Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm
The recovery of semantics from corrupted images is a significant challenge in image processing. Noise can obscure features, interfere with accurate analysis, and bias results. To address this issue, the Regularized Neighborhood Pixel Similarity Wavelet algorithm (PixSimWave) was developed for denois...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/18/7780 |
| _version_ | 1797577058628403200 |
|---|---|
| author | Romoke Grace Akindele Ming Yu Paul Shekonya Kanda Eunice Oluwabunmi Owoola Ifeoluwapo Aribilola |
| author_facet | Romoke Grace Akindele Ming Yu Paul Shekonya Kanda Eunice Oluwabunmi Owoola Ifeoluwapo Aribilola |
| author_sort | Romoke Grace Akindele |
| collection | DOAJ |
| description | The recovery of semantics from corrupted images is a significant challenge in image processing. Noise can obscure features, interfere with accurate analysis, and bias results. To address this issue, the Regularized Neighborhood Pixel Similarity Wavelet algorithm (PixSimWave) was developed for denoising Nifti (magnetic resonance imaging (MRI)). The PixSimWave algorithm uses regularized pixel similarity detection to improve the accuracy of noise reduction by creating patches to analyze the intensity of pixels and locate matching pixels, as well as adaptive neighborhood filtering to estimate noisy pixel values by allocating each pixel a weight based on its similarity. The wavelet transform breaks down the image into scales and orientations, allowing a sparse image representation to allocate a soft threshold on its similarity to the original pixels. The proposed method was evaluated on simulated and raw T1w MRIs, outperforming other methods in terms of an SSIM value of 0.9908 for a low Rician noise level of 3% and 0.9881 for a high noise level of 17%. The addition of Gaussian noise improved PSNR and SSIM, with the results indicating that the proposed method outperformed other models while preserving edges and textures. In summary, the PixSimWave algorithm is a viable noise-elimination approach that employs both sparse wavelet coefficients and regularized similarity with decreased computation time, improving the accuracy of noise reduction in images. |
| first_indexed | 2024-03-10T22:02:32Z |
| format | Article |
| id | doaj.art-9ed3b69ead7543c9b6b5d7a0f019a866 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T22:02:32Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9ed3b69ead7543c9b6b5d7a0f019a8662023-11-19T12:54:07ZengMDPI AGSensors1424-82202023-09-012318778010.3390/s23187780Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet AlgorithmRomoke Grace Akindele0Ming Yu1Paul Shekonya Kanda2Eunice Oluwabunmi Owoola3Ifeoluwapo Aribilola4School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSchool of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, ChinaSoftware Research Institute, Technological University of the Shannon, Midlands Midwest, Co. Westmeath, N37 HD68 Athlone, IrelandThe recovery of semantics from corrupted images is a significant challenge in image processing. Noise can obscure features, interfere with accurate analysis, and bias results. To address this issue, the Regularized Neighborhood Pixel Similarity Wavelet algorithm (PixSimWave) was developed for denoising Nifti (magnetic resonance imaging (MRI)). The PixSimWave algorithm uses regularized pixel similarity detection to improve the accuracy of noise reduction by creating patches to analyze the intensity of pixels and locate matching pixels, as well as adaptive neighborhood filtering to estimate noisy pixel values by allocating each pixel a weight based on its similarity. The wavelet transform breaks down the image into scales and orientations, allowing a sparse image representation to allocate a soft threshold on its similarity to the original pixels. The proposed method was evaluated on simulated and raw T1w MRIs, outperforming other methods in terms of an SSIM value of 0.9908 for a low Rician noise level of 3% and 0.9881 for a high noise level of 17%. The addition of Gaussian noise improved PSNR and SSIM, with the results indicating that the proposed method outperformed other models while preserving edges and textures. In summary, the PixSimWave algorithm is a viable noise-elimination approach that employs both sparse wavelet coefficients and regularized similarity with decreased computation time, improving the accuracy of noise reduction in images.https://www.mdpi.com/1424-8220/23/18/7780magnetic resonance imaging (MRI)Gaussian noiseRician noiseregularized pixel 16 detectionwavelet transformdenoising |
| spellingShingle | Romoke Grace Akindele Ming Yu Paul Shekonya Kanda Eunice Oluwabunmi Owoola Ifeoluwapo Aribilola Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm Sensors magnetic resonance imaging (MRI) Gaussian noise Rician noise regularized pixel 16 detection wavelet transform denoising |
| title | Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm |
| title_full | Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm |
| title_fullStr | Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm |
| title_full_unstemmed | Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm |
| title_short | Denoising of Nifti (MRI) Images with a Regularized Neighborhood Pixel Similarity Wavelet Algorithm |
| title_sort | denoising of nifti mri images with a regularized neighborhood pixel similarity wavelet algorithm |
| topic | magnetic resonance imaging (MRI) Gaussian noise Rician noise regularized pixel 16 detection wavelet transform denoising |
| url | https://www.mdpi.com/1424-8220/23/18/7780 |
| work_keys_str_mv | AT romokegraceakindele denoisingofniftimriimageswitharegularizedneighborhoodpixelsimilaritywaveletalgorithm AT mingyu denoisingofniftimriimageswitharegularizedneighborhoodpixelsimilaritywaveletalgorithm AT paulshekonyakanda denoisingofniftimriimageswitharegularizedneighborhoodpixelsimilaritywaveletalgorithm AT euniceoluwabunmiowoola denoisingofniftimriimageswitharegularizedneighborhoodpixelsimilaritywaveletalgorithm AT ifeoluwapoaribilola denoisingofniftimriimageswitharegularizedneighborhoodpixelsimilaritywaveletalgorithm |