Yan Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yan Tang has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
Jiang Xin
School of Computer Science and Engineering, Central South University, Changsha, People’s Republic of China
4 shared publicationsQiuping Huang
National Clinical Research Center for Mental Disorders, and Department of Psychiatry, The Second Xiangya Hospital of Central South University
3 shared publicationsShucai Huang
School of Computer Science and engineering, Central South University, Changsha, China
3 shared publications- Chengyuan Zhang
College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
2 shared publications - Fang Huang
Central South University
2 shared publications - Hao Zhang
Department of Physical Education and Research, Central South University, Changsha 410083, China
2 shared publications
Latest Publications
- 17 July 2026
- Published by Springer Nature
- p. 384-395
RAG2: Reinforcement Learning and Multi-agent Synergy for Graph-Enhanced Retrieval-Augmented Generation
- 17 July 2026
- Published by Springer Nature
- p. 384-395
RAG2: Reinforcement Learning and Multi-agent Synergy for Graph-Enhanced Retrieval-Augmented Generation
- 6 September 2023
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 61 (12) , 3335-3344
3DCNN predicting brain age using diffusion tensor imaging
Neuroimaging-based brain age prediction using deep learning is gaining popularity. However, few studies have attempted to leverage diffusion tensor imaging (DTI) to predict brain age. In this study, we proposed a 3D convolutional neural network model (3DCNN) and trained it on fractional anisotropy (FA) data from six publicly available datasets (n = 2406, age = 17–60) to estimate brain age. Implementing a two-loop nested cross-validation scheme with a tenfold cross-validation procedure, we achieved a robust prediction performance of a mean absolute error (MAE) of 2.785 and a correlation coefficient of 0.932. We also employed Grad-Cam++ to visualize the salient features of the proposed model. We identified a few highly salient fiber tracts, including the genu of corpus callosum and the left cerebellar peduncle, among others that play a pivotal role in our model. In sum, our model reliably predicted brain age and provided novel insight into age-related changes in brains’ axonal structure. Graphical Abstract
- 6 September 2023
- Published by Springer Nature in Medical & Biological Engineering & Computing
- Vol. 61 (12) , 3335-3344
3DCNN predicting brain age using diffusion tensor imaging
Neuroimaging-based brain age prediction using deep learning is gaining popularity. However, few studies have attempted to leverage diffusion tensor imaging (DTI) to predict brain age. In this study, we proposed a 3D convolutional neural network model (3DCNN) and trained it on fractional anisotropy (FA) data from six publicly available datasets (n = 2406, age = 17–60) to estimate brain age. Implementing a two-loop nested cross-validation scheme with a tenfold cross-validation procedure, we achieved a robust prediction performance of a mean absolute error (MAE) of 2.785 and a correlation coefficient of 0.932. We also employed Grad-Cam++ to visualize the salient features of the proposed model. We identified a few highly salient fiber tracts, including the genu of corpus callosum and the left cerebellar peduncle, among others that play a pivotal role in our model. In sum, our model reliably predicted brain age and provided novel insight into age-related changes in brains’ axonal structure. Graphical Abstract
- 1 February 2022
- Published by Springer Nature in Interdisciplinary Sciences: Computational Life Sciences
- Vol. 14 (2) , 532-544
Sex Differences of Cerebellum and Cerebrum: Evidence from Graph Convolutional Network
This work aims to exploit a novel graph neural network to predict the sex of the brain topological network, and to find the sex differences in the cerebrum and cerebellum. A two-branch multi-scale graph convolutional network (TMGCN) is designed to analyze the sex differences of the brain. Two complementary templates are used to construct cerebrum and cerebellum networks, respectively, followed by a two-branch sub-network with multi-scale filters and a trainable weighted fusion strategy for the final prediction. Finally, a trainable graph topk-pooling layer is utilized in our model to visualize key brain regions relevant to the prediction. The proposed TMGCN achieves a prediction accuracy of 84.48%. In the cerebellum, the bilateral Crus I–II, lobule VI and VIIb, and the posterior vermis (VI–X) are discriminative for this task. As for the cerebrum, the discriminative brain regions consist of the bilateral inferior temporal gyrus, the bilateral fusiform gyrus, the bilateral parahippocampal gyrus, the bilateral cingulate gyrus, the bilateral medial ventral occipital cortex, the bilateral lateral occipital cortex, the bilateral amygdala, and the bilateral hippocampus. This study tackles the sex prediction problem from a more comprehensive view, and may provide the resting-state fMRI evidence for further study of sex differences in the cerebellum and cerebrum. Graphical Abstract
