Jiancheng Yang is a Principal Investigator and tenure-track Assistant Professor leading the Health Intelligence (HINT) group at Aalto University and the ELLIS Institute Finland, specializing in AI for health with strengths in spatial intelligence, generative models, and multimodal deep learning. He combines a strong academic pedigree (PhD from Shanghai Jiao Tong, visiting positions at Harvard and EPFL) with hands-on product impact as co-founder and CTO of a medical AI startup that secured three NMPA approvals and multimillion-dollar funding. An author of 60+ publications, JC is widely recognized for creating MedMNIST, an influential collection of standardized biomedical image benchmarks that accelerates reproducible research. He serves in leadership roles for MICCAI and MIDL and sits on the editorial board of npj Digital Medicine, reflecting both community leadership and scholarly influence. Known for pragmatic code craftsmanship, he refactored core training and evaluation components of MedMNIST to improve clarity and reproducibility. Outside core research he organizes HIT Webinar, a popular open Chinese-language series bridging AI and healthcare, and is actively hiring PhD and postdoc researchers.
10 years of coding experience
6 years of employment as a software developer
Visiting PhD, Computer Science, Visiting PhD, Computer Science at Harvard University
Postdoc, Computer Science, Postdoc, Computer Science at EPFL
Doctor of Philosophy - PhD, Information Engineering, Doctor of Philosophy - PhD, Information Engineering at Shanghai Jiao Tong University
[pip install medmnist] 18 MNIST-like Datasets for 2D and 3D Biomedical Image Classification
Role in this project:
Back-end Developer
Contributions:59 commits, 1 PR, 79 pushes in 2 years 3 months
Contributions summary:Jiancheng refactored the code in the `train.py` file and made changes to the `medmnist/dataset.py`, `medmnist/evaluator.py`, and `medmnist/models.py` files, which suggests that they worked on improving the training, evaluation, and model definition aspects of the project. The refactoring included updates to data loading, model training, and the introduction of evaluation metrics. The changes appear to be aimed at improving code clarity and maintainability.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.