A Physics-based Generative Model to Synthesize Training Datasets for MRI-based Fat Quantification
Saved in:
| Published in: | arXiv.org (Dec 11, 2024), p. n/a |
|---|---|
| Main Author: | |
| Other Authors: | , , , |
| Published: |
Cornell University Library, arXiv.org
|
| Subjects: | |
| Online Access: | Citation/Abstract Full text outside of ProQuest |
| Tags: |
No Tags, Be the first to tag this record!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3144199254 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3144199254 | ||
| 045 | 0 | |b d20241211 | |
| 100 | 1 | |a Meneses, Juan P | |
| 245 | 1 | |a A Physics-based Generative Model to Synthesize Training Datasets for MRI-based Fat Quantification | |
| 260 | |b Cornell University Library, arXiv.org |c Dec 11, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Deep learning-based techniques have potential to optimize scan and post-processing times required for MRI-based fat quantification, but they are constrained by the lack of large training datasets. Generative models are a promising tool to perform data augmentation by synthesizing realistic datasets. However no previous methods have been specifically designed to generate datasets for quantitative MRI (q-MRI) tasks, where reference quantitative maps and large variability in scanning protocols are usually required. We propose a Physics-Informed Latent Diffusion Model (PI-LDM) to synthesize quantitative parameter maps jointly with customizable MR images by incorporating the signal generation model. We assessed the quality of PI-LDM's synthesized data using metrics such as the Fréchet Inception Distance (FID), obtaining comparable scores to state-of-the-art generative methods (FID: 0.0459). We also trained a U-Net for the MRI-based fat quantification task incorporating synthetic datasets. When we used a few real (10 subjects, \(~200\) slices) and numerous synthetic samples (\(>3000\)), fat fraction at specific liver ROIs showed a low bias on data obtained using the same protocol than training data (\(0.10\%\) at \(\hbox{ROI}_1\), \(0.12\%\) at \(\hbox{ROI}_2\)) and on data acquired with an alternative protocol (\(0.14\%\) at \(\hbox{ROI}_1\), \(0.62\%\) at \(\hbox{ROI}_2\)). Future work will be to extend PI-LDM to other q-MRI applications. | |
| 653 | |a Datasets | ||
| 653 | |a Data augmentation | ||
| 653 | |a Data acquisition | ||
| 653 | |a Signal generation | ||
| 653 | |a Image quality | ||
| 653 | |a Machine learning | ||
| 653 | |a Signal quality | ||
| 653 | |a Synthetic data | ||
| 700 | 1 | |a Yasmeen, George | |
| 700 | 1 | |a Hagemeyer, Christoph | |
| 700 | 1 | |a Chen, Zhaolin | |
| 700 | 1 | |a Uribe, Sergio | |
| 773 | 0 | |t arXiv.org |g (Dec 11, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3144199254/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2412.08741 |