Limin Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Limin Peng has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Dewen Hu
National university of defense technology, Changsha, China
3 shared publications - Ling-Li Zeng
National University of Defense Technology
2 shared publications - Chenyu Wang
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China
1 shared publication - Hong Li
Institute for Brain and Psychological Sciences, Sichuan Normal University, Chengdu, China; School of Psychology, South China Normal University, Guangzhou, China
1 shared publication Huaze Xu
College of Mechatronics and Automation, National University of Defense Technology, Changsha, Hunan, China
1 shared publication- Hui Shen
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China
1 shared publication
Latest Publications
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1474-1487
Feature and Semantic Matching Multisource Domain Adaptation for Diagnostic Classification of Neuropsychiatric Disorders
Multi-site resting-state functional magnetic resonance imaging (rs-fMRI) data have been increasingly utilized for diagnostic classification of neuropsychiatric disorders such as schizophrenia (SCZ) and major depressive disorder (MDD). However, the cross-site generalization ability of deep networks is limited due to the significant inter-site data heterogeneity caused by different MRI scanners or scanning protocols. To address this issue, we propose a feature and semantic matching multi-source domain adaptation method (FSM-MSDA) to learn site-invariant disorder-related feature representations. In FSM-MSDA, we adopt separate feature extractors for multiple source domains, and propose an accurate feature matching module to align the category-level feature distributions across multiple source domains and target domain. In addition, we also propose a semantic feature alignment module to eliminate the distribution discrepancy in high-level semantic features extracted from target samples by different source classifiers. Extensive experiments based on multi-site fMRI data of SCZ and MDD show the superiority and robustness of FSM-MSDA compared to state-of- the-art methods. Besides, FSM-MSDA achieves the average accuracy of 80.8% in the classification of SCZ, meeting the clinically diagnostic accuracy threshold of 80%. Shared discriminative brain regions including the middle temporal gyrus and the cerebellum regions are identified in the diagnostic classification of SCZ and MDD.
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1474-1487
Feature and Semantic Matching Multisource Domain Adaptation for Diagnostic Classification of Neuropsychiatric Disorders
Multi-site resting-state functional magnetic resonance imaging (rs-fMRI) data have been increasingly utilized for diagnostic classification of neuropsychiatric disorders such as schizophrenia (SCZ) and major depressive disorder (MDD). However, the cross-site generalization ability of deep networks is limited due to the significant inter-site data heterogeneity caused by different MRI scanners or scanning protocols. To address this issue, we propose a feature and semantic matching multi-source domain adaptation method (FSM-MSDA) to learn site-invariant disorder-related feature representations. In FSM-MSDA, we adopt separate feature extractors for multiple source domains, and propose an accurate feature matching module to align the category-level feature distributions across multiple source domains and target domain. In addition, we also propose a semantic feature alignment module to eliminate the distribution discrepancy in high-level semantic features extracted from target samples by different source classifiers. Extensive experiments based on multi-site fMRI data of SCZ and MDD show the superiority and robustness of FSM-MSDA compared to state-of- the-art methods. Besides, FSM-MSDA achieves the average accuracy of 80.8% in the classification of SCZ, meeting the clinically diagnostic accuracy threshold of 80%. Shared discriminative brain regions including the middle temporal gyrus and the cerebellum regions are identified in the diagnostic classification of SCZ and MDD.
- Open Access
- 15 July 2024
- Published by Wiley in Human Brain Mapping
- Vol. 45 (10) , e26726
Measuring functional connectivity in frequency‐domain helps to better characterize brain function
Resting‐state functional connectivity (FC) is widely used in multivariate pattern analysis of functional magnetic resonance imaging (fMRI), including identifying the locations of putative brain functional borders, predicting individual phenotypes, and diagnosing clinical mental diseases. However, limited attention has been paid to the analysis of functional interactions from a frequency perspective. In this study, by contrasting coherence‐based and correlation‐based FC with two machine learning tasks, we observed that measuring FC in the frequency domain helped to identify finer functional subregions and achieve better pattern discrimination capability relative to the temporal correlation. This study has proven the feasibility of coherence in the analysis of fMRI, and the results indicate that modeling functional interactions in the frequency domain may provide richer information than that in the time domain, which may provide a new perspective on the analysis of functional neuroimaging.
