Yichi Zhang

weixs 

Ph.D Candidate, Fudan University. Email: zhangyichi23@m.fudan.edu.cn

Github | Google Scholar | Semantic Scholar | ResearchGate

  • I am a Ph.D. candidate at School of Data Science and Artificial Intelligence Innovation and Incubation Institute, Fudan University, co-advised by Prof. Yuan Qi and Prof. Yuan Cheng. I am currently a visiting student at Inselspital, University of Bern, advised by Prof. Kuangyu Shi. Before that, I obtained Bachelor's degree and Master's degree from Beihang University in 2020 and 2023.
  • My research interests lie in the interdisciplinary field of artificial intelligence and healthcare, with a focus on developing AI systems applicable for accurate and efficient medical image analysis. In the past few years, I focus on developing foundation models applicable for nuclear medicine applications like PET image analysis. I have published over 20 peer-reviewed journal/conference articles with over 3,500 citations.
  • I am in the final year of my PhD and actively seeking research positions in academia and industry. Welcome to connect or reach out for potential opportunities.
  • Recent News

    [2025.10] πŸŽ™οΈ Invited to give a talk at MICCAI 26 EMA Young Scientist Forum.
    [2026.9] πŸŽ‰ One paper was accepted by BIBM 2026.
    [2026.9] 🌍 I've begun my academic visiting at Inselspital, University of Bern, SwitzerlandπŸ‡¨πŸ‡­
    [2026.8] πŸŽ‰ One paper was accepted by EMNLP 2026.
    [2026.5] πŸŽ‰ Three papers were early accepted by MICCAI 2026.
    [2026.4] πŸŽ‰ Our survey on the development, adaptation, and application of generalist segmentation foundation models in biomedical image and video analysis is published online at iRadiology.
    [2026.3] πŸ’‘ We release an updated version of SegAnyPET with thorough assessment on multi-center, multi-tracer, multi-disease datasets and evaluation of clinical utility in downstream applications.
    [2026.3] πŸŽ‰ Our work PETWB-REP was accepted by Scientific Data. The dataset is publicly available.
    [2025.11] πŸŽ‰ Our work PET2Rep on whole-body PET/CT radiology report generation benchmark was accepted by AAAI 2026, thanks to all co-authors.
    [2025.10] πŸŽ‰ Two papers were accepted by Radiotherapy and Oncology and Biomedical Signal Processing and Control.
    [2025.9] πŸŽ™οΈ Invited to give a talk at Shanghai Foundation Model Innovation Center (ζ¨‘ι€Ÿη©Ίι—΄).
    [2025.9] ✨ Our project SAM4MIS received the 1000th star, a milestone moment for us!
    [2025.7] πŸŽ‰ Our work SemiSAM+ on foundation model-driven semi-supervised medical image segmentation was accepted by Medical Image Analysis, thanks to all co-authors.
    [2025.6] πŸŽ‰ Our work SegAnyPET on foundation model for universal PET segmentation was accepted by ICCV 2025, thanks to all co-authors.

    Selected Publications

    Foundation Models for Medical Imaging

     
     
     
     
     
     
     
     

    Dataset/Benchmark for Biomedical Imaging and Healthcare Applications

     
     
     
     
     
     
     
     
     
    • Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
      Alain Lalande, Zhihao Chen, Thibaut Pommier, Thomas Decourselle, Abdul Qayyum, Michel Salomon, Dominique Ginhac, Youssef Skandarani, Arnaud Boucher, Khawla Brahim, Marleen de Bruijne, Robin Camarasa, Teresa M. Correia, Xue Feng, Kibrom B. Girum, Anja Hennemuth, Markus Huellebrand, Raabid Hussain, Matthias Ivantsits, Jun Ma, Craig Meyer, Rishabh Sharma, Jixi Shi, Nikolaos V. Tsekos, Marta Varela, Xiyue Wang, Sen Yang, Hannu Zhang, Yichi Zhang, Yuncheng Zhou, Xiahai Zhuang, Raphael Couturier, Fabrice Meriaudeau.
      Medical Image Analysis, 2022. (SCI Q1 TOP, IF=13.828)

     
    • AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
      Jun Ma, Yao Zhang, Song Gu, Cheng Zhu, Cheng Ge, Yichi Zhang, Xingle An, Congcong Wang, Qiyuan Wang, Xin Liu, Shucheng Cao, Qi Zhang, Shangqing Liu, Yunpeng Wang, Yuhui Li, Jian He, Xiaoping Yang.
      IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021. (SCI Q1 TOP, IF=17.861) [code]
      * ESI Highly Cited Paper

    Data/Label-Efficient Learning for Medical Image Analysis

     
     
     
     
     
     

    Model-Centric Advancements for Medical Image Analysis

     
     
     
     
     

    Talks and Presentations

    - From Structural to Functional Imaging: Towards Foundation Models for Positron Emission Tomography - Foundation Model-Driven Annotation-Efficient Medical Image Segmentation

    Academic Services

    Journal Reviews Conference Reviews

    Honors & Awards