Automatic Detection of Tumor Buds in Pan-Cytokeratin Stained Colorectal Cancer Sections by a Hybrid Image Analysis Approach

Bergler M, Benz M, Rauber D, Hartmann D, Kötter M, Eckstein M, Schneider-Stock R, Hartmann A, Merkel S, Bruns V, Wittenberg T, Geppert CI (2019)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2019

Publisher: Springer International Publishing

City/Town: Cham

Pages Range: 83--90

Conference Proceedings Title: Digital Pathology

Event location: Warwick , UK

ISBN: 978-3-030-23937-4

URI: https://link.springer.com/chapter/10.1007/978-3-030-23937-4_10

DOI: 10.1007/978-3-030-23937-4_10

Abstract

This contribution introduces a novel approach to the automatic detection of tumor buds in a digitalized pan-cytokeratin stained colorectal cancer slide. Tumor buds are representing an invasive pattern and are frequently investigated as a new diagnostic factor for measuring the aggressiveness of colorectal cancer. However, counting the number of buds under the microscope in a high power field by eyeballing is a strenuous, lengthy and error-prone task, whereas an automated solution could save time for the pathologists and enhance reproducibility. We propose a new hybrid method that consists of two steps. First possible tumor bud candidates are detected using a chain of classical image processing methods. Afterwards a convolutional deep neural network is applied to filter and reduce the number of false positive candidates detected in the first step. By comparing the automatically detected buds with a gold standard created by manual annotations, we gain a score of 0.977 for precision and 0.934 for sensitivity in our test sets on over 8.000 tumor buds.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Bergler, M., Benz, M., Rauber, D., Hartmann, D., Kötter, M., Eckstein, M.,... Geppert, C.-I. (2019). Automatic Detection of Tumor Buds in Pan-Cytokeratin Stained Colorectal Cancer Sections by a Hybrid Image Analysis Approach. In Reyes-Aldasoro CC, Janowczyk A, Veta M, Bankhead P, Sirinukunwattana K (Eds.), Digital Pathology (pp. 83--90). Warwick , UK: Cham: Springer International Publishing.

MLA:

Bergler, Matthias, et al. "Automatic Detection of Tumor Buds in Pan-Cytokeratin Stained Colorectal Cancer Sections by a Hybrid Image Analysis Approach." Proceedings of the European Congress on Digital Pathology, Warwick , UK Ed. Reyes-Aldasoro CC, Janowczyk A, Veta M, Bankhead P, Sirinukunwattana K, Cham: Springer International Publishing, 2019. 83--90.

BibTeX: Download