HTHaoteng Tang

Haoteng Tang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Haoteng Tang has a total of 70 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DRE: An effective dual-refined method for integrating small and large language models in open-domain dialogue evaluation

    by Kun Zhao, Bohao Yang, Chen Tang, Siyuan Dai, Haoteng Tang, Chenghua Lin, Liang Zhan

  • Open Access

    Interpretable multimodal learning for integrating neuroimaging and genetic data in Alzheimer’s disease

    by Kun Zhao, Siyuan Dai, Yingying Zhang, Guodong Liu, Pengfei Gu, Chenghua Lin, Paul M. Thompson, Alex Leow, Heng Huang, Lifang He, et al.

    Introduction: Early detection of Alzheimer's disease (AD) requires models that combine brain structure changes with genetic risk, but existing methods struggle to align these different data types. Methods: We present R-GenIMA, an interpretable multimodal large language model that pairs a region-of-interest vision transformer with genetic prompting to jointly analyze structural MRI and single nucleotide polymorphisms (SNPs). Each brain region becomes a visual token and SNP profiles are encoded as structured text, letting the model link regional atrophy to genetic factors through cross-modal attention. Tested on the ADNI cohort, R-GenIMA performs well in classifying four groups: normal cognition, subjective memory concerns, mild cognitive impairment, and AD. Results: Beyond accuracy, it produces biologically meaningful explanations, identifying stage-specific brain regions and genes. The model consistently highlighted known AD risk genes (APOE, BIN1, CLU, RBFOX1) and revealed stage-specific patterns: striatal involvement in subjective decline, frontotemporal changes in early impairment, and broad network disruption in AD. Discussion: These results show that interpretable multimodal AI can integrate imaging and genetics to reveal disease mechanisms, providing a foundation for clinical tools that enable earlier risk assessment and inform precision treatment in Alzheimer's disease.

  • Open Access

    Brain Structural Network Alterations in Alzheimer's Disease: Perspectives from Ethnicity‐Specific Factors

    by Haoteng Tang, Kun Zhao, Guodong Liu, Paul M. Thompson, Heng Huang, Alex Leow, Liang Zhan

    Background: Alzheimer's disease (AD) leads to distinct disruptions in brain networks, which can vary across ethnic populations. Using diffusion MRI‐derived brain structural networks, our study investigates ethnicity‐specific network alterations in Hispanic and White individuals during AD progression. Through network‐based statistical analysis, we identify significant subnetworks, including key brain regions‐of‐interest (ROIs) and connections, highlighting structural brain differences associated with ethnicity and disease status. These findings are critical for uncovering structural brain biomarkers and advancing our understanding of how demographic disparities influence neurodegenerative disease mechanisms, paving the way for more inclusive diagnostic and therapeutic strategies. Method: We utilize diffusion MRIs from OASIS (1326 subjects, mean age =70.42 ± 8.95, 738 women) and BrainLat dataset (763 subjects, mean age = 68.33 ± 11.19, 439 women) to construct structural brain networks (106 ROIs) based on Harvard‐Oxford Atlas and AAL Atlas. A Laplacian normalization is performed on these networks to standardize connectivity values, ensuring comparability across subjects and emphasizing relative structural differences by scaling node degrees and edge weights uniformly. Subjects are classified into AD and cognitively normal (NC) groups with specific ethnic labels (i.e., Hispanic and White). Network‐based statistic analysis was performed to identify significant subnetworks through edgewise comparisons between groups (e.g., AD/NC‐White vs. AD/NC‐Hispanic) with p ‐value < 0.05/(106*105/2). This analysis focused on detecting ethnicity‐specific patterns in network topology and pinpointing significant ROIs/connectomes contributing to structural differences Result: A total of 167 significantly different connections involving 76 corresponding ROIs were identified between two ethnic groups in the NC population. For instance, the connections between the Frontal Pole and the posterior superior temporal gyrus, posterior middle temporal gyrus, anterior inferior temporal gyrus, and temporo‐occipital inferior temporal gyrus are stronger in the Hispanic group. In the AD population, 32 significantly different connections involving 35 corresponding ROIs were identified. For example, distinct connectomic patterns were observed among the Angular Gyrus, Temporal Fusiform Cortex, and hippocampal regions between AD‐White and AD‐Hispanic populations, which may be attributed to cultural influences and comorbidities such as vascular disease. Conclusion: We investigated ethnicity‐specific brain network differences using diffusion MRI in both NC and AD populations, identifying significant connectomic variations linked to different ethnicities.


