Guided Representation Learning for the Classification of Hematopoietic Cells
Abstract
Cell classification in human bone marrow microscopy images is a challenging image analysis task due to the number and inter-connection of cell types. While machine learning techniques have vastly higher throughput and could thus be more reliable, humans are intrinsically capable of understanding relations between cell types. In this paper, we propose methods to incorporate such intrinsic model knowledge based on representation learning. To this end, we construct a manually defined, two-dimensional reference embedding, coined embedding guide, which we use together with inverse dimensionality reduction, a distance-based loss and a growing embedding technique. Results show improved classification scores as well as a visually interpretable and clearly defined embedding space.
Cite
Text
Gräbel et al. "Guided Representation Learning for the Classification of Hematopoietic Cells." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00067Markdown
[Gräbel et al. "Guided Representation Learning for the Classification of Hematopoietic Cells." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/grabel2021iccvw-guided/) doi:10.1109/ICCVW54120.2021.00067BibTeX
@inproceedings{grabel2021iccvw-guided,
title = {{Guided Representation Learning for the Classification of Hematopoietic Cells}},
author = {Gräbel, Philipp and Crysandt, Martina and Klinkhammer, Barbara Mara and Boor, Peter and Brümmendorf, Tim H. and Merhof, Dorit},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2021},
pages = {545-551},
doi = {10.1109/ICCVW54120.2021.00067},
url = {https://mlanthology.org/iccvw/2021/grabel2021iccvw-guided/}
}