Deep-learning-based image reconstruction with limited data: generating synthetic raw data using deep learning

Object Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and impr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Magma (New York, N.Y.) Ročník 37; číslo 6; s. 1059 - 1076
Hlavní autoři: Zijlstra, Frank, While, Peter Thomas
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 01.12.2024
Témata:
Algorithms
Basic Science - Reconstruction algorithms and artificial intelligence
Biomedical Engineering and Bioengineering
Brain - diagnostic imaging
Computer Appl. in Life Sciences
Deep Learning
Health Informatics
Humans
Image Processing, Computer-Assisted - methods
Imaging
Magnetic Resonance Imaging - methods
Medicine
Medicine & Public Health
Neural Networks, Computer
Radiology
Research Article
Solid State Physics
Deep learning
Accelerated MRI
Image reconstruction
Synthetic data
ISSN:1352-8661, 0968-5243, 1352-8661
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Object Deep learning has shown great promise for fast reconstruction of accelerated MRI acquisitions by learning from large amounts of raw data. However, raw data is not always available in sufficient quantities. This study investigates synthetic data generation to complement small datasets and improve reconstruction quality. Materials and methods An adversarial auto-encoder was trained to generate phase and coil sensitivity maps from magnitude images, which were combined into synthetic raw data. On a fourfold accelerated MR reconstruction task, deep-learning-based reconstruction networks were trained with varying amounts of training data (20 to 160 scans). Test set performance was compared between baseline experiments and experiments that incorporated synthetic training data. Results Training with synthetic raw data showed decreasing reconstruction errors with increasing amounts of training data, but importantly this was magnitude-only data, rather than real raw data. For small training sets, training with synthetic data decreased the mean absolute error (MAE) by up to 7.5%, whereas for larger training sets the MAE increased by up to 2.6%. Discussion Synthetic raw data generation improved reconstruction quality in scenarios with limited training data. A major advantage of synthetic data generation is that it allows for the reuse of magnitude-only datasets, which are more readily available than raw datasets.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1352-8661
0968-5243
1352-8661
DOI:10.1007/s10334-024-01193-4