Application of a 1H brain MRS benchmark dataset to deep learning for out-of-voxel artifacts
Author:
Gudmundson Aaron T.12, Davies-Jenkins Christopher W.12, Özdemir İpek12, Murali-Manohar Saipavitra12, Zöllner Helge J.12, Song Yulu12, Hupfeld Kathleen E.12, Schnitzler Alfons3, Oeltzschner Georg12, Stark Craig E. L.4, Edden Richard A. E.12
Affiliation:
1. Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins School of Medicine, Baltimore, MD, United States 2. F. M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD, United States 3. Institute of Clinical Neuroscience and Medical Psychology, Medical Faculty, Heinrich-Heine-University Düsseldorf, Düsseldorf, Germany 4. Department of Neurobiology and Behavior, University of California, Irvine, Irvine, CA, United States
Abstract
Abstract
Neural networks are potentially valuable for many of the challenges associated with MRS data. The purpose of this manuscript is to describe the AGNOSTIC dataset, which contains 259,200 synthetic 1H MRS examples for training and testing neural networks. AGNOSTIC was created using 270 basis sets that were simulated across 18 field strengths and 15 echo times. The synthetic examples were produced to resemble in vivo brain data with combinations of metabolite, macromolecule, residual water signals, and noise. To demonstrate the utility, we apply AGNOSTIC to train two Convolutional Neural Networks (CNNs) to address out-of-voxel (OOV) echoes. A Detection Network was trained to identify the point-wise presence of OOV echoes, providing proof of concept for real-time detection. A Prediction Network was trained to reconstruct OOV echoes, allowing subtraction during post-processing. Complex OOV signals were mixed into 85% of synthetic examples to train two separate CNNs for the detection and prediction of OOV signals. AGNOSTIC is available through Dryad, and all Python 3 code is available through GitHub. The Detection network was shown to perform well, identifying 95% of OOV echoes. Traditional modeling of these detected OOV signals was evaluated and may prove to be an effective method during linear-combination modeling. The Prediction Network greatly reduces OOV echoes within FIDs and achieved a median log10 normed-MSE of—1.79, an improvement of almost two orders of magnitude.
Reference91 articles.
1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M.,… Zheng, X. (2015). Tensorflow: Large-scale Machine Learning on Heterogeneous Distributed Systems. https://research.google/pubs/pub45166/ 2. Relaxation effects in nuclear magnetic resonance absorption;Bloembergen;Physical Review,1948 3. Density Matrix Theory and Applications 4. Reflections of pathways: A short perspective on ‘selection of coherence transfer pathways in NMR pulse experiments.’;Bodenhausen;Journal of Magnetic Resonance,2011
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|