I study brain
diseases...

About

I am a postdoctoral researcher in the group of Prof. Daniel Rueckert at the Chair for AI in Healthcare and Medicine, Technical University of Munich. My work combines biophysical modeling, inverse problems, and machine learning, ranging from patient-specific simulations of tumor growth to real-time optical imaging of brain tissue. The goal of my research is to personalize radiotherapy planning and neurosurgery. I received my PhD (summa cum laude) from TUM, supervised by Prof. Bjoern Menze. Before that, I studied physics, with an MSc from TUM and a BSc from St. Petersburg Polytechnic University.

Publications

For an always up-to-date list, please visit my Google Scholar page.
* denotes equal contribution

2026

• 
  Zimmer, L., Weidner, J., Balcerak, M., Kofler, F., Krupa, M., Ezhov, I., …, Wiestler, B. PREDICT-GBM: A multi-center platform to advance personalized glioblastoma radiotherapy planning npj Digital Medicine, 2026. Paper
• 
  Weidner, J., Zimmer, L., Ezhov, I., Balcerak, M., Menze, B., Rueckert, D., Wiestler, B. Brain tumor growth inversion via differentiable neural surrogates Medical Imaging with Deep Learning (MIDL), 2026. Paper
• 
  Scibilia, K., Rosier, M., Giannoni, L., Ricci, P., Lange, F., Pavone, F. S., …, Ezhov, I. A unified perspective on wavelength selection for molecular composition inference from diffuse spectroscopy Preprint, arXiv:2606.23223, 2026. arXiv

2025

• 
  Balcerak, M., Weidner, J., Karnakov, P., Ezhov, I., Litvinov, S., Koumoutsakos, P., …, Menze, B. Individualizing glioma radiotherapy planning by optimization of a data and physics-informed discrete loss Nature Communications, 2025. Paper
• 
  Mach, T., Rueckert, D., Berger, A. H., Lux, L., Ezhov, I. Addressing annotation scarcity in hyperspectral brain image segmentation with unsupervised domain adaptation International Symposium on Biomedical Image Processing and Analysis (SIPAIM), 2025. Paper
• 
  Hartenberger, M., …, Tachtsidis, I., Rueckert, D., Ezhov, I. Redefining spectral unmixing for in-vivo brain tissue analysis from hyperspectral imaging International Workshop on Computational Mathematics Modeling in Cancer Analysis (CMMCA), 2025. Paper

2024

• 
  Balcerak, M., Amiranashvili, T., Wagner, A., Weidner, J., Karnakov, P., Paetzold, J. C., Ezhov, I., …, Menze, B. Physics-regularized multi-modal image assimilation for brain tumor localization Advances in Neural Information Processing Systems (NeurIPS), 2024. Paper
• 
  Weidner, J., Ezhov, I., Balcerak, M., Metz, M.C., Litvinov, S., Kaltenbach, S., Feiner, L., Lux, L., Kofler, F., Lipkova, J., Latz, J., Rueckert, D., Menze, B., Wiestler, B. A learnable prior improves inverse tumor growth modeling IEEE Transactions on Medical Imaging, 2024. Paper
• 
  Ezhov, I., Scibilia, K., Giannoni, L., Kofler, F., Iliash, I., Hsieh, F., …, Rueckert, D. Learnable real-time inference of molecular composition from diffuse spectroscopy of brain tissue Journal of Biomedical Optics, 2024. PubMed

2023

• 
  Ezhov, I., Giannoni, L., Shit, S., Lange, F., Kofler, F., Menze, B., …, Rueckert, D. Identifying chromophore fingerprints of brain tumor tissue on hyperspectral imaging using principal component analysis European Conference on Biomedical Optics (ECBO), 2023. Paper
• 
  Metz, M. C.*, Ezhov, I.*, Peeken, J. C., Buchner, J. A., Lipkova, J., Kofler, F., …, Wiestler, B. Toward image-based personalization of glioblastoma therapy: A clinical and biological validation study of a novel, deep learning-driven tumor growth model Neuro-Oncology Advances, 2023. Paper
• 
  Ezhov, I., Scibilia, K., Franitza, K., Steinbauer, F., Shit, S., Zimmer, L., …, Menze, B. Learn-Morph-Infer: A new way of solving the inverse problem for brain tumor modeling Medical Image Analysis, 2023. Paper

2022

• 
  Ezhov, I., Rosier, M., Zimmer, L., Kofler, F., Shit, S., Paetzold, J. C., …, Menze, B. A for-loop is all you need. For solving the inverse problem in the case of personalized tumor growth modeling Proceedings of Machine Learning Research (PMLR), 2022. Paper

2021

• 
  Ezhov, I., Mot, T., Shit, S., Lipkova, J., Paetzold, J. C., Kofler, F., …, Menze, B. Geometry-aware neural solver for fast Bayesian calibration of brain tumor models IEEE Transactions on Medical Imaging, 2021. Paper

2020

• 
  Qasim, A.*, Ezhov, I.*, Shit, S., Schoppe, O., Paetzold, J. C., Sekuboyina, A., …, Menze, B. Red-GAN: Attacking class imbalance via conditioned generation. Yet another medical imaging perspective Medical Imaging with Deep Learning (MIDL), 2020. Paper

2019

• 
  Ezhov, I.*, Lipkova, J.*, Shit, S., Kofler, F., Collomb, N., Lemasson, B., …, Menze, B. Neural parameters estimation for brain tumor growth modeling International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019. Paper

Teaching & Mentoring

Awards

• 2023: Summa cum laude, PhD thesis, TU Munich
• 2021–2022: Two-time winner (1st place), MICCAI FeTS (Federated Tumor Segmentation) Challenge
• 2021: Winner (1st place), MICCAI VALDO (Vascular Lesions Detection and Segmentation) Challenge
• 2020: 1st place in MICCAI FeTA (Fetal Brain Tissue Annotation and Segmentation) Benchmark
• 2018–2022: Marie Skłodowska-Curie PhD fellowship
• 2018: NVIDIA GPU grant (co-applicant)
• 2013–2015: Erasmus Mundus full MSc scholarship (awarded to approximately 2% of applicants)
• 2007–2011: State scholarship for excellence in study

News

• Jun 2026New preprint on wavelength selection for molecular composition inference from diffuse spectroscopy by our MSc student Kevin Scibilia.
• Apr 2026Final defense pitch in Berlin for the BMBF GO-Bio next startup grant on rapid tumor biopsy analysis with hyperspectral imaging and ML.
• 2026Brain tumor growth inversion via differentiable neural surrogates, with PhD student Jonas Weidner, at MIDL 2026.
• 2026PREDICT-GBM, a multi-center platform for personalized glioblastoma radiotherapy planning, published in npj Digital Medicine.
• 2026Started designing the structure for the Responsible and Applied AI Center in Kenya.
• 2025Individualized glioma radiotherapy planning published in Nature Communications.
• 2024Physics-regularized multi-modal image assimilation for brain tumor localization at NeurIPS 2024.
• Dec 2023Completed my PhD at TU Munich with summa cum laude.
• Oct 2023Research stay at the Biomedical Optics Research Lab, UCL London, with Prof. Ilias Tachtsidis.

Contact

ivan.ezhov@tum.de
Chair for AI in Healthcare and Medicine
Technical University of Munich (TUM) and TUM University Hospital
Munich, Germany