- 1 February 2022
- Published by Springer Nature in Interdisciplinary Sciences: Computational Life Sciences
- Vol. 14 (2) , 532-544
Sex Differences of Cerebellum and Cerebrum: Evidence from Graph Convolutional Network
This work aims to exploit a novel graph neural network to predict the sex of the brain topological network, and to find the sex differences in the cerebrum and cerebellum. A two-branch multi-scale graph convolutional network (TMGCN) is designed to analyze the sex differences of the brain. Two complementary templates are used to construct cerebrum and cerebellum networks, respectively, followed by a two-branch sub-network with multi-scale filters and a trainable weighted fusion strategy for the final prediction. Finally, a trainable graph topk-pooling layer is utilized in our model to visualize key brain regions relevant to the prediction. The proposed TMGCN achieves a prediction accuracy of 84.48%. In the cerebellum, the bilateral Crus I–II, lobule VI and VIIb, and the posterior vermis (VI–X) are discriminative for this task. As for the cerebrum, the discriminative brain regions consist of the bilateral inferior temporal gyrus, the bilateral fusiform gyrus, the bilateral parahippocampal gyrus, the bilateral cingulate gyrus, the bilateral medial ventral occipital cortex, the bilateral lateral occipital cortex, the bilateral amygdala, and the bilateral hippocampus. This study tackles the sex prediction problem from a more comprehensive view, and may provide the resting-state fMRI evidence for further study of sex differences in the cerebellum and cerebrum. Graphical Abstract
- 1 January 2022
- Published by Journal of Systems Science and Information (JSSI) in Journal of Systems Science and Information
- Vol. 10 (2) , 193-202
DIUN: Deeper Inception U-Network for Recovering Partial Pixelated Images
In our daily life, it is nothing strange to see pixelated images that are spoiled artificially to hide certain information for protecting privacy or pixelated deliberately to cover up bad behaviors even crimes. To prevent these phenomena and recover the true information from pixelated images, it is meaningful to research an effective reconstruction method for recovering pixelated images. This paper aims at recovering the artificial partial pixelated images via deep learning (DL). To abstract more abundant features and enhance the repair ability of DL model, we propose a new DL structure, called deeper inception U-Net, to act as the generator of a generative adversarial network. We combine the feature loss with structural similarity index measure loss as the context loss to minimize the distance between feature maps of clear images and the generated images, which helps to improve the quality of repair images. After obtaining inception features, we use fusion layer to adaptively learn features in each inception block. To evaluate the performance of our model, we introduce a new home dataset that contains 10174 clear home images with corresponding pixelated images. A series of experiments show that our model has ability to rebuild pixelated images.
- 1 January 2022
- Published by Journal of Systems Science and Information (JSSI) in Journal of Systems Science and Information
- Vol. 10 (2) , 193-202
DIUN: Deeper Inception U-Network for Recovering Partial Pixelated Images
In our daily life, it is nothing strange to see pixelated images that are spoiled artificially to hide certain information for protecting privacy or pixelated deliberately to cover up bad behaviors even crimes. To prevent these phenomena and recover the true information from pixelated images, it is meaningful to research an effective reconstruction method for recovering pixelated images. This paper aims at recovering the artificial partial pixelated images via deep learning (DL). To abstract more abundant features and enhance the repair ability of DL model, we propose a new DL structure, called deeper inception U-Net, to act as the generator of a generative adversarial network. We combine the feature loss with structural similarity index measure loss as the context loss to minimize the distance between feature maps of clear images and the generated images, which helps to improve the quality of repair images. After obtaining inception features, we use fusion layer to adaptively learn features in each inception block. To evaluate the performance of our model, we introduce a new home dataset that contains 10174 clear home images with corresponding pixelated images. A series of experiments show that our model has ability to rebuild pixelated images.
