YSYonggang Shi

Yonggang Shi

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yonggang Shi has a total of 187 co-authors. Here are the top co-authors by number of shared publications:

  • Arthur W. Toga

    Laboratory of Neuro Imaging (LONI), USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA

    12 shared publications
  • Ivo D. Dinov

    University of Michigan

    12 shared publications
  • Paul Thompson

    Imaging Genetics Center, Mark and Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine of the University of Southern California, Marina del Rey, California, USA

    8 shared publications
  • Arthur W. Toga

    UCLA School of Medicine

    7 shared publications
  • Jianwei Zhang

    University of Southern California, Los Angeles, CA, USA

    6 shared publications
  • Mona Sharifi Sarabi

    USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, 2025 Zonal Avenue, Los Angeles, CA 90033, USA

    6 shared publications

Latest Publications

  • Open Access

    Graphical modeling of cortical tau pathology topography for its subtyping in Alzheimer’s disease

    by Jiaxin Yue, Xinkai Wang, John Ringman, Yonggang Shi

    Hyperphosphorylated tau tangles are essential hallmarks of Alzheimer’s disease (AD) and their propagation across brain regions was often considered to follow the classic Braak stages. Recent post-mortem and in vivo tau positron emission tomography (PET) studies, however, revealed the frequent presence of tau pathology heterogeneity. Clustering or event-based methods were proposed previously for the subtyping to tau pathology in AD, but they often lack robustness to varying distributions of disease severity across cohorts. To robustly discover and model tau pathology subtypes in AD, we propose in this work a novel graphical modeling framework that can disentangle the phenotypical differences of tau PET imaging due to disease heterogeneity from the spatiotemporal variations of disease stages. First, we propose a novel Reeb graph representation at the individual level to characterize the topographic patterns of salient tau pathology on cortical surfaces. Next, we use only cross-sectional tau PET data to develop a graphical model at the population level to encode the inter-subject spatiotemporal relationships, which enables us to robustly derive subtypes based on the topographic patterns of tau pathology and hence achieve increased generalization power to new samples with distinct tau pathology severity from the training data. Using synthetic and large-scale tau PET imaging data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Anti-Amyloid Treatment in Asymptomatic Alzheimer’s (A4) studies, we compare with the state-of-the-art SuStaIn method and demonstrate the improved generalization performance of the proposed method. In addition, we validate both methods on a cohort of autosomal dominant Alzheimer’s disease (ADAD) patients with known tau pathology patterns to show that our method has more robust performance in testing data with large deviations from training data. Furthermore, for preclinical patients of the A4 cohort, we demonstrate more significant differences in clinical cognitive measures can be observed across subtypes discovered by our method.

  • A Wasserstein-Space-Based Framework for Processing Fiber Orientation Geometry in Diffusion MRI

    by Xinyu Nie, Yonggang Shi

    The fiber orientation distribution (FOD) function is an advanced model for high angular resolution diffusion MRI, capable of representing complex crossing or fanning fiber geometries. However, the intricate mathematical structures of FOD functions pose significant challenges for data processing and analysis. Current frameworks often fail to consider fiber bundle rotation information among FOD peaks, leading to improper data processing, such as inaccurate FOD interpolation and, consequently, anatomically incorrect fiber tracking. This paper presents a novel Wasserstein space based framework for processing and analyzing FOD functions that systematically considers fiber-bundle-specific geometry. Our approach begins with a spherical deconvolution method to accurately detect and decompose FOD functions into single-peak lobes. These single-peak lobes are then embedded into the Wasserstein space, where a new metric for FOD functions is defined, capable of handling rotations among peak lobes. We introduce a geometry-aware clustering method to regroup the single-peak lobes for further bundle-specific FOD processing. The proposed framework is applied to the essential task of FOD interpolation, computed as the Barycenter of the new metric, with a fast approximation method for efficient computation. Experiments conducted on synthetic data, as well as datasets from the Human Connectome Project (HCP) and the Alzheimer's Disease Neuroimaging Initiative (ADNI), demonstrate that our framework effectively handles complex fiber geometries, provides anatomically meaningful FOD interpolations, and significantly enhances the performance of FOD-based tractography.


