Canine Signalling Interfaces for Bio Detection Dogs
This project started in 2013 as a collaboration between the ACI Lab and Medical Detection Dogs (MDD), the UK Charity that pioneered bio-detection with dogs. The ACI Lab team is led by Prof Clara Mancini, with doctoral student Kingsley Amoafo, co-supervisor Dr Colette Christiansen, and technical support from Mikki Thomas and his team, as well as previous contributions by Lucy Withington, Dr David Díaz Pardo de Vera and Dr Paul Piwek. The MDD team is led by Dr Claire Guest OBE, with Rob Harris, Mark Somerville and Claire Dowse.
Overview
Although common, some cancers are difficult to diagnose early, with non-invasive tests being highly inaccurate and invasive tests causing serious side effects while still being inconclusive. So, there is growing interest in finding accurate, non-invasive tests for early cancer diagnosis.
Dogs can be trained to recognise the odour of cancer cells in biological samples (e.g. urine, sweat, breath) and clinical trials are increasingly highlighting the potential of cancer detection with dogs. So, there is growing interest in learning from dogs' detection work to inform the development of diagnostic tools that emulate dogs' olfactory detection.
However, the conventional signalling protocols the dogs are trained to use to communicate what they detect (e.g. sitting down in front of a positive sample) are inconsistent with their evolutionary response to odours of interest and only allow them to provide binary responses (‘yes’ or ‘no’). This interferes with and limits the potential of the dogs’ detection work and limits what can be learned from the process.
​​
Harnessing the dogs' stimulus response
​
In collaboration with Medical Detection Dogs, world pioneer of bio-detection with dogs, we have developed a canine-centred sensor interface to record and analyse dogs’ spontaneous interaction patterns with biological samples, based on pressure data, and infer odour concentration levels without interfering with the dogs and their work. Enabling the dogs to spontaneously respond to the olfactory stimulus increases signalling reliability, and enabling them to provide nuanced responses increases signalling accuracy, possibly identifying different stages of the disease.
Our early findings suggest a correlation between pressure patterns and odour concentration. For example, the graphs shown here describe the interaction of a bio-detection dog with three samples containing decreasing concentrations of amyl acetate. During the development of the canine interface we used amyl acetate to control the odour concentration in the samples screened by the dogs, which has allowed us to better study their interaction patterns with the samples. ​
Lucy's early application of artificial neural networks (Multilayer Perceptron, MLP) to the classification task has yielded promising results, with the same classification rate for positive samples as the dogs’.​
Colorectal cancer detection
​
Medical Detection Dogs are currently using the latest generation of our sensor technology in their colorectal cancer detection trials. The apparatus captures both pressure and proximity data. Kingsley is developing a machine learning model to analyse the data to inform the development of a bio-electronic nose.
Video by Medical Detection Dogs
Further readings
​​
Withington, Lucy; Diaz Pardo de Vera, David; Guest, Claire; Mancini, Clara and Piwek, Paul (2021).Artificial Neural Networks for classifying the time series sensor data generated by medical detection dogs. Expert Systems with Applications, 184, article no. 115564.
​
Mancini, C., Harris, R., Aengenheister, B., Guest, C. (2015). Re-Centering Multispecies Practices: a Canine Interface for Cancer Detection Dogs. Proc. International ACM CHI Conference on Human Factors in Computing Systems, CHI’15, ACM Press, pp. 2673-2682.
Johnston-Wilder, O., Mancini, C., Aengenheister, B., Mills, J., Harris, R., Guest, C. (2015). Sensing the shape of canine responses to cancer. Intl. Congress on Animal-Computer Interaction, ACI’15, Proc. International Conference on Advances in Computer Entertainment Technology, article no. 63, ACM Digital Library.