NAP
The aim of the project is to investigate pathological sections of glioblastomas - the most common malignant brain tumors with an infauste prognosis1 - with modern machine learning methods and thus to relieve neuropathologists.
According to current research knowledge, the resistance of gliobloastoma to therapy is largely dependent on its strong heterogeneity. However, determination of heterogeneity is a lengthy process that is not part of standard diagnostics. In order to incorporate this step into standard diagnostics, the NAP project is training machine-leaning models that automatically analyze hematoxylin and eosin (HE) stained tissue slides. These HE slides are generated by default in tumor diagnostics, which does not impose any additional burden on clinical staff.
The Institute of Neuropathology at TUM provides the necessary image data for this purpose. The individual image scenes of the pathological sections are each around 6.5 gigabytes in size and have a resolution of 70,000 by 40,000 pixels.
1Glioblastoma multiforme (IDH wt.) (Latin for multiform) is the most common brain malignancy (WHO grade IV) in adults. The median survival is 15 months.
Publications
2026
- Krauss, Sara and Spiess, Ellena and Hieber, Daniel and Schobel, Johannes and Kramer, Frank and Müller, Dominik
(2026)
Overcoming Domain Shift in Atypical Mitotic Figure Detection
with Deep Ensemble Learning. (opens in a new window)
In: (Proceedings of the) Medical Informatics Europe (MIE), May, 25-28, 2026, Genova, Italy, pp. 77-81, Paper / Research Article.
(Studies in Health Technology and Informatics; 336).
ISBN 9781643686615
view fulltext
2025
- Spiess, Ellena and Müller, Dominik and Dinser, Moritz and Herbort, Volker and Liesche-Starnecker, Friederike and Schobel, Johannes and Hieber, Daniel
(2025)
Automatic Segmentation of Histopathological Glioblastoma Whole-Slide Images Utilizing MONAI. (opens in a new window)
In: (Proceedings of the) 35th Medical Informatics Europe Conference (MIE), May, 19-21, 2025, Glasgow, Scotland, UK, pp. 88-92.
(Studies in Health Technology and Informatics; 327).
ISBN 9781643685960
view fulltext
2024
- Hieber, Daniel and Haisch, Nico and Grambow, Gregor and Holl, Felix and Liesche-Starnecker, Friederike and Pryss, Rüdiger and Schlegel, Jürgen and Schobel, Johannes
(2024)
Comparing nnU-Net and deepflash2 for Histopathological Tumor Segmentation. (opens in a new window)
In: (Proceedings of the) Medical Informatics Europe Conference (MIE), September, 25-29, 2024, Athens, Greece, pp. 606-610.
(Studies in Health Technology and Informatics; 316).
ISBN 9781643685335
view fulltext - Hieber, Daniel and Holl, Felix and Nickl, Vera and Liesche-Starnecker, Friederike and Schobel, Johannes
(2024)
Perspective Chapter: Computer Vision-Based Digital Pathology for Central Nervous System Tumors – State-of-the-Art and Current Advances. (opens in a new window)
In:
Advanced Concepts and Strategies in Central Nervous System Tumors / Chow, Frances ; Hwang, Lindsay (Eds).
London: IntechOpen.
ISBN 9780850148084
view fulltext - Hieber, Daniel and Jungbäck, Nicola and Holl, Felix and Märkl, Bruno and Pryss, Rüdiger and Schobel, Johannes and Liesche-Starnecker, Friederike
(2024)
Using Eye-Tracking to find Differences in the Analysis ofWhole-Slide Images Between Physicians and Machine Learning Models –A Study Design. (opens in a new window)
In: (Meeting Abstracts of the) 68th Annual Meeting of the German Society of Neuropathology and Neuroanatomy (DGNN), 12.-14. September 2024, Regensburg, Germany, p. 45.
view fulltext - Hieber, Daniel and Jungbäck, Nicola and Holl, Felix and Märkl, Bruno and Pryss, Rüdiger and Schobel, Johannes and Liesche-Starnecker, Friederike
(2024)
Why We Don’t Save Whole-Slide Images as Lego Mosaics –Putting the Scale of Whole-Slide Images into Perspective. (opens in a new window)
In: (Meeting Abstracts of the) 68th Annual Meeting of the German Society of Neuropathology and Neuroanatomy (DGNN), 12.-14. September 2024, Regensburg, Germany, p. 46.
view fulltext
2023
- Prokop, Georg and Wiestler, Benedikt and Hieber, Daniel and Withake, Fynn and Mayer, Karoline and Gempt, Jens and Delbridge, Claire and Schmidt-Graf, Friederike and Pfarr, Nicole and Märkl, Bruno and Schlegel, Jürgen and Liesche-Starnecker, Friederike
(2023)
Multiscale quantification of morphological heterogeneity with creation of a predictor of longer survival in glioblastoma. (opens in a new window)
International Journal of Cancer.
ISSN 1097-0215
view fulltext - Hieber, Daniel and Karthan, Maximilian and Holl, Felix and Prokop, Georg and Märkl, Bruno and Pryss, Rüdiger and Liesche-Starnecker, Friederike and Schobel, Johannes
(2023)
Evaluating the Segment Anything Model for Histopathological Tissue Segmentation. (opens in a new window)
In: 68. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e. V. (GMDS), 17.-21. September 2023, Heilbronn, Germany, DocAbstr. 159.
view fulltext - Hieber, Daniel and Prokop, Georg and Karthan, Maximilian and Märkl, Bruno and Schlegel, J. and Pryss, Rüdiger and Grambow, Gregor and Schobel, Johannes and Liesche-Starnecker, Friederike
(2023)
Machine learning-based assessment of intratumor heterogeneity in glioblastoma. (opens in a new window)
In: (Abstracts of the) 20th International Congress of Neuropathology (ICN), September, 13-16, 2023, Berlin, Germany, Abstr. eP-NO-A78.
view fulltext - Hieber, Daniel and Prokop, Georg and Karthan, Maximilian and Märkl, Bruno and Schobel, Johannes and Liesche-Starnecker, Friederike
(2023)
Neural Network Assisted Pathology for Labeling Tumors in Whole-Slide-Images of Glioblastoma. (opens in a new window)
In: (Abstractband der) 106. Jahrestagung der Deutschen Gesellschaft für Pathologie "Pathology - more than meets the eye", 1.-3. Juni 2023, Leipzig, Germany, p. 218.
view fulltext - Hieber, Daniel and Prokop, Georg and Karthan, Maximilian and Holl, Felix and Kestler, Hans A. and Grambow, Gregor and Märkl, Bruno and Pryss, Rüdiger and Liesche-Starnecker, Friederike and Schobel, Johannes (2023) Towards an Architecture for Collecting a Multidimensional Glioblastoma Dataset. (opens in a new window) In: (Proceedings of the) IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS), June, 22-24, 2023, L'Aquila, Italy, pp. 904-909. ISBN 9798350312249
Contact
Team
Prof. Dr. Johannes Schobel
Daniel Hieber
Maximilian Karthan
PD Dr. Friederike Liesche-Starnecker (UK-Augsburg)
Partners
Institute for Pathology and Molecular Diagnostics - Augsburg University Hospital
Funding
/
Duration
Since July 2021
Links
/