  • Open Access

    Voxel‐wise deconvolution and surface shape analysis for the correction of meningeal off‐target bindings in tau PET

    by Jiaxin Yue, Jianwei Zhang, Yonggang Shi

    Background: Increasingly popular second‐generation tau PET tracers such as PI‐2620 and MK‐6240 often exhibits off‐target bindings in the meningeal areas. These artifacts lead to abnormally high uptake values on the cortex and complicate the interpretation of tau‐PET scans. To address this issue, we proposed a novel computational framework to effectively remove meningeal off‐target bindings and enhance the reliability of tau PET quantification on cortical regions. Method: First, we develop a voxel‐wise deconvolution to recover the original tau PET signal in the brain region to reduce spill‐in from neighboring meningeal regions caused by partial volume effects. Second, to further eliminate residual artifacts that persist after projecting the tau PET image onto cortical surfaces, we introduce a surface‐based artifact detection and removal method. Vertices that were spatially proximate to meningeal artifacts and displayed abnormal signal intensities were identified, and the values of these labeled vertices were reconstructed based on their connected neighbors on surface. Finally, to ensure consistent spatial smoothness and reduce noise, Laplacian smoothing was applied to the reconstructed surface data. This framework was evaluated using the Health and Aging Brain Study: Health Disparities (HABS‐HD) dataset which employs PI‐2620 tau PET tracer. 758 subjects were used in the experiments, comprising 513 CN, 201 MCI and 44 AD subjects at baseline. Additionally, 216 subjects have 432 longitudinal scans, with an average interval of 24 months. Result: Our framework effectively removed spill‐in meningeal artifacts while preserving tau pathology on cortical surfaces (Figure 1). The authenticity of the pathology was further validated by improved longitudinal pattern consistency and the expected local monotonic increase of tau deposition over time. Besides, the average SUVRs at temporal meta‐ROI exhibit stronger associations with diagnosis (CN/ MCI/ AD) and Aβ status (Figure 2), as indicated by higher Cohen's d and lower p ‐value. These findings suggest an enhanced diagnostic reliability of the processed tau PET data. Conclusion: Our proposed preprocessing framework effectively removes meningeal artifacts and enhances the diagnostic power of tau PET data on cortical surfaces. The improved data quality facilitates a better interpretation of tau pathology on the cortical surface. Funding Sources : RF1AG077578, RF1AG064584, R01EB022744, U19AG078109, P30AG066530.

  • Robust Topographical Representation for Longitudinal Propagation of Tau Pathology

    by Jiaxin Yue, Jianwei Zhang, Xinkai Wang, Yonggang Shi

    Tau pathology is a hallmark of Alzheimer’s disease (AD), and longitudinal tau positron emission tomography (PET) provides valuable insights into disease progression. However, the integration of tau PET data into computational models remains limited by challenges in encoding topographical information and ensuring longitudinal consistency. Existing biomarker-based representations often lack spatial flexibility and fail to account for covariance between brain regions. Additionally, traditional approaches often treat longitudinal scans as independent observations, neglecting temporal coherence. To address these limitations, we propose a novel Multiresolutional Reeb Graph representation that encodes the spatiotemporal propagation of tau topographical information. Our method constructs Reeb graphs to capture tau topography at a static time point and extends them into a multiresolutional framework to model disease evolution. We introduce a topology-based measurement for quantifying pathology spatial distribution similarity, and a severity interleaving distance for robust longitudinal staging. The efficiency of the proposed representation is validated in two downstream tasks: an integrated subtyping and staging system, and the longitudinal pathology prediction. The promising results compared with the current methods demonstrate the great potential of the proposed representation to enhancing the application of longitudinal tau PET data, and offering a reliable approach for studying AD progression.

