Publications
Here you can find our latest publications. We are working on deep learning-based microscopy applications, such as pathology:
2017
1.
Aubreville, Marc; Krappmann, Maximilian; Bertram, Christof; Klopfleisch, Robert; Maier, Andreas
A Guided Spatial Transformer Network for Histology Cell Differentiation Miscellaneous
2017, (Artwork Size: 5 pages ISBN: 9783038680369 ISSN: 2070-5786 Pages: 5 pages Publication Title: Eurographics Workshop on Visual Computing for Biology and Medicine).
Abstract | Links | BibTeX | Tags: Applied computing, Bioinformatics, Computing methodologies, FOS: Computer and information sciences, Neural networks, Object detection
@misc{aubreville_guided_2017,
title = {A Guided Spatial Transformer Network for Histology Cell Differentiation},
author = {Marc Aubreville and Maximilian Krappmann and Christof Bertram and Robert Klopfleisch and Andreas Maier},
url = {https://diglib.eg.org/handle/10.2312/vcbm20171233},
doi = {10.2312/VCBM.20171233},
year = {2017},
date = {2017-01-01},
urldate = {2025-02-11},
publisher = {The Eurographics Association},
abstract = {Identification and counting of cells and mitotic figures is a standard task in diagnostic histopathology. Due to the large overall cell count on histological slides and the potential sparse prevalence of some relevant cell types or mitotic figures, retrieving annotation data for sufficient statistics is a tedious task and prone to a significant error in assessment. Automatic classification and segmentation is a classic task in digital pathology, yet it is not solved to a sufficient degree. We present a novel approach for cell and mitotic figure classification, based on a deep convolutional network with an incorporated Spatial Transformer Network. The network was trained on a novel data set with ten thousand mitotic figures, about ten times more than previous data sets. The algorithm is able to derive the cell class (mitotic tumor cells, non-mitotic tumor cells and granulocytes) and their position within an image. The mean accuracy of the algorithm in a five-fold cross-validation is 91.45 %. In our view, the approach is a promising step into the direction of a more objective and accurate, semi-automatized mitosis counting supporting the pathologist.},
note = {Artwork Size: 5 pages
ISBN: 9783038680369
ISSN: 2070-5786
Pages: 5 pages
Publication Title: Eurographics Workshop on Visual Computing for Biology and Medicine},
keywords = {Applied computing, Bioinformatics, Computing methodologies, FOS: Computer and information sciences, Neural networks, Object detection},
pubstate = {published},
tppubtype = {misc}
}
Identification and counting of cells and mitotic figures is a standard task in diagnostic histopathology. Due to the large overall cell count on histological slides and the potential sparse prevalence of some relevant cell types or mitotic figures, retrieving annotation data for sufficient statistics is a tedious task and prone to a significant error in assessment. Automatic classification and segmentation is a classic task in digital pathology, yet it is not solved to a sufficient degree. We present a novel approach for cell and mitotic figure classification, based on a deep convolutional network with an incorporated Spatial Transformer Network. The network was trained on a novel data set with ten thousand mitotic figures, about ten times more than previous data sets. The algorithm is able to derive the cell class (mitotic tumor cells, non-mitotic tumor cells and granulocytes) and their position within an image. The mean accuracy of the algorithm in a five-fold cross-validation is 91.45 %. In our view, the approach is a promising step into the direction of a more objective and accurate, semi-automatized mitosis counting supporting the pathologist.