Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters
In clinical diagnosis, magnetic resonance imaging (MRI) plays a vital role in analyzing soft tissues. However, the images are affected by noise that is random in nature. The noise affects the quality of the image, which impacts the accuracy of diagnosis. To address this, in this paper, four enhanced...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10817572/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590335628279808 |
|---|---|
| author | Suganya Athisayamani A. Robert Singh Faten Khalid Karim Samih M. Mostafa |
| author_facet | Suganya Athisayamani A. Robert Singh Faten Khalid Karim Samih M. Mostafa |
| author_sort | Suganya Athisayamani |
| collection | DOAJ |
| description | In clinical diagnosis, magnetic resonance imaging (MRI) plays a vital role in analyzing soft tissues. However, the images are affected by noise that is random in nature. The noise affects the quality of the image, which impacts the accuracy of diagnosis. To address this, in this paper, four enhanced versions of filters: enhanced Lee filter (ELF), enhanced Frost filter (EFF), enhanced Kuan filter (EKF) and enhanced Boxcar filter (EBCF) are used. The enhanced image features are used for classification with three different CNN classification models: Convolutional Neural Network (CNN), CNN with attention module (CNN-AM) and CNN with a residual module (CNN-RM). The enhanced filters help in improving the features. In the proposed architecture, the spatial attention module achieves these benefits by applying operations such as average pooling, max pooling, and sigmoid activation to selectively highlight key spatial regions in MRI images, leading to improved classification accuracy and overall performance. The proposed methods are compared with the state-of-the-art methods, and they ensure better image enhancement with high PSNR values of 32.1, 36.7 and 39.1, respectively. The classification models ensure high accuracy of 94%, 95% and 98%. |
| format | Article |
| id | doaj-art-73c12ea0af294623bc320b8990e8bc51 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-73c12ea0af294623bc320b8990e8bc512025-01-24T00:01:54ZengIEEEIEEE Access2169-35362025-01-0113123991241010.1109/ACCESS.2024.352351610817572Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising FiltersSuganya Athisayamani0A. Robert Singh1Faten Khalid Karim2https://orcid.org/0000-0003-1111-5818Samih M. Mostafa3https://orcid.org/0000-0001-9234-5898School of Computing, Sastra Deemed to be University, Thanjavur, Tamil Nadu, IndiaDepartment of Computational Intelligence, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, IndiaDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi ArabiaComputer Science Department, Faculty of Computers and Information, South Valley University, Qena, EgyptIn clinical diagnosis, magnetic resonance imaging (MRI) plays a vital role in analyzing soft tissues. However, the images are affected by noise that is random in nature. The noise affects the quality of the image, which impacts the accuracy of diagnosis. To address this, in this paper, four enhanced versions of filters: enhanced Lee filter (ELF), enhanced Frost filter (EFF), enhanced Kuan filter (EKF) and enhanced Boxcar filter (EBCF) are used. The enhanced image features are used for classification with three different CNN classification models: Convolutional Neural Network (CNN), CNN with attention module (CNN-AM) and CNN with a residual module (CNN-RM). The enhanced filters help in improving the features. In the proposed architecture, the spatial attention module achieves these benefits by applying operations such as average pooling, max pooling, and sigmoid activation to selectively highlight key spatial regions in MRI images, leading to improved classification accuracy and overall performance. The proposed methods are compared with the state-of-the-art methods, and they ensure better image enhancement with high PSNR values of 32.1, 36.7 and 39.1, respectively. The classification models ensure high accuracy of 94%, 95% and 98%.https://ieeexplore.ieee.org/document/10817572/MRIELFEEFEKFEBFCNN |
| spellingShingle | Suganya Athisayamani A. Robert Singh Faten Khalid Karim Samih M. Mostafa Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters IEEE Access MRI ELF EEF EKF EBF CNN |
| title | Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters |
| title_full | Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters |
| title_fullStr | Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters |
| title_full_unstemmed | Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters |
| title_short | Automatic MRI Image Classification Using Attention and Residual CNNs With Enhanced Image Denoising Filters |
| title_sort | automatic mri image classification using attention and residual cnns with enhanced image denoising filters |
| topic | MRI ELF EEF EKF EBF CNN |
| url | https://ieeexplore.ieee.org/document/10817572/ |
| work_keys_str_mv | AT suganyaathisayamani automaticmriimageclassificationusingattentionandresidualcnnswithenhancedimagedenoisingfilters AT arobertsingh automaticmriimageclassificationusingattentionandresidualcnnswithenhancedimagedenoisingfilters AT fatenkhalidkarim automaticmriimageclassificationusingattentionandresidualcnnswithenhancedimagedenoisingfilters AT samihmmostafa automaticmriimageclassificationusingattentionandresidualcnnswithenhancedimagedenoisingfilters |