Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913296996630528 |
|---|---|
| author | Xue, Hui Hooper, Sarah Rehman, Azaan Pierce, Iain Treibel, Thomas Davies, Rhodri Bandettini, W Patricia Ramasawmy, Rajiv Javed, Ahsan Zhu, Zheren Yang, Yang Moon, James Campbell, Adrienne Kellman, Peter |
| author_facet | Xue, Hui Hooper, Sarah Rehman, Azaan Pierce, Iain Treibel, Thomas Davies, Rhodri Bandettini, W Patricia Ramasawmy, Rajiv Javed, Ahsan Zhu, Zheren Yang, Yang Moon, James Campbell, Adrienne Kellman, Peter |
| contents | The ability to recover MRI signal from noise is key to achieve fast acquisition, accurate quantification, and high image quality. Past work has shown convolutional neural networks can be used with abundant and paired low and high-SNR images for training. However, for applications where high-SNR data is difficult to produce at scale (e.g. with aggressive acceleration, high resolution, or low field strength), training a new denoising network using a large quantity of high-SNR images can be infeasible.
In this study, we overcome this limitation by improving the generalization of denoising models, enabling application to many settings beyond what appears in the training data. Specifically, we a) develop a training scheme that uses complex MRIs reconstructed in the SNR units (i.e., the images have a fixed noise level, SNR unit training) and augments images with realistic noise based on coil g-factor, and b) develop a novel imaging transformer (imformer) to handle 2D, 2D+T, and 3D MRIs in one model architecture. Through empirical evaluation, we show this combination improves performance compared to CNN models and improves generalization, enabling a denoising model to be used across field-strengths, image contrasts, and anatomy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02382 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy Xue, Hui Hooper, Sarah Rehman, Azaan Pierce, Iain Treibel, Thomas Davies, Rhodri Bandettini, W Patricia Ramasawmy, Rajiv Javed, Ahsan Zhu, Zheren Yang, Yang Moon, James Campbell, Adrienne Kellman, Peter Image and Video Processing The ability to recover MRI signal from noise is key to achieve fast acquisition, accurate quantification, and high image quality. Past work has shown convolutional neural networks can be used with abundant and paired low and high-SNR images for training. However, for applications where high-SNR data is difficult to produce at scale (e.g. with aggressive acceleration, high resolution, or low field strength), training a new denoising network using a large quantity of high-SNR images can be infeasible. In this study, we overcome this limitation by improving the generalization of denoising models, enabling application to many settings beyond what appears in the training data. Specifically, we a) develop a training scheme that uses complex MRIs reconstructed in the SNR units (i.e., the images have a fixed noise level, SNR unit training) and augments images with realistic noise based on coil g-factor, and b) develop a novel imaging transformer (imformer) to handle 2D, 2D+T, and 3D MRIs in one model architecture. Through empirical evaluation, we show this combination improves performance compared to CNN models and improves generalization, enabling a denoising model to be used across field-strengths, image contrasts, and anatomy. |
| title | Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2404.02382 |