1
|
Du Y, Niu J, Xing Y, Li B, Calhoun VD. Neuroimage Analysis Methods and Artificial Intelligence Techniques for Reliable Biomarkers and Accurate Diagnosis of Schizophrenia: Achievements Made by Chinese Scholars Around the Past Decade. Schizophr Bull 2024:sbae110. [PMID: 38982882 DOI: 10.1093/schbul/sbae110] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/11/2024]
Abstract
BACKGROUND AND HYPOTHESIS Schizophrenia (SZ) is characterized by significant cognitive and behavioral disruptions. Neuroimaging techniques, particularly magnetic resonance imaging (MRI), have been widely utilized to investigate biomarkers of SZ, distinguish SZ from healthy conditions or other mental disorders, and explore biotypes within SZ or across SZ and other mental disorders, which aim to promote the accurate diagnosis of SZ. In China, research on SZ using MRI has grown considerably in recent years. STUDY DESIGN The article reviews advanced neuroimaging and artificial intelligence (AI) methods using single-modal or multimodal MRI to reveal the mechanism of SZ and promote accurate diagnosis of SZ, with a particular emphasis on the achievements made by Chinese scholars around the past decade. STUDY RESULTS Our article focuses on the methods for capturing subtle brain functional and structural properties from the high-dimensional MRI data, the multimodal fusion and feature selection methods for obtaining important and sparse neuroimaging features, the supervised statistical analysis and classification for distinguishing disorders, and the unsupervised clustering and semi-supervised learning methods for identifying neuroimage-based biotypes. Crucially, our article highlights the characteristics of each method and underscores the interconnections among various approaches regarding biomarker extraction and neuroimage-based diagnosis, which is beneficial not only for comprehending SZ but also for exploring other mental disorders. CONCLUSIONS We offer a valuable review of advanced neuroimage analysis and AI methods primarily focused on SZ research by Chinese scholars, aiming to promote the diagnosis, treatment, and prevention of SZ, as well as other mental disorders, both within China and internationally.
Collapse
Affiliation(s)
- Yuhui Du
- School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, China
| | - Ju Niu
- School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, China
| | - Ying Xing
- School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, China
| | - Bang Li
- School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, China
| | - Vince D Calhoun
- The Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, 30303, GA, USA
| |
Collapse
|
2
|
Huynh N, Yan D, Ma Y, Wu S, Long C, Sami MT, Almudaifer A, Jiang Z, Chen H, Dretsch MN, Denney TS, Deshpande R, Deshpande G. The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification. Brain Sci 2024; 14:456. [PMID: 38790434 PMCID: PMC11119064 DOI: 10.3390/brainsci14050456] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2024] [Revised: 04/21/2024] [Accepted: 04/23/2024] [Indexed: 05/26/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Nguyen Huynh
- Auburn University Neuroimaging Center, Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, USA; (N.H.); (T.S.D.)
| | - Da Yan
- Department of Computer Sciences, Indiana University Bloomington, Bloomington, IN 47405, USA;
| | - Yueen Ma
- Department of Computer Sciences, The Chinese University of Hong Kong, Shatin, Hong Kong;
| | - Shengbin Wu
- Department of Mechanical Engineering, University of California, Berkeley, CA 94720, USA;
| | - Cheng Long
- School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore;
| | - Mirza Tanzim Sami
- Department of Computer Sciences, University of Alabama at Birmingham, Birmingham, AL 35294, USA; (M.T.S.); (A.A.)
| | - Abdullateef Almudaifer
- Department of Computer Sciences, University of Alabama at Birmingham, Birmingham, AL 35294, USA; (M.T.S.); (A.A.)
- College of Computer Science and Engineering, Taibah University, Yanbu 41477, Saudi Arabia
| | - Zhe Jiang
- Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, USA;
| | - Haiquan Chen
- Department of Computer Sciences, California State University, Sacramento, CA 95819, USA;
| | - Michael N. Dretsch
- Walter Reed Army Institute of Research-West, Joint Base Lewis-McChord, WA 98433, USA;
| | - Thomas S. Denney
- Auburn University Neuroimaging Center, Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, USA; (N.H.); (T.S.D.)
- Department of Psychological Sciences, Auburn University, Auburn, AL 36849, USA
- Alabama Advanced Imaging Consortium, Birmingham, AL 36849, USA
- Center for Neuroscience, Auburn University, Auburn, AL 36849, USA
| | - Rangaprakash Deshpande
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA 02129, USA;
| | - Gopikrishna Deshpande
- Auburn University Neuroimaging Center, Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, USA; (N.H.); (T.S.D.)
- Department of Psychological Sciences, Auburn University, Auburn, AL 36849, USA
- Alabama Advanced Imaging Consortium, Birmingham, AL 36849, USA
- Center for Neuroscience, Auburn University, Auburn, AL 36849, USA
- Department of Psychiatry, National Institute of Mental Health and Neurosciences, Bangalore 560030, India
- Department of Heritage Science and Technology, Indian Institute of Technology, Hyderabad 502285, India
| |
Collapse
|
3
|
Peng L, Luo Z, Zeng LL, Hou C, Shen H, Zhou Z, Hu D. Parcellating the human brain using resting-state dynamic functional connectivity. Cereb Cortex 2022; 33:3575-3590. [PMID: 35965076 DOI: 10.1093/cercor/bhac293] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2022] [Revised: 07/01/2022] [Accepted: 07/02/2022] [Indexed: 11/14/2022] Open
Abstract
Brain cartography has expanded substantially over the past decade. In this regard, resting-state functional connectivity (FC) plays a key role in identifying the locations of putative functional borders. However, scant attention has been paid to the dynamic nature of functional interactions in the human brain. Indeed, FC is typically assumed to be stationary across time, which may obscure potential or subtle functional boundaries, particularly in regions with high flexibility and adaptability. In this study, we developed a dynamic FC (dFC)-based parcellation framework, established a new functional human brain atlas termed D-BFA (DFC-based Brain Functional Atlas), and verified its neurophysiological plausibility by stereo-EEG data. As the first dFC-based whole-brain atlas, the proposed D-BFA delineates finer functional boundaries that cannot be captured by static FC, and is further supported by good correspondence with cytoarchitectonic areas and task activation maps. Moreover, the D-BFA reveals the spatial distribution of dynamic variability across the brain and generates more homogenous parcels compared with most alternative parcellations. Our results demonstrate the superiority and practicability of dFC in brain parcellation, providing a new template to exploit brain topographic organization from a dynamic perspective. The D-BFA will be publicly available for download at https://github.com/sliderplm/D-BFA-618.
Collapse
Affiliation(s)
- Limin Peng
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
| | - Zhiguo Luo
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
| | - Ling-Li Zeng
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
| | - Chenping Hou
- College of Science, National University of Defense Technology, Changsha 410073, China
| | - Hui Shen
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
| | - Zongtan Zhou
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
| | - Dewen Hu
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
| |
Collapse
|