AUTOMATED PARTICLE CLASSIFICATION BASED ON DIGITAL ACQUISITION AND ANALYSIS OF FLOW CYTOMETRIC PULSE WAVE-FORMS

In flow cytometry, the typical use of front-end analog processing limi ts the pulse waveform features that can be measured to pulse integral, height, and width. Direct digitizing of the waveforms provides a mean s for the extraction of additional features, for example, pulse skewne ss and kurtosis, and Fourier properties. In this work, we have first d emonstrated that the Fourier properties of the pulse can be employed u sefully for discrimination between different types of cells that other wise cannot be classified by using only time-domain features of the pu lse. We then implemented and evaluated automatic procedures for cell c lassification based on neural networks. We established that neural net works could provide an efficient means of classification of cell types without the need for user interaction. The neural networks were also employed in an innovative manner for analysis of the digital flow cyto metric data without feature extraction. The performance of the neural networks was compared with that of a more conventional means of classi fication, the K-means clustering algorithm. Neural networks can be rea lized in hardware, and this, in addition to their highly parallel arch itecture, makes them an important potential part of real-time analysis systems. These results are discussed in terms of the design of a real -time digital data acquisition system for flow cytometry. (C) 1996 Wil ey-Liss, Inc.