Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction

Повышение отношения сигнал/шум в низкопольной МРТ с помощью глубокой нейросетевой реконструкции изображений
Matthew Scott Rosen, Bo Zhu, G. Cody Bagnall, Néha Koonjoo, Danyal Fareed Bhutto
2021-04-15

AUTOMAPMRI denoisingdeep learning image reconstructionlow-field MRIsignal-to-noise ratio
Recent years have seen a resurgence of interest in inexpensive low magnetic field (< 0.3 T) MRI systems mainly due to advances in magnet, coil and gradient set designs. Most of these advances have focused on improving hardware and signal acquisition strategies, and far less on the use of advanced image reconstruction methods to improve attainable image quality at low field. We describe here the use of our end-to-end deep neural network approach (AUTOMAP) to improve the image quality of highly noise-corrupted low-field MRI data. We compare the performance of this approach to two additional state-of-the-art denoising pipelines. We find that AUTOMAP improves image reconstruction of data acquired on two very different low-field MRI systems: human brain data acquired at 6.5 mT, and plant root data acquired at 47 mT, demonstrating SNR gains above Fourier reconstruction by factors of 1.5- to 4.5-fold, and 3-fold, respectively. In these applications, AUTOMAP outperformed two different contemporary image-based denoising algorithms, and suppressed noise-like spike artifacts in the reconstructed images. The impact of domain-specific training corpora on the reconstruction performance is discussed. The AUTOMAP approach to image reconstruction will enable significant image quality improvements at low-field, especially in highly noise-corrupted environments.
1
AUTOMAP outperformed two contemporary image-based denoising pipelines and suppressed noise-like spike artifacts in reconstructed images.
2
AUTOMAP, an end-to-end deep neural network, improves reconstruction quality for highly noise-corrupted low-field MRI data.
3
On human brain data acquired at 6.5 mT, AUTOMAP achieved signal-to-noise gains of 1.5- to 4.5-fold over Fourier reconstruction.
4
On plant root data acquired at 47 mT, AUTOMAP produced a threefold signal-to-noise gain over Fourier reconstruction.
5
Reconstruction performance depends on the domain-specific training corpus, highlighting the importance of matched training data.

highly noise-corrupted low-field MRI data from human brain and plant root imaging at 6.5 mT and 47 mT

image-quality and signal-to-noise improvement through deep-learning MRI reconstruction, including suppression of noise-like spike artifacts

Publication Details
Publication Date
2021-04-15
Journal
Publisher
ISSN
Cited by
168
Access Type
Author Information
Authors
Matthew Scott Rosen
Bo Zhu
G. Cody Bagnall
Néha Koonjoo
Danyal Fareed Bhutto
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%