Geert Litjens is an assistant professor of Computational Pathology at the Radboud University Medical Center. His research is at the intersection of machine learning, medical imaging, and oncology. He co-chairs the Computational Pathology Group, which develops automated machine learning systems for cancer detection, biomarker discovery and quantification, and improved prognostication.
He is also the developer of the ASAP software package for analyzing and visualizing whole-slide images and (co-)organizer of several high-profile challenges in medical imaging such as PROMISE12, CAMELYON, and PANDA. He (co-)authored over 60 publications in medical, imaging, and machine learning conferences and journals.
PhD in Medical Sciences, 2015
Radboud University Medical Center
MSc in Biomedical Image Analysis, 2010
Eindhoven University of Technology
BSc in Biomedical Engineering, 2006
Eindhoven University of Technology
CPG indicates funding for the Computational Pathology Group
This is a selection of the publications I am most proud of. For a full listing, please go to this page.
Extensive experience with Python for data science and machine learning. Often used package include Numpy, Scipy, Tensorflow, Theano, and Matplotlib.
I used C++ for the development of image analysis algorithms using ITK and MeVisLab. In addition, ASAP is an open source Qt-based C++ application, developed for both Windows and Linux.
All software and algorithms I develop are under version control. Nowadays, we make extensive use of Git and Github for source code management.
Since 2014 my research has focused on challenges in diagnostic pathology. This has helped me attain knowledge on pathologist’s workflows in many applications, with emphasis on those in oncology.
During my MSc and PhD theses I worked at a major radiology hardware vendor and at a radiology department. I have some experience with all imaging modalities common in radiology, but most expertise with different types of MR imaging.
I have taken several (bio-)statistics courses and have working experience with advanced statistical methods. Examples include survival analysis and mixed models.
Since 2013 I have been developing algorithms based on deep learning, initially with Theano, later with TensorFlow. My initial work and that of many others is covered in our [survey]({{< ref “/publication/litj-17/index.md” >}}).
I have been working on image processing tools for over a decade and have applied, among others, image registration, filtering, and morphological image processing in different projects.
Dutch: native
English: fluent
German: intermediate
French: basic