Deep learning based thermal image segmentation for laboratory animals tracking

ABSTRACT

Automated systems for behaviour classification of laboratory animals are an attractive alternative to manual scoring. However, the proper animals separation and tracking, especially when they are in close contact, is the bottleneck of the behaviour analysis systems. In this paper, we propose a method for the segmentation of thermal images of laboratory rats that are in close contact during social behaviour tests. For this, we are using thermal imaging – a technology that requires neither light nor human presence. The aim of the study was: (1) an efficiency analysis of deep learning based image segmentation algorithms for the need of laboratory rats images, (2) analysis of different methods of original thermal data conversion to grey scale images for the purpose of the segmentation, (3) evaluation of the image data range impact on segmentation results using deep learning networks. We have trained U-Net and V-Net architectures with images obtained from different temperature ranges. The results indicate, that networks trained on images containing a narrow range of temperature data equal to animals’ body temperature or even its part, are able to better perform the object segmentation than networks trained on the original data.

KEYWORDS:

• Image segmentation
• deep learning
• automated behavior recognition
• rodent social behavior

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work has been partially supported by Statutory Funds of Electronics, Telecommunications and Informatics Faculty, Gdansk University of Technology.

Notes on contributors

Magdalena Mazur-Milecka

Magdalena Mazur-Milecka works at Biomedical Engineering Department at Gdansk University of Technology. Her research area is computer vision and machine learning in biology and medicine.

Jacek Ruminski

Prof. Jacek Ruminski (Ph.D. in Computer Science, habilitation in Biocybernetics and Biomedical Engineering) is a head of Biomedical Engineering Department at GUT. He has spent about 2 years working on projects at different European institutions. He was a coordinator or an investigator in about 20 projects receiving a number of awards, including for best papers, practical innovations (7 medals and awards) and also the Andronicos G. Kantsios Award. Prof. Ruminski is the author of about 210 papers, and several patent applications and patents. Recently he was a main coordinator of the European eGlasses project focused on HCI using smartglasses. His research is focused on application of machine learning in healthcare.