- 15 July 2024
- Published by Wiley in Human Brain Mapping
- Vol. 45 (10) , e26726
Open AccessMeasuring functional connectivity in frequency‐domain helps to better characterize brain function
Resting‐state functional connectivity (FC) is widely used in multivariate pattern analysis of functional magnetic resonance imaging (fMRI), including identifying the locations of putative brain functional borders, predicting individual phenotypes, and diagnosing clinical mental diseases. However, limited attention has been paid to the analysis of functional interactions from a frequency perspective. In this study, by contrasting coherence‐based and correlation‐based FC with two machine learning tasks, we observed that measuring FC in the frequency domain helped to identify finer functional subregions and achieve better pattern discrimination capability relative to the temporal correlation. This study has proven the feasibility of coherence in the analysis of fMRI, and the results indicate that modeling functional interactions in the frequency domain may provide richer information than that in the time domain, which may provide a new perspective on the analysis of functional neuroimaging.
- Open Access
- 15 August 2018
- Published by Wiley in Brain and Behavior
- Vol. 8 (9) , e01022
Functional connectivity changes in the entorhinal cortex of taxi drivers
Introduction: As a major interface between the hippocampus and the neocortex, the entorhinal cortex (EC) is widely known to play a pivotal role in spatial memory and navigation. Previous studies have suggested that the EC can be divided into the anterior‐lateral (alEC) and the posterior‐medial subregions (pmEC), with the former receiving object‐related information from the perirhinal cortex and the latter receiving scene‐related information from the parahippocampal cortex. However, the functional connectivity maps of the EC subregions in the context of extensive navigation experience remain elusive. In this study, we analyzed the functional connectivity of the EC in subjects with long‐term navigation experience and aimed to find the navigation‐related change in the functional properties of the human EC.Methods: We investigated the resting‐state functional connectivity changes in the EC subregions by comparing the EC functional connectivity maps of 20 taxi drivers with those of 20 nondriver controls. Furthermore, we examined whether the functional connectivity changes of the EC were related to the number of taxi driving years.Results: Significantly reduced functional connectivity was found in the taxi drivers between the left pmEC and the right anterior cingulate cortex (ACC), right angular gyrus, and bilateral precuneus as well as some temporal regions, and between the right pmEC and the left inferior temporal gyrus. Notably, the strength of the functional connectivity between the left pmEC and the left precuneus, as well as the right ACC, was negatively correlated with the years of taxi driving.Conclusion: This is the first study to explore the impact of long‐term navigation experience on the connectivity patterns of the EC, the results of which may shed new light on the potential influence of extensive navigational training on the functional organization of the EC in healthy human brains.
- 15 August 2018
- Published by Wiley in Brain and Behavior
- Vol. 8 (9) , e01022
Open AccessFunctional connectivity changes in the entorhinal cortex of taxi drivers
Introduction: As a major interface between the hippocampus and the neocortex, the entorhinal cortex (EC) is widely known to play a pivotal role in spatial memory and navigation. Previous studies have suggested that the EC can be divided into the anterior‐lateral (alEC) and the posterior‐medial subregions (pmEC), with the former receiving object‐related information from the perirhinal cortex and the latter receiving scene‐related information from the parahippocampal cortex. However, the functional connectivity maps of the EC subregions in the context of extensive navigation experience remain elusive. In this study, we analyzed the functional connectivity of the EC in subjects with long‐term navigation experience and aimed to find the navigation‐related change in the functional properties of the human EC.Methods: We investigated the resting‐state functional connectivity changes in the EC subregions by comparing the EC functional connectivity maps of 20 taxi drivers with those of 20 nondriver controls. Furthermore, we examined whether the functional connectivity changes of the EC were related to the number of taxi driving years.Results: Significantly reduced functional connectivity was found in the taxi drivers between the left pmEC and the right anterior cingulate cortex (ACC), right angular gyrus, and bilateral precuneus as well as some temporal regions, and between the right pmEC and the left inferior temporal gyrus. Notably, the strength of the functional connectivity between the left pmEC and the left precuneus, as well as the right ACC, was negatively correlated with the years of taxi driving.Conclusion: This is the first study to explore the impact of long‐term navigation experience on the connectivity patterns of the EC, the results of which may shed new light on the potential influence of extensive navigational training on the functional organization of the EC in healthy human brains.