Urologic Oncology / Digital Pathology
The junior working group "Urologic Oncology / Digital Pathology" under the guidance of Dr. Yuri Tolkach has research interests in following areas:
- Computational pathology and artificial intelligence - based methods for diagnostic and prognostic applications (including correlation to radiology and nuclear medicine imaging).
- Molecular characterization of the uro-oncological diseases.
- Genetic evolution of primary and metastatic prostate cancer, including mathematical modelling (in cooperation with Florian Kreten and Anton Bovier, Hausdorff Center for Mathematics, University of Bonn, Bonn, Germany).
- Tolkach Y, et al. High-accuracy prostate cancer pathology using deep learning. Nature Machine Intelligence 2020. doi: 10.1038/s42256-020-0200-7.
- Eminaga O, Tolkach Y, Kunder C, et al. Deep Learning for Prostate Pathology (Preprint). ArXiv 2019. arXiv:1910.04918.
- Eminaga O, Abbas M, Tolkach Y, et al. Biologic and Prognostic Feature Scores from Whole-Slide Histology Images Using Deep Learning (Preprint). ArXiv 2019. arXiv:1910.09100.
- Kremer A, Kremer T, Kristiansen G, and Tolkach Y. Where is the limit of prostate cancer biomarker research? Systematic investigation of potential prognostic and diagnostic biomarkers. BMC Urology 2019; 19:46.
- Tolkach Y, Ellinger J, Kremer A, et al. Apelin and apelin receptor expression in renal cell carcinoma. Br J Cancer 2019; 120: 633-639.
Correlation between pathology(blue – high-grade prostate cancer, green – low-grade prostate cancer) and PSMA-based positron-emission tomography / magnet resonance tomography (PSMA PET / MRT), Credits: Iurii Tolkach
Prognostic role of mRNA expression in primary prostate cancer (Top 15 genes with the highest prognostic value), Credits: Iurii Tolkach