Automated Particle Identification through Regression Analysis of Size, Shape and Colour

Rodriquez Luna, J. C., Cooper, J.M. and Neale, S. (2016) Automated Particle Identification through Regression Analysis of Size, Shape and Colour. In: SPIE Photonics West, San Francisco, CA, USA, 13-18 Feb 2016, 97110R. (doi: 10.1117/12.2211107)

Abstract

Rapid point of care diagnostic tests and tests to provide therapeutic information are now available for a range of specific conditions from the measurement of blood glucose levels for diabetes to card agglutination tests for parasitic infections. Due to a lack of specificity these test are often then backed up by more conventional lab based diagnostic methods for example a card agglutination test may be carried out for a suspected parasitic infection in the field and if positive a blood sample can then be sent to a lab for confirmation. The eventual diagnosis is often achieved by microscopic examination of the sample. In this paper we propose a computerized vision system for aiding in the diagnostic process; this system used a novel particle recognition algorithm to improve specificity and speed during the diagnostic process. We will show the detection and classification of different types of cells in a diluted blood sample using regression analysis of their size, shape and colour. The first step is to define the objects to be tracked by a Gaussian Mixture Model for background subtraction and binary opening and closing for noise suppression. After subtracting the objects of interest from the background the next challenge is to predict if a given object belongs to a certain category or not. This is a classification problem, and the output of the algorithm is a Boolean value (true/false). As such the computer program should be able to ”predict” with reasonable level of confidence if a given particle belongs to the kind we are looking for or not. We show the use of a binary logistic regression analysis with three continuous predictors: size, shape and color histogram. The results suggest this variables could be very useful in a logistic regression equation as they proved to have a relatively high predictive value on their own.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Cooper, Professor Jonathan and Neale, Dr Steven
• Authors: Rodriquez Luna, J. C., Cooper, J.M., and Neale, S.
• College/School: College of Science and Engineering > School of Engineering > Biomedical Engineering
• Copyright Holders: Copyright © 2016 SPIE
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher.