Kaile Zhang

Dr. Kaile Zhang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 November 2024 in Tomography
Verified
Journal Article
Open access
PDF file
WZWei Zhang
Wei Zhang
WZWeiming Zeng
Weiming Zeng
HCHongyu Chen
Hongyu Chen
JLJie Liu
Jie Liu
HYHongjie Yan
Hongjie Yan
NWNizhuan Wang
Nizhuan Wang
Background: Early diagnosis of depression is crucial for effective treatment and suicide prevention. Traditional methods rely on self-report questionnaires and clinical assessments, lacking objective biomarkers. Combining functional magnetic resonance imaging (fMRI) with artificial intelligence can enhance depression diagnosis using neuroimaging indicators, but depression-specific fMRI datasets are often small and imbalanced, posing challenges for classification models. New Method: We propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating convolutional neural networks (CNN) and recurrent neural networks (RNN) to capture both temporal and spatial features of brain activity. STANet comprises the following steps: (1) Aggregate spatio-temporal information via independent component analysis (ICA). (2) Utilize multi-scale deep convolution to capture detailed features. (3) Balance data using the synthetic minority over-sampling technique (SMOTE) to generate new samples for minority classes. (4) Employ the attention-Fourier gate recurrent unit (AFGRU) classifier to capture long-term dependencies, with an adaptive weight assignment mechanism to enhance model generalization. Results: STANet achieves superior depression diagnostic performance, with 82.38% accuracy and a 90.72% AUC. The Spatio-Temporal Feature Aggregation module enhances classification by capturing deeper features at multiple scales. The AFGRU classifier, with adaptive weights and a stacked Gated Recurrent Unit (GRU), attains higher accuracy and AUC. SMOTE outperforms other oversampling methods. Additionally, spatio-temporal aggregated features achieve better performance compared to using only temporal or spatial features. Comparison with existing methods: STANet significantly outperforms traditional classifiers, deep learning classifiers, and functional connectivity-based classifiers. Conclusions: The successful performance of STANet contributes to enhancing the diagnosis and treatment assessment of depression in clinical settings on imbalanced and small fMRI.

9 December 2024 in Tomography
Verified
Journal Article
Open access
PDF file
YFYu Feng
Yu Feng
WZWeiming Zeng
Weiming Zeng
YXYifan Xie
Yifan Xie
HCHongyu Chen
Hongyu Chen
LWLei Wang
Lei Wang
NWNizhuan Wang
Nizhuan Wang
Background: Although it has been noticed that depressed patients show differences in processing emotions, the precise neural modulation mechanisms of positive and negative emotions remain elusive. FMRI is a cutting-edge medical imaging technology renowned for its high spatial resolution and dynamic temporal information, making it particularly suitable for the neural dynamics of depression research. Methods: To address this gap, our study firstly leveraged fMRI to delineate activated regions associated with positive and negative emotions in healthy individuals, resulting in the creation of the positive emotion atlas (PEA) and the negative emotion atlas (NEA). Subsequently, we examined neuroimaging changes in depression patients using these atlases and evaluated their diagnostic performance based on machine learning. Results: Our findings demonstrate that the classification accuracy of depressed patients based on PEA and NEA exceeded 0.70, a notable improvement compared to the whole-brain atlases. Furthermore, ALFF analysis unveiled significant differences between depressed patients and healthy controls in eight functional clusters during the NEA, focusing on the left cuneus, cingulate gyrus, and superior parietal lobule. In contrast, the PEA revealed more pronounced differences across fifteen clusters, involving the right fusiform gyrus, parahippocampal gyrus, and inferior parietal lobule. Conclusions: These findings emphasize the complex interplay between emotion modulation and depression, showcasing significant alterations in both PEA and NEA among depression patients. This research enhances our understanding of emotion modulation in depression, with implications for diagnosis and treatment evaluation.

31 December 2025 in Brain and Language
Verified
Journal Article
Open access
RTRan Tao
Ran Tao
KZKaile Zhang
Kaile Zhang
YFYan Feng
Yan Feng
YWYi Weng
Yi Weng
GPGang Peng
Gang Peng
This study investigated the neural basis of lexical tone representation in Cantonese, a complex tone language that contrasts pitch height and slope to convey lexical meaning. We used sparse-sampling fMRI to measure brain activity from native Cantonese speakers performing three tasks involving tonal syllables: passive listening, silent repetition, and word identification. Behavioral performance with high identification rates confirmed effective stimulus processing. Group-level activation and multivariate pattern analyses revealed a distributed bilateral network encompassing the bilateral precentral gyri (PrCG), right superior frontal gyrus (RSFG), bilateral superior temporal gyri (STG), left inferior parietal sulcus (LIPS), and bilateral lingual gyri (BiLG), which reliably encoded tone categories. Using dissimilarity matrices constructed from tonal features and neural activation patterns, representational similarity analysis (RSA) showed bilateral STG encoding pitch height and LIPS processing pitch slope. The frontal regions, LIPS, and BiLG contribute to holistic tone processing. This contrasts with the temporal-parietal network identified in previous Mandarin studies, suggesting that Cantonese tones invoke a bilateral and more extended brain network. The inter-subject RSA results revealed significant brain-behavioral correlations in the frontal and parietal regions, suggesting that these regions are closely associated with tone categorization performance. Other regions showed non-significant correlations, indicating their involvement in tone processing but not directly predicting behavioral performance. Together, these findings enhance our understanding of the neural mechanisms underlying tone perception in complex tonal languages and highlight the intricate role of bilateral cortical networks supporting the representation of complex suprasegmental phonetic features.