- Open Access
- 30 August 2021
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 12
Identification of Methamphetamine Abstainers by Resting-State Functional Magnetic Resonance Imaging
Methamphetamine (MA) can cause brain structural and functional impairment, but there are few studies on whether this difference will sustain on MA abstainers. The purpose of this study is to investigate the correlation of brain networks in MA abstainers. In this study, 47 people detoxified for at least 14 months and 44 normal people took a resting-state functional magnetic resonance imaging (RS-fMRI) scan. A dynamic (i.e., time-varying) functional connectivity (FC) is obtained by applying sliding windows in the time courses on the independent components (ICs). The windowed correlation data for each IC were then clustered by k-means. The number of subjects in each cluster was used as a new feature for individual identification. The results show that the classifier achieved satisfactory performance (82.3% accuracy, 77.7% specificity, and 85.7% sensitivity). We find that there are significant differences in the brain networks of MA abstainers and normal people in the time domain, but the spatial differences are not obvious. Most of the altered functional connections (time-varying) are identified to be located at dorsal default mode network. These results have shown that changes in the correlation of the time domain may play an important role in identifying MA abstainers. Therefore, our findings provide valuable insights in the identification of MA and elucidate the pathological mechanism of MA from a resting-state functional integration point of view.
- 30 August 2021
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 12
Open AccessIdentification of Methamphetamine Abstainers by Resting-State Functional Magnetic Resonance Imaging
Methamphetamine (MA) can cause brain structural and functional impairment, but there are few studies on whether this difference will sustain on MA abstainers. The purpose of this study is to investigate the correlation of brain networks in MA abstainers. In this study, 47 people detoxified for at least 14 months and 44 normal people took a resting-state functional magnetic resonance imaging (RS-fMRI) scan. A dynamic (i.e., time-varying) functional connectivity (FC) is obtained by applying sliding windows in the time courses on the independent components (ICs). The windowed correlation data for each IC were then clustered by k-means. The number of subjects in each cluster was used as a new feature for individual identification. The results show that the classifier achieved satisfactory performance (82.3% accuracy, 77.7% specificity, and 85.7% sensitivity). We find that there are significant differences in the brain networks of MA abstainers and normal people in the time domain, but the spatial differences are not obvious. Most of the altered functional connections (time-varying) are identified to be located at dorsal default mode network. These results have shown that changes in the correlation of the time domain may play an important role in identifying MA abstainers. Therefore, our findings provide valuable insights in the identification of MA and elucidate the pathological mechanism of MA from a resting-state functional integration point of view.
- Open Access
- 11 August 2021
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 12
Identifying Methamphetamine Abstainers With Convolutional Neural Networks and Short-Time Fourier Transform
Few studies have investigated the functional patterns of methamphetamine abstainers. A better understanding of the underlying neurobiological mechanism in the brains of methamphetamine abstainers will help to explain their abnormal behaviors. Forty-two male methamphetamine abstainers, currently in a long-term abstinence status (for at least 14 months), and 32 male healthy controls were recruited. All subjects underwent functional MRI while responding to drug-associated cues. This study proposes to combine a convolutional neural network with a short-time Fourier transform to identify different brain patterns between methamphetamine abstainers and controls. The short-time Fourier transformation provides time-localized frequency information, while the convolutional neural network extracts the structural features of the time–frequency spectrograms. The results showed that the classifier achieved a satisfactory performance (98.9% accuracy) and could extract robust brain voxel information. The highly discriminative power voxels were mainly concentrated in the left inferior orbital frontal gyrus, the bilateral postcentral gyri, and the bilateral paracentral lobules. This study provides a novel insight into the different functional patterns between methamphetamine abstainers and healthy controls. It also elucidates the pathological mechanism of methamphetamine abstainers from the view of time–frequency spectrograms.
