSNet showed superior noise reduction capabilities not only on Rician noise in MR images but also on low-dose perfusion noise in CT images. Juneja et al [ 123 ] utilized dDLR in order to assess the image quality of conventional respiratory-triggered 3D magnetic resonance cholangiopancreatography (Resp-MRCP) and breath-hold 3D MRCP (BH-MRCP). Their experiments were done is 1.5-T setting using 42 patients, and two radiologists rated the visibility of the proximal common bile duct (CBD), pancreaticobiliary junction, distal main pancreatic duct, cystic duct, and right and left hepatic ducts in the final images.…”

Section: Noise Reduction In Mrimentioning

confidence: 99%

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging—State-of-the-Art and Challenges

et al. 2022

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

show abstract

Denoising of magnetic resonance imaging using Bayes shrinkage based fused wavelet transform and autoencoder based deep learning approach

Cited by 28 publications

References 50 publications

Denoising of computed tomography using bilateral median based autoencoder network

Denoising of computed tomography using bilateral median based autoencoder network

Asymptomatic COVID-19 CT image denoising method based on wavelet transform combined with improved PSO

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging—State-of-the-Art and Challenges

Contact Info

Product

Resources

About