About Me
I am currently a second-year Ph.D. student in Computer Science at Vanderbilt University, supervised by Prof. Yuankai Huo. My research interests lie in medical image analysis, vision-language models, and computer vision, with a particular focus on developing efficient and interpretable deep learning frameworks for large-scale pathology image processing. Before joining Vanderbilt, I received my B.S. degree from the School of Life Sciences and Biotechnology at Shanghai Jiao Tong University in 2024. Outside of research, I enjoy baseball, cooking and fitness.
🎓 Academic Background
2024.8 – present
Ph.D. student in Computer Science, Vanderbilt University
Advisor: Prof. Yuankai Huo
2020.9 – 2024.6
B.Sc. in Bioscience, Minor in Automation, Shanghai Jiao Tong University
Advisors: Dr. Jing Ke and Prof. Hui Lu
📰 News
- [July. 2026] One paper was accepted to IEEE Transactions on Image Processing.
- [June. 2026] Two co-authored paper was accepted to MICCAI 2026.
- [May. 2026] One survey paper was accepted to Briefings in Bioinformatics.
- [Apr. 2026] Four papers were accepted for MIDL 2026.
- [Jul. 2025] Two papers were accepted for Oral presentation at MIDL 2025.
- [Feb. 2025] One paper was accepted to CVPR 2025.
- [Oct. 2024] One paper was accepted to SPIE Medical Imaging 2025.
- [Jun. 2023] One paper was accepted to MICCAI 2023.
- [Jan. 2023] One paper was accepted to Medical Image Analysis.
📝 Selected Publications
A comprehensive survey of computer vision methods for spatial transcriptomics
Junchao Zhu, Ruining Deng, Tianyuan Yao, et al., Briefings in Bioinformatics, 2026
Paper
ASIGN: An Anatomy-aware Spatial Imputation Graphic Network for 3D Spatial Transcriptomics
Junchao Zhu, Ruining Deng, Tianyuan Yao, et al., CVPR 2025
Paper | Code
MagNet: Multi-Level Attention Graph Network for Predicting High-Resolution Spatial Transcriptomics
Junchao Zhu, Ruining Deng, Tianyuan Yao, et al., MIDL 2025 (Oral)
Paper | Code
TCSegNet: An Anti-biased TBSRTC-Category Aware Nuclei Segmentation Framework with a Multi-label Thyroid Cytology Benchmark
Junchao Zhu, Yiqing Shen, Haolin Zhang, Jing Ke, MICCAI 2023
Paper | Code
ClusterSeg: A crowd cluster pinpointed nucleus segmentation framework with cross-modality datasets
Jing Ke, Yizhou Lu, Yiqing Shen, Junchao Zhu, et al., Medical Image Analysis, 2023
Paper
💼 Professional Experience
Ph.D. Intern – Data Science & Digital Health (DSAI), Johnson & Johnson (May 2025 – Aug 2025)
- Working on Vision–Language Models and multimodal foundation models for spatial transcriptomics.
- Developing hierarchical alignment frameworks between vision and omics modalities.
- Collaborating with the digital pathology team to explore large-scale deployment of multimodal AI in biomedical imaging.
Graduate Research Assistant, Vanderbilt University (Aug. 2024 – present)
- Developing 3D-aware spatial transcriptomics models for multi-section data reconstruction.
- Building high-resolution spatial omics benchmarks.
- Exploring quantization and efficient deployment of medical segmentation networks.
Research Assistant, Shanghai Jiao Tong University (Sep. 2021 – May 2024)
- Proposed TCSegNet and ClusterSeg frameworks for thyroid cytology analysis.
- Constructed one of the first multi-label thyroid cytology datasets.
- Designed end-to-end diagnosis pipeline integrating segmentation and classification.
🏆 Honors & Awards
- 🧠 MIDL 2025 Travel Award
- 🥇 Gold Medal & Best Software Project Nominee — iGEM Competition, 2021
- ⚾ 2nd Place — Shanghai Collegiate Baseball Championship, 2024
- 🧮 3rd Prize — 13th Chinese College Students Mathematics Competition
- 🎓 Jingding Biology Strengthening Basic Disciplines Program Scholarship
- ✈ Graduate School Travel Grant — Vanderbilt University, 2024–2025
Technical Skills
Programming: Python, MATLAB, R, LaTeX
Frameworks: PyTorch, Keras
Tools: Linux, Git, VS Code, PyCharm
Languages: Chinese, English