- 11 August 2021
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 12
Open AccessIdentifying Methamphetamine Abstainers With Convolutional Neural Networks and Short-Time Fourier Transform
Few studies have investigated the functional patterns of methamphetamine abstainers. A better understanding of the underlying neurobiological mechanism in the brains of methamphetamine abstainers will help to explain their abnormal behaviors. Forty-two male methamphetamine abstainers, currently in a long-term abstinence status (for at least 14 months), and 32 male healthy controls were recruited. All subjects underwent functional MRI while responding to drug-associated cues. This study proposes to combine a convolutional neural network with a short-time Fourier transform to identify different brain patterns between methamphetamine abstainers and controls. The short-time Fourier transformation provides time-localized frequency information, while the convolutional neural network extracts the structural features of the time–frequency spectrograms. The results showed that the classifier achieved a satisfactory performance (98.9% accuracy) and could extract robust brain voxel information. The highly discriminative power voxels were mainly concentrated in the left inferior orbital frontal gyrus, the bilateral postcentral gyri, and the bilateral paracentral lobules. This study provides a novel insight into the different functional patterns between methamphetamine abstainers and healthy controls. It also elucidates the pathological mechanism of methamphetamine abstainers from the view of time–frequency spectrograms.
- Open Access
- 28 May 2020
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2020, 1-5
Identifying Methamphetamine Dependence Using Regional Homogeneity in BOLD Signals
Methamphetamine is a highly addictive drug of abuse, which will cause a series of abnormal consequences mentally and physically. This paper is aimed at studying whether the abnormalities of regional homogeneity (ReHo) could be effective features to distinguish individuals with methamphetamine dependence (MAD) from control subjects using machine-learning methods. We made use of resting-state fMRI to measure the regional homogeneity of 41 individuals with MAD and 42 age- and sex-matched control subjects and found that compared with control subjects, individuals with MAD have lower ReHo values in the right medial superior frontal gyrus but higher ReHo values in the right temporal inferior fusiform. In addition, AdaBoost classifier, a pretty effective ensemble learning of machine learning, was employed to classify individuals with MAD from control subjects with abnormal ReHo values. By utilizing the leave-one-out cross-validation method, we got the accuracy more than 84.3%, which means we can almost distinguish individuals with MAD from the control subjects in ReHo values via machine-learning approaches. In a word, our research results suggested that the AdaBoost classifier-neuroimaging approach may be a promising way to find whether a person has been addicted to methamphetamine, and also, this paper shows that resting-state fMRI should be considered as a biomarker, a noninvasive and effective assistant tool for evaluating MAD.
- 28 May 2020
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2020, 1-5
Open AccessIdentifying Methamphetamine Dependence Using Regional Homogeneity in BOLD Signals
Methamphetamine is a highly addictive drug of abuse, which will cause a series of abnormal consequences mentally and physically. This paper is aimed at studying whether the abnormalities of regional homogeneity (ReHo) could be effective features to distinguish individuals with methamphetamine dependence (MAD) from control subjects using machine-learning methods. We made use of resting-state fMRI to measure the regional homogeneity of 41 individuals with MAD and 42 age- and sex-matched control subjects and found that compared with control subjects, individuals with MAD have lower ReHo values in the right medial superior frontal gyrus but higher ReHo values in the right temporal inferior fusiform. In addition, AdaBoost classifier, a pretty effective ensemble learning of machine learning, was employed to classify individuals with MAD from control subjects with abnormal ReHo values. By utilizing the leave-one-out cross-validation method, we got the accuracy more than 84.3%, which means we can almost distinguish individuals with MAD from the control subjects in ReHo values via machine-learning approaches. In a word, our research results suggested that the AdaBoost classifier-neuroimaging approach may be a promising way to find whether a person has been addicted to methamphetamine, and also, this paper shows that resting-state fMRI should be considered as a biomarker, a noninvasive and effective assistant tool for evaluating MAD.
- Open Access
- 8 March 2019
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 13, 185
Brain Differences Between Men and Women: Evidence From Deep Learning
Do men and women have different brains? Previous neuroimage studies sought to answer this question based on morphological difference between specific brain regions, reporting unfortunately conflicting results. In the present study, we aim to use a deep learning technique to address this challenge based on a large open-access, diffusion MRI database recorded from 1,065 young healthy subjects, including 490 men and 575 women healthy subjects. Different from commonly used 2D Convolutional Neural Network (CNN), we proposed a 3D CNN method with a newly designed structure including three hidden layers in cascade with a linear layer and a terminal Softmax layer. The proposed 3D CNN was applied to the maps of factional anisotropy (FA) in the whole-brain as well as specific brain regions. The entropy measure was applied to the lowest-level image features extracted from the first hidden layer to examine the difference of brain structure complexity between men and women. The obtained results compared with the results from using the Support Vector Machine (SVM) and Tract-Based Spatial Statistics (TBSS). The proposed 3D CNN yielded a better classification result (93.3%) than the SVM (78.2%) on the whole-brain FA images, indicating gender-related differences likely exist in the whole-brain range. Moreover, high classification accuracies are also shown in several specific brain regions including the left precuneus, the left postcentral gyrus, the left cingulate gyrus, the right orbital gyrus of frontal lobe, and the left occipital thalamus in the gray matter, and middle cerebellum peduncle, genu of corpus callosum, the right anterior corona radiata, the right superior corona radiata and the left anterior limb of internal capsule in the while matter. This study provides a new insight into the structure difference between men and women, which highlights the importance of considering sex as a biological variable in brain research.
