Share Email Print
cover

Proceedings Paper

Automated classification and recognition of bacterial particles in flow by multi-angle scatter measurement and a support-vector machine classifier
Author(s): Bartek Rajwa; Murugesan Venkatapathi; Kathy Ragheb; Padmapriya P. Banada; E. Daniel Hirleman; Todd Lary; J. Paul Robinson
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Biological microparticles scatter light in all directions when illuminated. The complex scatter pattern is dependent on particle size, shape, refraction index, density, and morphology. Commercial flow cytometers allow measurement at two nominal angles (2°⩽θ1⩽20° and 70°⩽θ2⩽110°) of scattered light intensity from individual microparticles with a speed varying from 10 to 10000 particles per second. The choice of angle is dictated by the fact that scattered light in the small-angle region is primarily influenced by cell size and refractive index, whereas side scatter intensity is related to the granularity of cellular structures. These rudimentary measurements cannot be used to separate populations of cells of similar shape, size, or structure. Hence, there have been several attempts in cytometry to measure the entire scatter patterns. However, the published concepts required use of unique custom-built cytometers and could not be applied to existing instruments. The presented work demonstrates application of pattern-recognition techniques to classify particles on the basis of their discrete scatter patterns collected at just five different angles, and accompanied by the measurement of axial light loss. Our approach can be used with existing instruments and requires only the addition of a custom-built scatter-detector. Our analytical model of scatter of laser beams by individual bacterial cells suspended in a fluid was used to determine the location for scatter sensors. Experimental results were used to train the pattern recognition system. It has been shown that information provided just by six scatter-related parameters was sufficient to recognize various bacteria with 90-99% success rate.

Paper Details

Date Published: 19 February 2007
PDF: 7 pages
Proc. SPIE 6441, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues V, 64410O (19 February 2007); doi: 10.1117/12.699227
Show Author Affiliations
Bartek Rajwa, Bindley Bioscience Ctr., Purdue Univ. (United States)
Murugesan Venkatapathi, Bindley Bioscience Ctr., Purdue Univ. (United States)
Purdue Univ. (United States)
Kathy Ragheb, Bindley Bioscience Ctr., Purdue Univ. (United States)
Padmapriya P. Banada, Purdue Univ. (United States)
E. Daniel Hirleman, Purdue Univ. (United States)
Todd Lary, Cellular Analysis Technology Ctr., Beckman Coulter, Inc. (United States)
J. Paul Robinson, Bindley Bioscience Ctr., Purdue Univ. (United States)


Published in SPIE Proceedings Vol. 6441:
Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues V
Daniel L. Farkas; Robert C. Leif; Dan V. Nicolau, Editor(s)

© SPIE. Terms of Use
Back to Top