  • GPU Accelerated Modeling of Cortical Radial and Tangential Connectivity Changes in Neurodegeneration

    by Hongbo Zhang, Xinyu Nie, Jiaxin Yue, Yuan Li, John Ringman, Yonggang Shi

    The diffusion MRI signals in the human cerebral cortex are strongly associated with neurodegenerative diseases. Although models like NODDI have been extensively used to characterize cortical microstructure degeneration, they fall short in capturing detailed, orientation-specific connectivity changes within the cortex. In this study, we introduce a method to decompose cortical tissue diffusion signal to radial and tangential components. Our approach uses data from multi-shell diffusion imaging and combines it with anatomical information from brain surfaces. By applying a GPU accelerated probabilistic optimization framework, we can accurately and efficiently estimate these diffusion components while keeping the results smooth and consistent with the cortical anatomy. We test our method on data from HCP subjects and a clinical dataset of patients with autosomal dominant Alzheimer’s Disease (ADAD) subjects. Our results demonstrate that the proposed method can more effectively reveal cortical gray matter connectivity changes related to tau pathology than metrics from the NODDI model. Our codebase is publicly available at https://github.com/Haibaobob/FOD-ctx-decomp

  • Surface-Based Multi-axis Longitudinal Disentanglement Using Contrastive Learning for Alzheimer’s Disease

    by Jianwei Zhang, Yonggang Shi

    Accurate modeling of disease progression is essential for comprehending the heterogeneous neuropathologies such as Alzheimer’s Disease (AD). Traditional neuroimaging analysis often confound disease effects with normal aging, complicating the differential diagnosis. Recent advancements in deep learning have catalyzed the development of disentanglement techniques in Autoencoder networks, aiming to segregate longitudinal changes attributable to aging from those due to disease-specific alterations within the latent space. However, existing longitudinal disentanglement methods usually model disease as a single axis factor which ignores the complexity and heterogeneity of Alzheimer’s Disease. In response to this issue, we propose a novel Surface-based Multi-axis Disentanglement framework. This framework posits multiple disease axes within the latent space, enhancing the model’s capacity to encapsulate the multifaceted nature of AD, which includes various disease trajectories. To assign axes to data trajectories without explicit ground truth labels, we implement a longitudinal contrastive loss leveraging self-supervision, thereby refining the separation of disease trajectories. Evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset (N=1321), our model demonstrates superior performance in delineating between cognitively normal (CN), mild cognitive impairment (MCI), and AD subjects, classification of stable MCI vs converting MCI and Amyloid status, compared to the single-axis model. This is further substantiated through an ablation study on the contrastive loss, underscoring the utility of our multi-axis approach in capturing the complex progression patterns of AD. The code is available at: https://github.com/jianweizhang17/MultiAxisDisentanglement.git.


  • Multistage Alignment and Fusion for Multimodal Multiclass Alzheimer’s Disease Diagnosis

    by Shuo Huang, Lujia Zhong, Yonggang Shi

    For the early diagnosis of Alzheimer’s disease (AD), it is essential that we have effective multiclass classification methods that can distinct subjects with mild cognitive impairment (MCI) from cognitively normal (CN) subjects and AD patients. However, significant overlaps of biomarker distributions among these groups make this a difficult task. In this work, we propose a novel framework for multimodal, multiclass AD diagnosis that can integrate information from diverse and complex modalities to resolve ambiguity among the disease groups and hence enhance classification performances. More specifically, our approach integrates T1-weighted MRI, tau PET, fiber orientation distribution (FOD) from diffusion MRI (dMRI), and Montreal Cognitive Assessment (MoCA) scores to classify subjects into AD, MCI, and CN groups. We introduce a Swin-FOD model to extract order-balanced features from FOD and use contrastive learning to align MRI and PET features. These aligned features and MoCA scores are then processed with a Tabular Prior-data Fitted In-context Learning (TabPFN) method, which selects model parameters based on the alignment between input data and prior data during pre-training, eliminating the need for additional training or fine-tuning. Evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset (\(n = 1147\)), our model achieved a diagnosis accuracy of 73.21%, outperforming all comparison models (\(n=10\)). We also performed Shapley analysis and quantitatively evaluated the essential contributions of each modality.