Summary
Jiahong Ouyang is a Lead Clinical Machine Learning Scientist and Stanford PhD candidate in Electrical Engineering with a decade of experience building ML methods for medical imaging across modalities including MRI, CT, PET, ultrasound, OCT, and microscopy. He combines deep research expertise in self-supervised learning and generative models with industry impact—shipping novel weakly supervised ultrasound detection work accepted to IPMI and developing a prognostic CT-based model at Genentech that cut endpoint variance by nearly 40% for clinical-trial covariate adjustment. Comfortable moving ideas from theory to deployment, he joined insitro in 2024 to drive clinical ML applications and has a background spanning Philips Research and Genentech internships. Trained at Stanford, Carnegie Mellon, and Tsinghua, he blends rigorous academic methods with practical solutions for noisy clinical endpoints and limited labels. Colleagues describe him as a bridge between cutting-edge research and measurable clinical impact.
10 years of coding experience
Bachelor's degree Automation, Bachelor's degree Automation at Tsinghua University
Master's degree Robotics System Development, Master's degree Robotics System Development at Carnegie Mellon University
Doctor of Philosophy - PhD Electrical and Electronics Engineering, Doctor of Philosophy - PhD Electrical and Electronics Engineering at Stanford University
Chinese, English