1
|
Zheng W, Bao C, Mu R, Wang J, Li T, Zhao Z, Yao Z, Hu B. Frequency-specific dual-attention based adversarial network for blood oxygen level-dependent time series prediction. Hum Brain Mapp 2024; 45:e70032. [PMID: 39329501 DOI: 10.1002/hbm.70032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Revised: 09/03/2024] [Accepted: 09/10/2024] [Indexed: 09/28/2024] Open
Abstract
Functional magnetic resonance imaging (fMRI) is currently one of the most popular technologies for measuring brain activity in both research and clinical contexts. However, clinical constraints often result in short fMRI scan durations, limiting the diagnostic performance for brain disorders. To address this limitation, we developed an end-to-end frequency-specific dual-attention-based adversarial network (FDAA-Net) to extend the time series of existing blood oxygen level-dependent (BOLD) data, enhancing their diagnostic utility. Our approach leverages the frequency-dependent nature of fMRI signals using variational mode decomposition (VMD), which adaptively tracks brain activity across different frequency bands. We integrated the generative adversarial network (GAN) with a spatial-temporal attention mechanism to fully capture relationships among spatially distributed brain regions and temporally continuous time windows. We also introduced a novel loss function to estimate the upward and downward trends of each frequency component. We validated FDAA-Net on the Human Connectome Project (HCP) database by comparing the original and predicted time series of brain regions in the default mode network (DMN), a key network activated during rest. FDAA-Net effectively overcame linear frequency-specific challenges and outperformed other popular prediction models. Test-retest reliability experiments demonstrated high consistency between the functional connectivity of predicted outcomes and targets. Furthermore, we examined the clinical applicability of FDAA-Net using short-term fMRI data from individuals with autism spectrum disorder (ASD) and major depressive disorder (MDD). The model achieved a maximum predicted sequence length of 40% of the original scan durations. The prolonged time series improved diagnostic performance by 8.0% for ASD and 11.3% for MDD compared with the original sequences. These findings highlight the potential of fMRI time series prediction to enhance diagnostic power of brain disorders in short fMRI scans.
Collapse
Affiliation(s)
- Weihao Zheng
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
| | - Cong Bao
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
| | - Renhui Mu
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
| | - Jun Wang
- Second Clinical School, Lanzhou University, Lanzhou, China
- Department of Magnetic Resonance, Lanzhou University Second Hospital, Lanzhou, China
| | - Tongtong Li
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
| | - Ziyang Zhao
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
| | - Zhijun Yao
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
| | - Bin Hu
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, China
- School of Medical Technology, Beijing Institute of Technology, Beijing, China
- CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, China
- Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors, Chinese Academy of Sciences, Lanzhou, China
| |
Collapse
|
2
|
Ji Y, Silva RF, Adali T, Wen X, Zhu Q, Jiang R, Zhang D, Qi S, Calhoun VD. Joint multi-site domain adaptation and multi-modality feature selection for the diagnosis of psychiatric disorders. Neuroimage Clin 2024; 43:103663. [PMID: 39226701 DOI: 10.1016/j.nicl.2024.103663] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2024] [Revised: 08/18/2024] [Accepted: 08/25/2024] [Indexed: 09/05/2024]
Abstract
Identifying biomarkers for computer-aided diagnosis (CAD) is crucial for early intervention of psychiatric disorders. Multi-site data have been utilized to increase the sample size and improve statistical power, while multi-modality classification offers significant advantages over traditional single-modality based approaches for diagnosing psychiatric disorders. However, inter-site heterogeneity and intra-modality heterogeneity present challenges to multi-site and multi-modality based classification. In this paper, brain functional and structural networks (BFNs/BSNs) from multiple sites were constructed to establish a joint multi-site multi-modality framework for psychiatric diagnosis. To do this we developed a hypergraph based multi-source domain adaptation (HMSDA) which allowed us to transform source domain subjects into a target domain. A local ordinal structure based multi-task feature selection (LOSMFS) approach was developed by integrating the transformed functional and structural connections (FCs/SCs). The effectiveness of our method was validated by evaluating diagnosis of both schizophrenia (SZ) and autism spectrum disorder (ASD). The proposed method obtained accuracies of 92.2 %±2.22 % and 84.8 %±2.68 % for the diagnosis of SZ and ASD, respectively. We also compared with 6 DA, 10 multi-modality feature selection, and 8 multi-site and multi-modality methods. Results showed the proposed HMSDA+LOSMFS effectively integrated multi-site and multi-modality data to enhance psychiatric diagnosis and identify disorder-specific diagnostic brain connections.
