The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification
Brain Sciences · 30.04.2024 · 14 (5) · 456
DOI: 10.3390/brainsci14050456 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 30.04.2024. Verfasst von Nguyen Huynh und 12 weiteren Autor:innen. Beteiligte Einrichtung: Auburn University Neuroimaging Center, Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, USA. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIMH NIH HHS, U.S. Army Medical Research and Development Command (MRDC), NIMH (National Institute of Mental Health, Bethesda, MD, USA).
Abstract (Originalsprache)
Functional connectivity (FC) obtained from resting-state functional magnetic resonance imaging has been integrated with machine learning algorithms to deliver consistent and reliable brain disease classification outcomes. However, in classical learning procedures, custom-built specialized feature selection techniques are typically used to filter out uninformative features from FC patterns to generalize efficiently on the datasets. The ability of convolutional neural networks (CNN) and other deep learning models to extract informative features from data with grid structure (such as images) has led to the surge in popularity of these techniques. However, the designs of many existing CNN models still fail to exploit the relationships between entities of graph-structure data (such as networks). Therefore, graph convolution network (GCN) has been suggested as a means for uncovering the intricate structure of brain network data, which has the potential to substantially improve classification accuracy. Furthermore, overfitting in classifiers can be largely attributed to the limited number of available training samples. Recently, the generative adversarial network (GAN) has been widely used in the medical field for its generative aspect that can generate synthesis images to cope with the problems of data scarcity and patient privacy. In our previous work, GCN and GAN have been designed to investigate FC patterns to perform diagnosis tasks, and their effectiveness has been tested on the ABIDE-I dataset. In this paper, the models will be further applied to FC data derived from more public datasets (ADHD, ABIDE-II, and ADNI) and our in-house dataset (PTSD) to justify their generalization on all types of data. The results of a number of experiments show the powerful characteristic of GAN to mimic FC data to achieve high performance in disease prediction. When employing GAN for data augmentation, the diagnostic accuracy across ADHD-200, ABIDE-II, and ADNI datasets surpasses that of other machine learning models, including results achieved with BrainNetCNN. Specifically, in ADHD, the accuracy increased from 67.74% to 73.96% with GAN, in ABIDE-II from 70.36% to 77.40%, and in ADNI, reaching 52.84% and 88.56% for multiclass and binary classification, respectively. GCN also obtains decent results, with the best accuracy in ADHD datasets at 71.38% for multinomial and 75% for binary classification, respectively, and the second-best accuracy in the ABIDE-II dataset (72.28% and 75.16%, respectively). Both GAN and GCN achieved the highest accuracy for the PTSD dataset, reaching 97.76%. However, there are still some limitations that can be improved. Both methods have many opportunities for the prediction and diagnosis of diseases.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Auburn University Neuroimaging Center, Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, USA.
- Department of Computer Sciences, Indiana University Bloomington, Bloomington, IN 47405, USA.
- Department of Computer Sciences, The Chinese University of Hong Kong, Shatin, Hong Kong.
- Department of Mechanical Engineering, University of California, Berkeley, CA 94720, USA.
- School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore.
- Department of Computer Sciences, University of Alabama at Birmingham, Birmingham, AL 35294, USA.
ORCID-Profile: Mirza Tanzim Sami, Haiquan Chen, Thomas S Denney, Gopikrishna Deshpande
Förderung
- NIMH NIH HHS
- U.S. Army Medical Research and Development Command (MRDC)
- NIMH (National Institute of Mental Health, Bethesda, MD, USA)
- multiple agencies
Zitieren
APA
Huynh, N., Yan, D., Ma, Y., Wu, S., Long, C., Sami, M. T., Almudaifer, A., Jiang, Z., Chen, H., Dretsch, M. N., Denney, T. S., Deshpande, R., & Deshpande, G. (2024). The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification. Brain Sciences, 14(5), 456. https://doi.org/10.3390/brainsci14050456
Vancouver
Huynh N, Yan D, Ma Y, Wu S, Long C, Sami MT, et al. The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification. Brain Sciences. 2024;14(5):456. doi:10.3390/brainsci14050456
BibTeX
@article{Huynh2024,
author = {Huynh, Nguyen and Yan, Da and Ma, Yueen and Wu, Shengbin and Long, Cheng and Sami, Mirza Tanzim and Almudaifer, Abdullateef and Jiang, Zhe and Chen, Haiquan and Dretsch, Michael N and Denney, Thomas S and Deshpande, Rangaprakash and Deshpande, Gopikrishna},
title = {The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification},
journal = {Brain Sciences},
year = {2024},
volume = {14},
number = {5},
pages = {456},
doi = {10.3390/brainsci14050456}
}
EUVIMED