Augmented Noise Learning Framework for Enhancing Medical Image Denoising
Deep learning attempts medical image denoising either by directly learning the noise present or via first learning the image content. We observe that residual learning (RL) often suffers from signal leakage while dictionary learning (DL) is prone to Gibbs (ringing) artifacts. In this paper, we propo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9520361/ |
| _version_ | 1818692691258507264 |
|---|---|
| author | Swati Rai Jignesh S. Bhatt S. K. Patra |
| author_facet | Swati Rai Jignesh S. Bhatt S. K. Patra |
| author_sort | Swati Rai |
| collection | DOAJ |
| description | Deep learning attempts medical image denoising either by directly learning the noise present or via first learning the image content. We observe that residual learning (RL) often suffers from signal leakage while dictionary learning (DL) is prone to Gibbs (ringing) artifacts. In this paper, we propose an unsupervised noise learning framework that enhances denoising by augmenting the limitation of RL with the strength of DL and vice versa. To this end, we propose a ten-layer deep residue network (DRN) augmented with patch-based dictionaries. The input images are presented to patch-based DL to indirectly learn the noise via sparse representation while given to the DRN to directly learn the noise. An optimum noise characterization is captured by iterating DL/DRN network against proposed loss. The denoised images are obtained by subtracting the learned noise from available data. We show that augmented DRN effectively handles high-frequency regions to avoid Gibbs artifacts due to DL while augmented DL helps to reduce the overfitting due to RL. Comparative experiments with many state-of-the-arts on MRI and CT datasets (2D/3D) including low-dose CT (LDCT) are conducted on a GPU-based supercomputer. The proposed network is trained by adding different levels of Rician noise for MRI and Poisson noise for CT images considering different nature and statistical distribution of datasets. The ablation studies are carried out that demonstrate enhanced denoising performance with minimal signal leakage and least artifacts by proposed augmented approach. |
| first_indexed | 2024-12-17T13:01:49Z |
| format | Article |
| id | doaj.art-c6069af9a6db48c096365f53761e062d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T13:01:49Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c6069af9a6db48c096365f53761e062d2022-12-21T21:47:21ZengIEEEIEEE Access2169-35362021-01-01911715311716810.1109/ACCESS.2021.31067079520361Augmented Noise Learning Framework for Enhancing Medical Image DenoisingSwati Rai0Jignesh S. Bhatt1https://orcid.org/0000-0003-4468-7994S. K. Patra2Indian Institute of Information Technology (IIIT) Vadodara, Gandhinagar, IndiaIndian Institute of Information Technology (IIIT) Vadodara, Gandhinagar, IndiaIndian Institute of Information Technology (IIIT) Vadodara, Gandhinagar, IndiaDeep learning attempts medical image denoising either by directly learning the noise present or via first learning the image content. We observe that residual learning (RL) often suffers from signal leakage while dictionary learning (DL) is prone to Gibbs (ringing) artifacts. In this paper, we propose an unsupervised noise learning framework that enhances denoising by augmenting the limitation of RL with the strength of DL and vice versa. To this end, we propose a ten-layer deep residue network (DRN) augmented with patch-based dictionaries. The input images are presented to patch-based DL to indirectly learn the noise via sparse representation while given to the DRN to directly learn the noise. An optimum noise characterization is captured by iterating DL/DRN network against proposed loss. The denoised images are obtained by subtracting the learned noise from available data. We show that augmented DRN effectively handles high-frequency regions to avoid Gibbs artifacts due to DL while augmented DL helps to reduce the overfitting due to RL. Comparative experiments with many state-of-the-arts on MRI and CT datasets (2D/3D) including low-dose CT (LDCT) are conducted on a GPU-based supercomputer. The proposed network is trained by adding different levels of Rician noise for MRI and Poisson noise for CT images considering different nature and statistical distribution of datasets. The ablation studies are carried out that demonstrate enhanced denoising performance with minimal signal leakage and least artifacts by proposed augmented approach.https://ieeexplore.ieee.org/document/9520361/Augmented noise learningdeep residue networkdenoisingdictionary learninginverse ill-posed problemunsupervised learning |
| spellingShingle | Swati Rai Jignesh S. Bhatt S. K. Patra Augmented Noise Learning Framework for Enhancing Medical Image Denoising IEEE Access Augmented noise learning deep residue network denoising dictionary learning inverse ill-posed problem unsupervised learning |
| title | Augmented Noise Learning Framework for Enhancing Medical Image Denoising |
| title_full | Augmented Noise Learning Framework for Enhancing Medical Image Denoising |
| title_fullStr | Augmented Noise Learning Framework for Enhancing Medical Image Denoising |
| title_full_unstemmed | Augmented Noise Learning Framework for Enhancing Medical Image Denoising |
| title_short | Augmented Noise Learning Framework for Enhancing Medical Image Denoising |
| title_sort | augmented noise learning framework for enhancing medical image denoising |
| topic | Augmented noise learning deep residue network denoising dictionary learning inverse ill-posed problem unsupervised learning |
| url | https://ieeexplore.ieee.org/document/9520361/ |
| work_keys_str_mv | AT swatirai augmentednoiselearningframeworkforenhancingmedicalimagedenoising AT jigneshsbhatt augmentednoiselearningframeworkforenhancingmedicalimagedenoising AT skpatra augmentednoiselearningframeworkforenhancingmedicalimagedenoising |