Improving Structural MRI Preprocessing with Hybrid Transformer GANs
Magnetic resonance imaging (MRI) is a technique that is widely used in practice to evaluate any pathologies in the human body. One of the areas of interest is the human brain. Naturally, MR images are low-resolution and contain noise due to signal interference, the patient’s body’s radio-frequency e...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/13/9/1893 |
| _version_ | 1827725547950571520 |
|---|---|
| author | Ovidijus Grigas Rytis Maskeliūnas Robertas Damaševičius |
| author_facet | Ovidijus Grigas Rytis Maskeliūnas Robertas Damaševičius |
| author_sort | Ovidijus Grigas |
| collection | DOAJ |
| description | Magnetic resonance imaging (MRI) is a technique that is widely used in practice to evaluate any pathologies in the human body. One of the areas of interest is the human brain. Naturally, MR images are low-resolution and contain noise due to signal interference, the patient’s body’s radio-frequency emissions and smaller Tesla coil counts in the machinery. There is a need to solve this problem, as MR tomographs that have the capability of capturing high-resolution images are extremely expensive and the length of the procedure to capture such images increases by the order of magnitude. Vision transformers have lately shown state-of-the-art results in super-resolution tasks; therefore, we decided to evaluate whether we can employ them for structural MRI super-resolution tasks. A literature review showed that similar methods do not focus on perceptual image quality because upscaled images are often blurry and are subjectively of poor quality. Knowing this, we propose a methodology called HR-MRI-GAN, which is a hybrid transformer generative adversarial network capable of increasing resolution and removing noise from 2D T1w MRI slice images. Experiments show that our method quantitatively outperforms other SOTA methods in terms of perceptual image quality and is capable of subjectively generalizing to unseen data. During the experiments, we additionally identified that the visual saliency-induced index metric is not applicable to MRI perceptual quality assessment and that general-purpose denoising networks are effective when removing noise from MR images. |
| first_indexed | 2024-03-10T22:32:51Z |
| format | Article |
| id | doaj.art-45ceba1b811c48e086513815f10b32dc |
| institution | Directory Open Access Journal |
| issn | 2075-1729 |
| language | English |
| last_indexed | 2024-03-10T22:32:51Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj.art-45ceba1b811c48e086513815f10b32dc2023-11-19T11:37:45ZengMDPI AGLife2075-17292023-09-01139189310.3390/life13091893Improving Structural MRI Preprocessing with Hybrid Transformer GANsOvidijus Grigas0Rytis Maskeliūnas1Robertas Damaševičius2Faculty of Informatics, Kaunas University of Technology, 50254 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, 50254 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, 50254 Kaunas, LithuaniaMagnetic resonance imaging (MRI) is a technique that is widely used in practice to evaluate any pathologies in the human body. One of the areas of interest is the human brain. Naturally, MR images are low-resolution and contain noise due to signal interference, the patient’s body’s radio-frequency emissions and smaller Tesla coil counts in the machinery. There is a need to solve this problem, as MR tomographs that have the capability of capturing high-resolution images are extremely expensive and the length of the procedure to capture such images increases by the order of magnitude. Vision transformers have lately shown state-of-the-art results in super-resolution tasks; therefore, we decided to evaluate whether we can employ them for structural MRI super-resolution tasks. A literature review showed that similar methods do not focus on perceptual image quality because upscaled images are often blurry and are subjectively of poor quality. Knowing this, we propose a methodology called HR-MRI-GAN, which is a hybrid transformer generative adversarial network capable of increasing resolution and removing noise from 2D T1w MRI slice images. Experiments show that our method quantitatively outperforms other SOTA methods in terms of perceptual image quality and is capable of subjectively generalizing to unseen data. During the experiments, we additionally identified that the visual saliency-induced index metric is not applicable to MRI perceptual quality assessment and that general-purpose denoising networks are effective when removing noise from MR images.https://www.mdpi.com/2075-1729/13/9/1893magnetic resonance imagingsuper resolution |
| spellingShingle | Ovidijus Grigas Rytis Maskeliūnas Robertas Damaševičius Improving Structural MRI Preprocessing with Hybrid Transformer GANs Life magnetic resonance imaging super resolution |
| title | Improving Structural MRI Preprocessing with Hybrid Transformer GANs |
| title_full | Improving Structural MRI Preprocessing with Hybrid Transformer GANs |
| title_fullStr | Improving Structural MRI Preprocessing with Hybrid Transformer GANs |
| title_full_unstemmed | Improving Structural MRI Preprocessing with Hybrid Transformer GANs |
| title_short | Improving Structural MRI Preprocessing with Hybrid Transformer GANs |
| title_sort | improving structural mri preprocessing with hybrid transformer gans |
| topic | magnetic resonance imaging super resolution |
| url | https://www.mdpi.com/2075-1729/13/9/1893 |
| work_keys_str_mv | AT ovidijusgrigas improvingstructuralmripreprocessingwithhybridtransformergans AT rytismaskeliunas improvingstructuralmripreprocessingwithhybridtransformergans AT robertasdamasevicius improvingstructuralmripreprocessingwithhybridtransformergans |