Automatic Embedding Interventions for the Classification of Hematopoietic Cells

Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition, vol. 36, pp. 5104–5110

Abstract

The classification of hematopoietic cells is the most essential step in automating the analysis of human bone marrow samples. However, the complex structure of cell classes as well as class imbalance make this a challenging task, even for neural networks. Based on projective latent interventions, we propose automatic interventions that iteratively update a learned embedding with suitable transformations that shift different cell types apart and contract samples of the same type together. We present different ways of applying these: either directly on a higher-dimensional embedding or in a parametric version in two dimensions. We analyze the hyper-parameters and evaluate the proposed approach on a challenging dataset of hematopoietic cells. The results show an improvement of up to 3 percentage points for the classification F-score.

Authors 7

1. Philipp Gräbel Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Institute of Imaging and Computer Vision,Germany

   Institute of Imaging and Computer Vision, RWTH Aachen University, Germany

2. Julian Thull Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Institute of Imaging and Computer Vision,Germany

   Institute of Imaging and Computer Vision, RWTH Aachen University, Germany

3. Martina Margrit Crysandt Aachen Department of Hematology and Oncology

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Dept. of Hematology and Oncology University Hospital,Germany

   Dept. of Hematology and Oncology University Hospital, RWTH Aachen University, Germany

4. Barbara M. Klinkhammer Aachen Institute of Pathology

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   University Hospital RWTH Aachen University,Institute of Pathology,Germany

   Institute of Pathology, University Hospital RWTH Aachen University, Germany

5. Peter Boor Aachen Institute of Pathology

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   University Hospital RWTH Aachen University,Institute of Pathology,Germany

   Institute of Pathology, University Hospital RWTH Aachen University, Germany

6. Tim H. Brümmendorf Aachen Department of Hematology and Oncology

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Dept. of Hematology and Oncology University Hospital,Germany

   Dept. of Hematology and Oncology University Hospital, RWTH Aachen University, Germany

7. Dorit Merhof Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Institute of Imaging and Computer Vision,Germany

   Institute of Imaging and Computer Vision, RWTH Aachen University, Germany