Training Nuclei Detection Algorithms with Simple Annotations

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...

Full description

Saved in:
Bibliographic Details
Published in:Journal of pathology informatics 2017-01, Vol.8 (1), p.21-21, Article 21
Main Authors: Kost, Henning, Homeyer, André, Molin, Jesper, Lundström, Claes, Hahn, Horst Karl
Format: Article
Language:English
Subjects:
Active learning
Algorithms
Annotations
Breast cancer
Cancer
Classification
Extraction
Image detection
Machine learning
Markers
Nuclei
Nuclei detection
Pathology
Run time (computers)
Teaching methods
Tessellation
Training
Training set generation
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2153-3539
2229-5089
2153-3539
DOI:10.4103/jpi.jpi_3_17