Collapse
Affiliation(s)
- Yixin Ji
- Department of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China
| | - Rogers F Silva
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA
| | - Tülay Adali
- Department of CSEE, University of Maryland, USA
| | - Xuyun Wen
- Department of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China
| | - Qi Zhu
- Department of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China
| | - Rongtao Jiang
- Department of Psychiatry and Neuroscience, Yale School of Medicine, New Haven, CT, USA
| | - Daoqiang Zhang
- Department of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China.
| | - Shile Qi
- Department of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China; Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China.
| | - Vince D Calhoun
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA
| |
Collapse
|
3
|
Li T, Guo Y, Zhao Z, Chen M, Lin Q, Hu X, Yao Z, Hu B. Automated Diagnosis of Major Depressive Disorder With Multi-Modal MRIs Based on Contrastive Learning: A Few-Shot Study. IEEE Trans Neural Syst Rehabil Eng 2024; 32:1566-1576. [PMID: 38512734 DOI: 10.1109/tnsre.2024.3380357] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/23/2024]
Abstract
Depression ranks among the most prevalent mood-related psychiatric disorders. Existing clinical diagnostic approaches relying on scale interviews are susceptible to individual and environmental variations. In contrast, the integration of neuroimaging techniques and computer science has provided compelling evidence for the quantitative assessment of major depressive disorder (MDD). However, one of the major challenges in computer-aided diagnosis of MDD is to automatically and effectively mine the complementary cross-modal information from limited datasets. In this study, we proposed a few-shot learning framework that integrates multi-modal MRI data based on contrastive learning. In the upstream task, it is designed to extract knowledge from heterogeneous data. Subsequently, the downstream task is dedicated to transferring the acquired knowledge to the target dataset, where a hierarchical fusion paradigm is also designed to integrate features across inter- and intra-modalities. Lastly, the proposed model was evaluated on a set of multi-modal clinical data, achieving average scores of 73.52% and 73.09% for accuracy and AUC, respectively. Our findings also reveal that the brain regions within the default mode network and cerebellum play a crucial role in the diagnosis, which provides further direction in exploring reproducible biomarkers for MDD diagnosis.
Collapse
|
4
|
Liu J, Yang W, Ma Y, Dong Q, Li Y, Hu B. Effective hyper-connectivity network construction and learning: Application to major depressive disorder identification. Comput Biol Med 2024; 171:108069. [PMID: 38394798 DOI: 10.1016/j.compbiomed.2024.108069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2023] [Revised: 01/08/2024] [Accepted: 01/27/2024] [Indexed: 02/25/2024]
Abstract
Functional connectivity (FC) derived from resting-state fMRI (rs-fMRI) is a primary approach for identifying brain diseases, but it is limited to capturing the pairwise correlation between regions-of-interest (ROIs) in the brain. Thus, hyper-connectivity which describes the higher-order relationship among multiple ROIs is receiving increasing attention. However, most hyper-connectivity methods overlook the directionality of connections. The direction of information flow constitutes a pivotal factor in shaping brain activity and cognitive processes. Neglecting this directional aspect can lead to an incomplete understanding of high-order interactions within the brain. To this end, we propose a novel effective hyper-connectivity (EHC) network that integrates direction detection and hyper-connectivity modeling. It characterizes the high-order directional information flow among multiple ROIs, providing a more comprehensive understanding of brain activity. Then, we develop a directed hypergraph convolutional network (DHGCN) to acquire deep representations from EHC network and functional indicators of ROIs. In contrast to conventional hypergraph convolutional networks designed for undirected hypergraphs, DHGCN is specifically tailored to handle directed hypergraph data structures. Moreover, unlike existing methods that primarily focus on fMRI time series, our proposed DHGCN model also incorporates multiple functional indicators, providing a robust framework for feature learning. Finally, deep representations generated via DHGCN, combined with demographic factors, are used for major depressive disorder (MDD) identification. Experimental results demonstrate that the proposed framework outperforms both FC and undirected hyper-connectivity models, as well as surpassing other state-of-the-art methods. The identification of EHC abnormalities through our framework can enhance the analysis of brain function in individuals with MDD.