  • Open Access

    R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression

    by Kun Zhao, Siyuan Dai, Yingying Zhang, Guodong Liu, Pengfei Gu, Chenghua Lin, Paul M. Thompson, Alex Leow, Heng Huang, Lifang He, et al.

    Early detection of Alzheimer's disease (AD) requires models capable of integrating macro-scale neuroanatomical alterations with micro-scale genetic susceptibility, yet existing multimodal approaches struggle to align these heterogeneous signals. We introduce R-GenIMA, an interpretable multimodal large language model that couples a novel ROI-wise vision transformer with genetic prompting to jointly model structural MRI and single nucleotide polymorphisms (SNPs) variations. By representing each anatomically parcellated brain region as a visual token and encoding SNP profiles as structured text, the framework enables cross-modal attention that links regional atrophy patterns to underlying genetic factors. Applied to the ADNI cohort, R-GenIMA achieves state-of-the-art performance in four-way classification across normal cognition (NC), subjective memory concerns (SMC), mild cognitive impairment (MCI), and AD. Beyond predictive accuracy, the model yields biologically meaningful explanations by identifying stage-specific brain regions and gene signatures, as well as coherent ROI-Gene association patterns across the disease continuum. Attention-based attribution revealed genes consistently enriched for established GWAS-supported AD risk loci, including APOE, BIN1, CLU, and RBFOX1. Stage-resolved neuroanatomical signatures identified shared vulnerability hubs across disease stages alongside stage-specific patterns: striatal involvement in subjective decline, frontotemporal engagement during prodromal impairment, and consolidated multimodal network disruption in AD. These results demonstrate that interpretable multimodal AI can synthesize imaging and genetics to reveal mechanistic insights, providing a foundation for clinically deployable tools that enable earlier risk stratification and inform precision therapeutic strategies in Alzheimer's disease.


  • Open Access

    Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification

    by Pengfei Gu, Huimin Li, Haoteng Tang, Dongkuan, Xu, Erik Enriquez, DongChul Kim, Bin Fu, Danny Z. Chen

    Modern deep neural networks have shown remarkable performance in medical image classification. However, such networks either emphasize pixel-intensity features instead of fundamental anatomical structures (e.g., those encoded by topological invariants), or they capture only simple topological features via single-parameter persistence. In this paper, we propose a new topology-guided classification framework that extracts multi-scale and multi-filtration persistent topological features and integrates them into vision classification backbones. For an input image, we first compute cubical persistence diagrams (PDs) across multiple image resolutions/scales. We then develop a ``vineyard'' algorithm that consolidates these PDs into a single, stable diagram capturing signatures at varying granularities, from global anatomy to subtle local irregularities that may indicate early-stage disease. To further exploit richer topological representations produced by multiple filtrations, we design a cross-attention-based neural network that directly processes the consolidated final PDs. The resulting topological embeddings are fused with feature maps from CNNs or Transformers. By integrating multi-scale and multi-filtration topologies into an end-to-end architecture, our approach enhances the model's capacity to recognize complex anatomical structures. Evaluations on three public datasets show consistent, considerable improvements over strong baselines and state-of-the-art methods, demonstrating the value of our comprehensive topological perspective for robust and interpretable medical image classification.

