Curriculum Vitae
George Yiasemis, PhD, MSc
Postdoctoral Researcher · AI for Oncology Lab · Netherlands Cancer Institute · Amsterdam, Netherlands
Research Interests
Deep learning and computer vision for AI in oncology — mainly medical image reconstruction and foundation models, with collaborative work on AI for radiology, surgery, pathology, biology, and proteomics.
Experience
Netherlands Cancer Institute · AI for Oncology Lab · Amsterdam
Supervisor: Jonas Teuwen
- Reconstruction and foundation models (AIFOFOMO); collaborative AI projects with radiology, surgery, pathology, biology, and proteomics colleagues
- Lead developer of AIFOFOMO in the Foundation Models for Oncology Lab
- Supervision of PhD researchers in computer vision and medical imaging
Netherlands Cancer Institute & University of Amsterdam
Supervisors: Jonas Teuwen, Jan Jakob Sonke, Clara I. Sánchez.
Thesis: What We Do Sample, We Must Learn to Reconstruct: From Missing k-Space Data to Meaningful Images — Deep Learning in MRI Reconstruction and Beyond (thesis)
- Deep learning for accelerated MRI acquisition, reconstruction, and adaptive sampling
- Creator and maintainer of the open-source DIRECT toolkit
- Collaboration with radiologists, medical physicists, and AI researchers across NKI
Education
University of Amsterdam & Netherlands Cancer Institute
Supervisors: Jonas Teuwen, Jan Jakob Sonke, Clara I. Sánchez
Imperial College London
Thesis: Mirror Descent and Interacting Mirror Descent: Almost Dimension-Free Convex Optimization for Non-Euclidean Spaces
University of Cyprus · 1st in Department and Faculty of Pure and Applied Sciences
Thesis: Computational Approach of the Orr-Sommerfeld Equation with the Finite Elements Method (10/10)
University of Patras, Greece
Publications
Full list with direct paper links on the publications page.
Selected first-author work includes publications at CVPR, MIDL, Magnetic Resonance Imaging, JOSS, and SPIE Medical Imaging.
Software
PyTorch pipeline for imaging inverse problems (MRI reconstruction, denoising, dealiasing). Implements RecurrentVarNet, vSHARP, RIM, LPD, and VarNet with pretrained models in the Model Zoo. Winner · Multi-Coil MRI Challenge 2022; podium · CMRxRecon 2023 & 2024. JOSS 2022 · Docs
High-performance C++20 whole-slide image reader with native Python bindings for digital pathology and multiplex imaging. Supports SVS, QPTIFF, MRXS, OME-TIFF, OME-Zarr, Philips iSyntax, Zeiss CZI, Ventana, Olympus VSI, and more — with multi-channel fluorescence, Z-stacks, and T-series. Thread-safe and PyTorch DataLoader-ready. Docs · Apache 2.0
Internal framework for foundation model research at the Foundation Models for Oncology Lab (NKI).
Honors & Awards
2nd & 3rd place, CMRxRecon Challenge (MICCAI), Marrakesh
Runner-up, CMRxRecon Challenge (MICCAI), Vancouver
Winner, Multi-Coil MRI Reconstruction Challenge, Calgary
Corporate Partnership Programme MSc Group Project Prize, Imperial College London
Cyprus Mathematical Society Award; Top Graduating Student, Faculty of Pure and Applied Sciences, University of Cyprus
Rose and Irving Saff Award, University of Cyprus
Mentoring & Service
- Supervision of PhD researchers at NKI (foundation models, medical imaging)
- Mentoring of MSc students during PhD (MRI sampling, latent diffusion for reconstruction)
- International conference presentations: CVPR, MICCAI, MIDL, RSNA, SPIE Medical Imaging
Technical Skills
Languages & frameworks: Python, PyTorch, PyTorch Lightning, MATLAB, Cython
Areas: AI for oncology, deep learning, computer vision, medical image reconstruction, foundation models, collaborative medical imaging and molecular AI
Engineering: Git, CI/CD, Docker, Singularity, HPC/Slurm, unit testing, reproducible experimentation
Languages
English (fluent) · Greek (native) · Dutch (beginner) · Spanish (beginner)