Collapse
Affiliation(s)
- Jingyu Liu
- Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, and the School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China
| | - Wenxin Yang
- School of Information Science and Engineering, Lanzhou University, 730000, Lanzhou, China
| | - Yulan Ma
- School of Automation Science and Electrical Engineering, State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, 100191, China
| | - Qunxi Dong
- Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, and the School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China.
| | - Yang Li
- School of Automation Science and Electrical Engineering, State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, 100191, China.
| | - Bin Hu
- Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, and the School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China.
| |
Collapse
|
5
|
Luo Y, Chen W, Zhan L, Qiu J, Jia T. Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI. Neuroimage 2024; 285:120497. [PMID: 38142755 DOI: 10.1016/j.neuroimage.2023.120497] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2023] [Revised: 11/21/2023] [Accepted: 12/11/2023] [Indexed: 12/26/2023] Open
Abstract
Major depressive disorder (MDD) is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is increasingly applied in the diagnosis and pathological research of MDD. Different machine learning algorithms are then developed to exploit the rich information in rsfMRI and discriminate MDD patients from normal controls. Despite recent advances reported, the MDD discrimination accuracy has room for further improvement. The generalizability and interpretability of the discrimination method are not sufficiently addressed either. Here, we propose a machine learning method (MFMC) for MDD discrimination by concatenating multiple features and stacking multiple classifiers. MFMC is tested on the REST-meta-MDD data set that contains 2428 subjects collected from 25 different sites. MFMC yields 96.9% MDD discrimination accuracy, demonstrating a significant improvement over existing methods. In addition, the generalizability of MFMC is validated by the good performance when the training and testing subjects are from independent sites. The use of XGBoost as the meta classifier allows us to probe the decision process of MFMC. We identify 13 feature values related to 9 brain regions including the posterior cingulate gyrus, superior frontal gyrus orbital part, and angular gyrus, which contribute most to the classification and also demonstrate significant differences at the group level. The use of these 13 feature values alone can reach 87% of MFMC's full performance when taking all feature values. These features may serve as clinically useful diagnostic and prognostic biomarkers for MDD in the future.
Collapse
Affiliation(s)
- Yunsong Luo
- College of Computer and Information Science, Southwest University, Chongqing, 400715, PR China.
| | - Wenyu Chen
- College of Computer and Information Science, Southwest University, Chongqing, 400715, PR China.
| | - Ling Zhan
- College of Computer and Information Science, Southwest University, Chongqing, 400715, PR China.
| | - Jiang Qiu
- Key Laboratory of Cognition and Personality (SWU), Ministry of Education, Chongqing, 400715, PR China; School of Psychology, Southwest University (SWU), Chongqing, 400715, PR China; Southwest University Branch, Collaborative Innovation Center of Assessment Toward Basic Education Quality at Beijing Normal University, Chongqing, 400715, PR China.
| | - Tao Jia
- College of Computer and Information Science, Southwest University, Chongqing, 400715, PR China.
| |
Collapse
|
6
|
Zheng G, Zheng W, Zhang Y, Wang J, Chen M, Wang Y, Cai T, Yao Z, Hu B. An attention-based multi-modal MRI fusion model for major depressive disorder diagnosis. J Neural Eng 2023; 20:066005. [PMID: 37844568 DOI: 10.1088/1741-2552/ad038c] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 10/16/2023] [Indexed: 10/18/2023]
Abstract
Objective.Major depressive disorder (MDD) is one of the biggest threats to human mental health. MDD is characterized by aberrant changes in both structure and function of the brain. Although recent studies have developed some deep learning models based on multi-modal magnetic resonance imaging (MRI) for MDD diagnosis, the latent associations between deep features derived from different modalities were largely unexplored by previous studies, which we hypothesized may have potential benefits in improving the diagnostic accuracy of MDD.Approach.In this study, we proposed a novel deep learning model that fused both structural MRI (sMRI) and resting-state MRI (rs-fMRI) data to enhance the diagnosis of MDD by capturing the interactions between deep features extracted from different modalities. Specifically, we first employed a brain function encoder (BFE) and a brain structure encoder (BSE) to extract the deep features from fMRI and sMRI, respectively. Then, we designed a function and structure co-attention fusion (FSCF) module that captured inter-modal interactions and adaptively fused multi-modal deep features for MDD diagnosis.Main results.This model was evaluated on a large cohort and achieved a high classification accuracy of 75.2% for MDD diagnosis. Moreover, the attention distribution of the FSCF module assigned higher attention weights to structural features than functional features for diagnosing MDD.Significance.The high classification accuracy highlights the effectiveness and potential clinical of the proposed model.