  • Instantaneous Frequency: A New Functional Biomarker for Dynamic Brain Causal Networks

    by Haoteng Tang, Siyuan Dai, Lei Guo, Pengfei Gu, Guodong Liu, Alex D. Leow, Paul M. Thompson, Heng Huang, Liang Zhan, For The Alzheimer’S Disease Neuroimaging Initiative

    This study introduces instantaneous frequency (IF) analysis as a novel method for characterizing dynamic brain causal networks from functional magnetic resonance imaging blood-oxygen-level-dependent signals. Effective connectivity, estimated using dynamic causal modeling, is analyzed to derive IF sequences, with the average IF across brain regions serving as a potential biomarker for global network oscillatory behavior. Analysis of data from the Alzheimer’s Disease (AD) Neuroimaging Initiative, Open Access Series of Imaging Studies, and Human Connectome Project demonstrates the method’s efficacy in distinguishing between clinical and demographic groups, such as cognitive decline stages (e.g., normal control, early mild cognitive impairment [MCI], late MCI, and AD), sex differences, and sleep quality levels. Statistical analyses reveal significant group differences in IF metrics, highlighting its potential as a sensitive indicator for early diagnosis and monitoring of neurodegenerative and cognitive conditions.


  • Open Access

    A General Paradigm for Fine-Tuning Large Language Models in Alzheimer’s Disease Diagnosis

    by Marcus Zhan, Kun Zhao, Guodong Liu, Haoteng Tang

    Alzheimer's disease (AD), a complex neurodegenerative disorder, presents significant challenges for early and accurate diagnosis due to its multifactorial nature. This study introduces a novel approach to fine-tuning large language models (LLMs) for classifying AD-related dementia stages, using genetic and contextual demographic data. By harnessing the unique ability of LLMs to capture complex relationships in high-dimensional data, we developed a prompt structure that integrates genetic information, such as single nucleotide polymorphisms (SNPs), with patient-specific factors like age, sex, and clinical scores. Extensive experiments on the ADNI dataset demonstrate the superior performance of LLM-based methods. Our findings highlight the crucial role of high-quality prompts and carefully curated data in improving model accuracy. This research lays the groundwork for applying LLMs in precision medicine, providing a scalable and interpretable framework to address complex biomedical challenges, extending beyond AD.


  • Open Access

    Instantaneous Frequency: A New Functional Biomarker for Dynamic Brain Causal Networks

    by Haoteng Tang, Siyuan Dai, Lei Guo, Pengfei Gu, Guodong Liu, Alex D. Leow, Paul M. Thompson, Heng Huang, Liang Zhan, The Alzheimer’s Disease Neuroimaging Initiative

    This study introduces instantaneous frequency (IF) analysis as a novel method for characterizing dynamic brain causal networks from fMRI blood-oxygen-level-dependent (BOLD) signals. Effective connectivity, estimated using dynamic causal modeling (DCM), is analyzed to derive IF sequences, with the average IF across brain regions serving as a potential biomarker for global network oscillatory behavior. Analysis of data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), Open Access Series of Imaging Studies (OASIS), and Human Connectome Project (HCP) demonstrates the method’s efficacy in distinguishing between clinical and demographic groups, such as cognitive decline stages, sex differences, and sleep quality levels. Statistical analyses reveal significant group differences in IF metrics, highlighting its potential as a sensitive indicator for early diagnosis and monitoring of neurodegenerative and cognitive conditions. Graphical Highlights: The study introduces instantaneous frequency (IF) as a novel biomarker derived from dynamic brain effective connectivity, capturing temporal fluctuations in brain networks. The proposed IF biomarker effectively differentiates between various clinical stages, such as Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD), and demographic factors, including sex and sleep quality. The robustness and clinical relevance of the IF biomarker are validated using three independent datasets: ADNI, OASIS, and HCP, demonstrating its potential in cognitive and neurological research.


  • BPEN: Brain Posterior Evidential Network for trustworthy brain imaging analysis

    by Kai Ye, Haoteng Tang, Siyuan Dai, Igor Fortel, Paul M. Thompson, R. Scott Mackin, Alex Leow, Heng Huang, Liang Zhan