- 8 March 2019
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 13, 185
Open AccessBrain Differences Between Men and Women: Evidence From Deep Learning
Do men and women have different brains? Previous neuroimage studies sought to answer this question based on morphological difference between specific brain regions, reporting unfortunately conflicting results. In the present study, we aim to use a deep learning technique to address this challenge based on a large open-access, diffusion MRI database recorded from 1,065 young healthy subjects, including 490 men and 575 women healthy subjects. Different from commonly used 2D Convolutional Neural Network (CNN), we proposed a 3D CNN method with a newly designed structure including three hidden layers in cascade with a linear layer and a terminal Softmax layer. The proposed 3D CNN was applied to the maps of factional anisotropy (FA) in the whole-brain as well as specific brain regions. The entropy measure was applied to the lowest-level image features extracted from the first hidden layer to examine the difference of brain structure complexity between men and women. The obtained results compared with the results from using the Support Vector Machine (SVM) and Tract-Based Spatial Statistics (TBSS). The proposed 3D CNN yielded a better classification result (93.3%) than the SVM (78.2%) on the whole-brain FA images, indicating gender-related differences likely exist in the whole-brain range. Moreover, high classification accuracies are also shown in several specific brain regions including the left precuneus, the left postcentral gyrus, the left cingulate gyrus, the right orbital gyrus of frontal lobe, and the left occipital thalamus in the gray matter, and middle cerebellum peduncle, genu of corpus callosum, the right anterior corona radiata, the right superior corona radiata and the left anterior limb of internal capsule in the while matter. This study provides a new insight into the structure difference between men and women, which highlights the importance of considering sex as a biological variable in brain research.
- 31 October 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 78 (21) , 30839-30863
Efficient region of visual interests search for geo-multimedia data
- 31 October 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 78 (21) , 30839-30863
Efficient region of visual interests search for geo-multimedia data
- Open Access
Efficient Region of Visual Interests Search for Geo-multimedia Data
With the proliferation of online social networking services and mobile smart devices equipped with mobile communications module and position sensor module, massive amount of multimedia data has been collected, stored and shared. This trend has put forward higher request on massive multimedia data retrieval. In this paper, we investigate a novel spatial query named region of visual interests query (RoVIQ), which aims to search users containing geographical information and visual words. Three baseline methods are presented to introduce how to exploit existing techniques to address this problem. Then we propose the definition of this query and related notions at the first time. To improve the performance of query, we propose a novel spatial indexing structure called quadtree based inverted visual index which is a combination of quadtree, inverted index and visual words. Based on it, we design a efficient search algorithm named region of visual interests search to support RoVIQ. Experimental evaluations on real geo-image datasets demonstrate that our solution outperforms state-of-the-art method.
Open AccessEfficient Region of Visual Interests Search for Geo-multimedia Data
With the proliferation of online social networking services and mobile smart devices equipped with mobile communications module and position sensor module, massive amount of multimedia data has been collected, stored and shared. This trend has put forward higher request on massive multimedia data retrieval. In this paper, we investigate a novel spatial query named region of visual interests query (RoVIQ), which aims to search users containing geographical information and visual words. Three baseline methods are presented to introduce how to exploit existing techniques to address this problem. Then we propose the definition of this query and related notions at the first time. To improve the performance of query, we propose a novel spatial indexing structure called quadtree based inverted visual index which is a combination of quadtree, inverted index and visual words. Based on it, we design a efficient search algorithm named region of visual interests search to support RoVIQ. Experimental evaluations on real geo-image datasets demonstrate that our solution outperforms state-of-the-art method.