RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images

Abstract The use of a light-weight deep learning Convolutional Neural Network (CNN) augmented with the power of Fuzzy Non-Sample Shearlet Transformation (FNSST) has successfully solved the problem of reducing noise and artifacts in Low-Dose Computed Tomography (LDCT) pictures. Both the Normal-Dose C...

Full description

Saved in:
Bibliographic Details
Main Authors: Haewon Byeon, Ruchi Kshatri Patel, Deepak A. Vidhate, Sherzod Kiyosov, Saima Ahmed Rahin, Ismail Keshta, T. R. Vijaya Lakshmi
Format: Article
Language:English
Published: Springer 2024-01-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-024-05634-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134778631684096
author Haewon Byeon
Ruchi Kshatri Patel
Deepak A. Vidhate
Sherzod Kiyosov
Saima Ahmed Rahin
Ismail Keshta
T. R. Vijaya Lakshmi
author_facet Haewon Byeon
Ruchi Kshatri Patel
Deepak A. Vidhate
Sherzod Kiyosov
Saima Ahmed Rahin
Ismail Keshta
T. R. Vijaya Lakshmi
author_sort Haewon Byeon
collection DOAJ
description Abstract The use of a light-weight deep learning Convolutional Neural Network (CNN) augmented with the power of Fuzzy Non-Sample Shearlet Transformation (FNSST) has successfully solved the problem of reducing noise and artifacts in Low-Dose Computed Tomography (LDCT) pictures. Both the Normal-Dose Computed Tomography (NDCT) and the Low-Dose Computed Tomography (LDCT) images from the dataset are subjected to the FNSST decomposition procedure during the training phase, producing high-frequency sub-images that act as input for the CNN. The CNN creates a meaningful connection between the high-frequency sub-images from LDCT and their corresponding residual sub-images during the training operation. The CNN is given the capacity to distinguish between LDCT high-frequency sub-images and expected high-frequency sub-images, which frequently have varying levels of noise or artifacts, especially in a fuzzy setting. The FNSST-CNN then successfully distinguishes LDCT high-frequency sub-images from the expected high-frequency sub-images during the testing phase, thereby reducing noise and artifacts. When compared to other approaches like KSVD, BM3D, and conventional image domain CNNs, the performance of FNSST-CNN is impressive as shown by better peak signal-to-noise ratios, stronger structural similarity, and a closer likeness to NDCT pictures.
format Article
id doaj-art-a617a5573abd42abb331c98ab837dda3
institution OA Journals
issn 3004-9261
language English
publishDate 2024-01-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-a617a5573abd42abb331c98ab837dda32025-08-20T02:31:38ZengSpringerDiscover Applied Sciences3004-92612024-01-016111410.1007/s42452-024-05634-6RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical imagesHaewon Byeon0Ruchi Kshatri Patel1Deepak A. Vidhate2Sherzod Kiyosov3Saima Ahmed Rahin4Ismail Keshta5T. R. Vijaya Lakshmi6Department of Digital Anti-Aging Healthcare, Inje UniversityShri Ram Institute of TechnologyDepartment of Information Technology, Dr Vithalrao Vikhe Patil College of EngineeringThe Department of Tax and Taxation, Tashkent Institute of FinanceUnited International UniversityComputer Science and Information Systems Department, College of Applied Sciences, AlMaarefa UniversityMahatma Gandhi Institute of Technology GandipetAbstract The use of a light-weight deep learning Convolutional Neural Network (CNN) augmented with the power of Fuzzy Non-Sample Shearlet Transformation (FNSST) has successfully solved the problem of reducing noise and artifacts in Low-Dose Computed Tomography (LDCT) pictures. Both the Normal-Dose Computed Tomography (NDCT) and the Low-Dose Computed Tomography (LDCT) images from the dataset are subjected to the FNSST decomposition procedure during the training phase, producing high-frequency sub-images that act as input for the CNN. The CNN creates a meaningful connection between the high-frequency sub-images from LDCT and their corresponding residual sub-images during the training operation. The CNN is given the capacity to distinguish between LDCT high-frequency sub-images and expected high-frequency sub-images, which frequently have varying levels of noise or artifacts, especially in a fuzzy setting. The FNSST-CNN then successfully distinguishes LDCT high-frequency sub-images from the expected high-frequency sub-images during the testing phase, thereby reducing noise and artifacts. When compared to other approaches like KSVD, BM3D, and conventional image domain CNNs, the performance of FNSST-CNN is impressive as shown by better peak signal-to-noise ratios, stronger structural similarity, and a closer likeness to NDCT pictures.https://doi.org/10.1007/s42452-024-05634-6CNNBiomedical ImagePeak Signal-To-Noise ratioStructural similarityArtifact Problem
spellingShingle Haewon Byeon
Ruchi Kshatri Patel
Deepak A. Vidhate
Sherzod Kiyosov
Saima Ahmed Rahin
Ismail Keshta
T. R. Vijaya Lakshmi
RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images
Discover Applied Sciences
CNN
Biomedical Image
Peak Signal-To-Noise ratio
Structural similarity
Artifact Problem
title RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images
title_full RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images
title_fullStr RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images
title_full_unstemmed RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images
title_short RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images
title_sort retracted article non sample fuzzy based convolutional neural network model for noise artifact in biomedical images
topic CNN
Biomedical Image
Peak Signal-To-Noise ratio
Structural similarity
Artifact Problem
url https://doi.org/10.1007/s42452-024-05634-6
work_keys_str_mv AT haewonbyeon retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages
AT ruchikshatripatel retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages
AT deepakavidhate retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages
AT sherzodkiyosov retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages
AT saimaahmedrahin retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages
AT ismailkeshta retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages
AT trvijayalakshmi retractedarticlenonsamplefuzzybasedconvolutionalneuralnetworkmodelfornoiseartifactinbiomedicalimages