I am pursuing Ph.D at Artificial Intelligence and Biomedical Image Analysis Lab, School of Engineering, Westlake University (Hangzhou, China), affiliated with a joint-supervision program with Zhejiang University, supervised by Prof. Lin Yang. Before that, I received my B.Eng Degree from School of Automation Science and Electrical Engineering, Beihang University (Beijing, China) in June 2021.
My research interest includes medical image analysis and computer vision. I have worked on developing advanced detection methods for microscopy images. Currently, my research is centered on Multi-Modal Pretraining and Alignment for gigapixel whole slide images.
π₯ News
- 2024.09: Β ππ One MICCAI 2024 paper was invited as oral presentation!
- 2024.07: Β ππ One paper was accepted by European Conference on Computer Vision (ECCV 2024)!
- 2024.05: Β ππ One paper was Early Accepted by International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024)!.
- 2023.12: Β ππ Awarded as Zhejiang University 2023 Outstanding Graduates!
- 2023.05: Β ππ One paper was Early Accepted by International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)!.
- 2022.12: Β ππ Awarded as Zhejiang University 2022 Outstanding Graduates!
- 2022.01: Β ππ One paper was accepted by IEEE International Symposium on Biomedical Imaging (ISBI 2022)!
π Publications
![sym](images/wila.png)
WiLA: Large-Scale Whole-Slide Image-Language Alignment of Pathology Foundation Models (Under Review of IEEE Transactions on Medical Imaging)
Pingyi Chen, Chenglu Zhu, Honglin Li, Jingxiong Li, Lin Yang
- Large-scale visual-language alignment for whole slide images which shows superior zero-shot classification and retrieval performance.
![sym](images/wsivqa.png)
WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering European Conference on Computer Vision (ECCV 2024)
Pingyi Chen, Chenglu Zhu, Sunyi Zheng, Honglin Li, Lin Yang
- Establish a scalable pipeline to curate slide-level VQA datasets.
- Propose a WSI-VQA framework to reframe previous WSI-related tasks into a QA pattern.
![sym](images/wsicaption.png)
WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Images International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024 oral)
Pingyi Chen, Honglin Li, Chenglu Zhu, Sunyi Zheng, Zhongyi Shui, Lin Yang
- Establish a pathology report dataset with GPT.
- Propose a multiple instance generation (MI-Gen) framework to generate text based on gigapixel inputs.
-
Exploring Unsupervised Cell Recognition with Prior Self-activation Maps. Pingyi Chen, Chenglu Zhu, Zhongyi Shui, Jiatong Cai, Sunyi Zheng, Shichuan Zhang, Lin Yang MICCAI 2023
-
Category Separation For Weakly Supervised Multi-Class Cell Counting. Jiatong Cai, Chenglu Zhu, Pingyi Chen, Shichuan Zhang, Honglin Li, Yuxuan Sun, Lin Yang IEEE ISBI 2022
π Honors and Awards
- 2023.12 Zhejiang University 2023 Outstanding Graduates.
- 2022.12 Zhejiang University 2022 Outstanding Graduates.
- 2022.06 Westlake University Outstanding Cadres of the Graduate Student Union.
π Educations
- 2021.09 - (now), Ph.D candidate at Westlake University & Zhejiang University.
- 2017.09 - 2021.06, Bachelor of Engineering, Automation, Beihang University, Beijing, China.
π¬ Talks
π» Internships
- 2021.03 - 2021.08, SenseTimeοΌεζ±€οΌResearch, Beijing, China.