Collapse
Affiliation(s)
- Guowei Zheng
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
- School of Computer Science and Technology, Harbin Institute of Technology, Harbin, People's Republic of China
| | - Weihao Zheng
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Yu Zhang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Junyu Wang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Miao Chen
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Yin Wang
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Tianhong Cai
- Institute of Computer Software and Theory, School of information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Zhijun Yao
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
| | - Bin Hu
- Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University, Lanzhou, People's Republic of China
- School of Medical Technology, Beijing Institute of Technology, Beijing, People's Republic of China
- CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Shanghai, People's Republic of China
- Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors, Chinese Academy of Sciences, Lanzhou, People's Republic of China
| |
Collapse
|
7
|
Wang C, Zhang L, Zhang J, Qiao L, Liu M. Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification. J Pers Med 2023; 13:jpm13020251. [PMID: 36836485 PMCID: PMC9958959 DOI: 10.3390/jpm13020251] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2022] [Revised: 12/27/2022] [Accepted: 01/13/2023] [Indexed: 01/31/2023] Open
Abstract
Background: Functional brain networks (FBNs) derived from resting-state functional MRI (rs-fMRI) have shown great potential in identifying brain disorders, such as autistic spectrum disorder (ASD). Therefore, many FBN estimation methods have been proposed in recent years. Most existing methods only model the functional connections between brain regions of interest (ROIs) from a single view (e.g., by estimating FBNs through a specific strategy), failing to capture the complex interactions among ROIs in the brain. Methods: To address this problem, we propose fusion of multiview FBNs through joint embedding, which can make full use of the common information of multiview FBNs estimated by different strategies. More specifically, we first stack the adjacency matrices of FBNs estimated by different methods into a tensor and use tensor factorization to learn the joint embedding (i.e., a common factor of all FBNs) for each ROI. Then, we use Pearson's correlation to calculate the connections between each embedded ROI in order to reconstruct a new FBN. Results: Experimental results obtained on the public ABIDE dataset with rs-fMRI data reveal that our method is superior to several state-of-the-art methods in automated ASD diagnosis. Moreover, by exploring FBN "features" that contributed most to ASD identification, we discovered potential biomarkers for ASD diagnosis. The proposed framework achieves an accuracy of 74.46%, which is generally better than the compared individual FBN methods. In addition, our method achieves the best performance compared to other multinetwork methods, i.e., an accuracy improvement of at least 2.72%. Conclusions: We present a multiview FBN fusion strategy through joint embedding for fMRI-based ASD identification. The proposed fusion method has an elegant theoretical explanation from the perspective of eigenvector centrality.
Collapse
Affiliation(s)
- Chengcheng Wang
- School of Mathematics Science, Liaocheng University, Liaocheng 252000, China
| | - Limei Zhang
- School of Computer Science and Technology, Shandong Jianzhu University, Jinan 250101, China
- Correspondence: (L.Z.); (M.L.)
| | - Jinshan Zhang
- College of Mathematics and Statistics, Sichuan University of Science and Engineering, Zigong 643000, China
| | - Lishan Qiao
- School of Mathematics Science, Liaocheng University, Liaocheng 252000, China
| | - Mingxia Liu
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA
- Correspondence: (L.Z.); (M.L.)
| |
Collapse
|
8
|
Zhu M, Quan Y, He X. The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network. Front Hum Neurosci 2023; 17:1094592. [PMID: 36778038 PMCID: PMC9908753 DOI: 10.3389/fnhum.2023.1094592] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2022] [Accepted: 01/12/2023] [Indexed: 01/27/2023] Open
Abstract
Introduction The early diagnosis of major depressive disorder (MDD) is very important for patients that suffer from severe and irreversible consequences of depression. It has been indicated that functional connectivity (FC) analysis based on functional magnetic resonance imaging (fMRI) data can provide valuable biomarkers for clinical diagnosis. However, previous studies mainly focus on brain disease classification in small sample sizes, which may lead to dramatic divergences in classification accuracy. Methods This paper attempts to address this limitation by applying the deep graph convolutional neural network (DGCNN) method on a large multi-site MDD dataset. The resting-state fMRI data are acquired from 830 MDD patients and 771 normal controls (NC) shared by the REST-meta-MDD consortium. Results The DGCNN model trained with the binary network after thresholding, identified MDD patients from normal controls and achieved an accuracy of 72.1% with 10-fold cross-validation, which is 12.4%, 9.8%, and 7.6% higher than SVM, RF, and GCN, respectively. Moreover, the process of dataset reading and model training is faster. Therefore, it demonstrates the advantages of the DGCNN model with low time complexity and sound classification performance. Discussion Based on a large, multi-site dataset from MDD patients, the results expressed that DGCNN is not an extremely accurate method for MDD diagnosis. However, there is an improvement over previous methods with our goal of better understanding brain function and ultimately providing a biomarker or diagnostic capability for MDD diagnosis.
Collapse
Affiliation(s)
- Manyun Zhu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Yu Quan
- Information Center of Shengjing Hospital of China Medical University, Shenyang, China
| | - Xuan He
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China,*Correspondence: Xuan He,
| |
Collapse
|