SNShuo Ni

Shuo Ni

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shuo Ni has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Does sub‐cortical PI‐2620 tau PET signal reflect Alzheimer's disease status?

    by Shuo Ni, Jiaxin Yue, Yonggand Shi

    Background: The first‐generation tau PET tracer AV‐1451 has been widely used to study tau pathology in Alzheimer's disease (AD), but it's high off‐target binding in sub‐cortical structures has limited our ability to examine possible tau pathology in these structures. With the increasing popularity of second‐generation tau PET tracers such as PI‐2620 and MK‐6240 that exhibit low off‐target binding signals in sub‐cortical structures, it is important to examine whether their signals can be useful in evaluating the severity of tau pathology of sub‐cortical structures in AD. Method: This study utilized tau PET data based on the PI‐2620 tracer from the Health and Aging Brain Study: Health Disparities (HABS‐HD). Overall, data used in this study are from 1,492 participants with both T1‐weighted MRI and tau PET imaging, along with the available clinical and cognitive metrics such as the Consensus Diagnosis (CDX). The cohort included 1097 cognitively unimpaired (CU) and 395 cognitively impaired (CI) participants, which are comprised of 479 Black, 447 Hispanic, and 566 non‐Hispanic White subjects. Subcortical regions of interest included key structures from both the left and right hemispheres including the thalamus, caudate, putamen, pallidum, hippocampus, amygdala, and accumbens. Automated segmentation maps were generated from T1‐weighted MRI using FreeSurfer and applied to the corresponding PET images to calculate mean standard uptake value ratio (SUVR) values for each subcortical region. Result: Significant differences in tau SUVR values were observed in the caudate ( p ‐value < 1e‐2), hippocampus ( p ‐value < 1e‐2), and amygdala ( p ‐value < 1e‐4) across diagnostic categories in the entire cohort. Ethnic group analyses for CU and CI subjects revealed statistically significant differences in different sub‐cortical regions. Among non‐Hispanic White participants, differences were significant in the putamen ( p ‐value < 1e‐2), hippocampus ( p ‐value < 1e‐2), and amygdala ( p ‐value < 1e‐5). Significant differences were observed in the caudate ( p ‐value < 1e‐2) for Black participants, while the amygdala showed statistically significant differences ( p ‐value < 5e‐2) for Hispanic participants. Conclusion: Ethnicity plays an important role on sub‐cortical tau PET signal for CU and CI, especially for non‐Hispanic White in the amygdala area. Funding Sources : RF1AG077578, RF1AG064584, R01EB022744, U19AG078109, P30AG066530.

  • Open Access

    USC-DCT: A Collection of Diverse Classification Tasks

    by Adam M. Jones, Gozde Sahin, Zachary W. Murdock, Yunhao Ge, Ao Xu, Yuecheng Li, Di Wu, Shuo Ni, Po-Hsuan Huang, Kiran Lekkala, et al.

    Machine learning is a crucial tool for both academic and real-world applications. Classification problems are often used as the preferred showcase in this space, which has led to a wide variety of datasets being collected and utilized for a myriad of applications. Unfortunately, there is very little standardization in how these datasets are collected, processed, and disseminated. As new learning paradigms like lifelong or meta-learning become more popular, the demand for merging tasks for at-scale evaluation of algorithms has also increased. This paper provides a methodology for processing and cleaning datasets that can be applied to existing or new classification tasks as well as implements these practices in a collection of diverse classification tasks called USC-DCT. Constructed using 107 classification tasks collected from the internet, this collection provides a transparent and standardized pipeline that can be useful for many different applications and frameworks. While there are currently 107 tasks, USC-DCT is designed to enable future growth. Additional discussion provides explanations of applications in machine learning paradigms such as transfer, lifelong, or meta-learning, how revisions to the collection will be handled, and further tips for curating and using classification tasks at this scale.


  • Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge

    by Hongyan Gu, Mohammad Haeri, Shuo Ni, Christopher Kazu Williams, Neda Zarrin-Khameh, Shino Magaki, Xiang ‘Anthony’ Chen


  • Open Access

    Lightweight Learner for Shared Knowledge Lifelong Learning

    by Yunhao Ge, Yuecheng Li, Di Wu, Ao Xu, Adam M. Jones, Amanda Sofie Rios, Iordanis Fostiropoulos, Shixian Wen, Po-Hsuan Huang, Zachary William Murdock, et al.

    In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicated LL machinery is then deployed to mitigate the forgetting of old tasks as new tasks are learned. This is inherently slow. We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel. After learning their respective tasks, agents share and consolidate their knowledge over a decentralized communication network, so that, in the end, all agents can master all tasks. We present one solution to SKILL which uses Lightweight Lifelong Learning (LLL) agents, where the goal is to facilitate efficient sharing by minimizing the fraction of the agent that is specialized for any given task. Each LLL agent thus consists of a common task-agnostic immutable part, where most parameters are, and individual task-specific modules that contain fewer parameters but are adapted to each task. Agents share their task-specific modules, plus summary information ("task anchors") representing their tasks in the common task-agnostic latent space of all agents. Receiving agents register each received task-specific module using the corresponding anchor. Thus, every agent improves its ability to solve new tasks each time new task-specific modules and anchors are received. On a new, very challenging SKILL-102 dataset with 102 image classification tasks (5,033 classes in total, 2,041,225 training, 243,464 validation, and 243,464 test images), we achieve much higher (and SOTA) accuracy over 8 LL baselines, while also achieving near perfect parallelization. Code and data can be found at https://github.com/gyhandy/Shared-Knowledge-Lifelong-Learning

  • Top Cited Papers
    Open Access

    Improving Workflow Integration with xPath: Design and Evaluation of a Human-AI Diagnosis System in Pathology

    by Hongyan Gu, Yuan Liang, Yifan Xu, Christopher Kazu Williams, Shino Magaki, Negar Khanlou, Harry Vinters, Zesheng Chen, Shuo Ni, Chunxu Yang, et al.

    Recent developments in AI have provided assisting tools to support pathologists’ diagnoses. However, it remains challenging to incorporate such tools into pathologists’ practice; one main concern is AI’s insufficient workflow integration with medical decisions. We observed pathologists’ examination and discovered that the main hindering factor to integrate AI is its incompatibility with pathologists’ workflow. To bridge the gap between pathologists and AI, we developed a human-AI collaborative diagnosis tool— xPath —that shares a similar examination process to that of pathologists, which can improve AI’s integration into their routine examination. The viability of xPath is confirmed by a technical evaluation and work sessions with 12 medical professionals in pathology. This work identifies and addresses the challenge of incorporating AI models into pathology, which can offer first-hand knowledge about how HCI researchers can work with medical professionals side-by-side to bring technological advances to medical tasks towards practical applications.


  • Open Access

    Improving Workflow Integration with xPath: Design and Evaluation of a Human-AI Diagnosis System in Pathology

    by Hongyan Gu, Yuan Liang, Yifan Xu, Christopher Kazu Williams, Shino Magaki, Negar Khanlou, Harry Vinters, Zesheng Chen, Shuo Ni, Chunxu Yang, et al.

    Recent developments in AI have provided assisting tools to support pathologists' diagnoses. However, it remains challenging to incorporate such tools into pathologists' practice; one main concern is AI's insufficient workflow integration with medical decisions. We observed pathologists' examination and discovered that the main hindering factor to integrate AI is its incompatibility with pathologists' workflow. To bridge the gap between pathologists and AI, we developed a human-AI collaborative diagnosis tool -- xPath -- that shares a similar examination process to that of pathologists, which can improve AI's integration into their routine examination. The viability of xPath is confirmed by a technical evaluation and work sessions with twelve medical professionals in pathology. This work identifies and addresses the challenge of incorporating AI models into pathology, which can offer first-hand knowledge about how HCI researchers can work with medical professionals side-by-side to bring technological advances to medical tasks towards practical applications.