Assistant Professor of Artificial Intelligence in Radiology
The Intelligent Medical Systems (IMEDS) Laboratory focuses on development of AI methods and tools advancing disease prevention and mitigation of treatment complications.
My research focuses on developing scalable, trustworthy artificial intelligence and computer vision methods for medical imaging, using musculoskeletal (MSK) data as a primary anchor to drive clinical and surgical decision-making. A central pillar of my work is translating routine radiological images, such as plain films, MRI, and CT, into precise, actionable biomarkers. This includes automated lower-limb alignment measurements, as well as disease subtyping and staging.
Methodologically, my lab develops deployable AI models featuring uncertainty quantification, model calibration, and efficient neural network architectures. By advancing these methods, we ensure that AI tools deliver the reliable confidence bounds essential for test-time inference. A related line of investigation is efficiency: our work has produced new methods for performing multimodal imaging biomarker quantification at scale.
A core priority of my group is practical translation. We build open-source software and web platforms that let clinicians and surgeons integrate automated image analysis directly into research and practice. While anchored in MSK radiology, my group actively applies these core methodologies across adjacent medical and biomedical domains, including brain tumor characterization and retinal imaging.
Moving forward, we aim to leverage these methods to understand how routine MSK encounters can serve as broader windows for early disease detection and treatment optimization across health systems.
Biography
Prof. Aleksei Tiulpin is an Assistant Professor of Artificial Intelligence in Radiology at Weill Cornell Medicine. He earned his PhD (with distinction) in Medicine from the University of Oulu, Finland. He subsequently completed post-doctoral fellowships at KU Leuven, Belgium, and Aalto University, Finland, focusing on uncertainty quantification and personalized decision-making. Appointed Assistant Professor at the University of Oulu in 2022, Dr. Tiulpin also held visiting appointments at Aalto University and the Technion - Israel Institute of Technology prior to joining Weill Cornell Medicine in 2026.
Distinctions:
ISSLS Prize in Clinical Science 2026, The International Society for the Study of the Lumbar Spine
Selected Publications:
McSweeney, T. P., Akkaya, Z., Zhou, J., Wu, P. H., Bonnheim, N. B., Link, T. M., ... & Tiulpin, A. (2026). Data-driven classification of lumbar spine degeneration trajectories in chronic low back pain. European Spine Journal, 1-13.; https://link.springer.com/content/pdf/10.1007/s00586-026-09840-1.pdf
Hu, Z., Kemppainen, A., Johnson, D., Panfilov, E., Nguyen, H. H., Cootes, T., ... & Tiulpin, A. (2026, October). Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs. MICCAI 2026; https://arxiv.org/pdf/2606.15250
Dang, T., Nguyen, H. H., & Tiulpin, A. (2024, October). Singr: Brain tumor segmentation via signed normalized geodesic transform regression. MICCAI 2024; https://arxiv.org/pdf/2405.16813
Nguyen, H. H., Blaschko, M. B., Saarakkala, S., & Tiulpin, A. (2023). Clinically-inspired multi-agent transformers for disease trajectory forecasting from multimodal data. IEEE transactions on medical imaging, 43(1), 529-541.;https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10242080
