Training nuclei detection algorithms with simple annotations
Journal article, 2017

Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.

Active learning

Machine learning

Nuclei detection

Training set generation

Author

Henning Kost

Fraunhofer-Institut fur Bildgestutzte Medizin MEVIS

André Homeyer

Fraunhofer-Institut fur Bildgestutzte Medizin MEVIS

Jesper Molin

Sectra

Chalmers, Applied Information Technology (Chalmers), Interaction design

Claes Lundström

Linköping University

Sectra

Horst Karl Hahn

Fraunhofer-Institut fur Bildgestutzte Medizin MEVIS

Journal of Pathology Informatics

2229-5089 (ISSN) 2153-3539 (eISSN)

Vol. 8 1 206227

Subject Categories

Medical Engineering

DOI

10.4103/jpi.jpi_3_17

More information

Latest update

11/7/2022