Application of neural networks to flow cytometry data analysis and real-time cell classification.

Conventional analysis of flow cytometric data requires that population identification be performed graphically after a sample has been run using two-parameter scatter plots. As more parameters are measured, the number of possible two-parameter plots increases geometrically, making data analysis increasingly cumbersome. Artificial Neural Systems (ANS), also known as neural networks, are a powerful and convenient method for overcoming this data bottleneck. ANS "learn" to make classifications using all of the measured parameters simultaneously. Mathematical models and programming expertise are not required. ANS are inherently parallel so that high processing speed can be achieved. Because ANS are nonlinear, curved class boundaries and other nonlinearities can emerge naturally. Here, we present biomedical and oceanographic data to demonstrate the useful properties of neural networks for processing and analyzing flow cytometry data. We show that ANS are equally useful for human leukocytes and marine plankton data. They can easily accommodate nonlinear variations in data, detect subtle changes in measurements, interpolate and classify cells they were not trained on, and analyze multiparameter cell data in real time. Real-time classification of a mixture of six cyanobacteria strains was achieved with an average accuracy of 98%.

Use of a neural net computer system for analysis of flow cytometric data of phytoplankton populations.

Flow cytometry has been used over the past 5 years to begin detailed exploration of the distribution and abundance of picoplankton in the oceans. Light scattering and fluorescence measurements on individual plankton cells in seawater samples allow construction of population signatures from size and pigment characteristics. The use of "list mode" data has made these studies possible, but on-shore analysis of copious data does not permit on-site reexamination of important or unexpected observations, and overall effort is greatly handicapped by data analysis time. Here we describe the application of neural net computer technology to the analysis of flow cytometry data. Although the data used in this study are from oceanographic research, the results are general and should be directly applicable to flow cytometry data of any sort. Neural net computers are ideally suited to perform the pattern recognition required for the quantitative analysis of flow cytometry data. Rather than being programmed to perform analysis, the neural net computer is "taught" how to analyze the cell populations by presenting examples of inputs and correct results. Once the system is "trained," similar data sets can be analyzed rapidly and objectively, minimizing the need for laborious user interaction. The neural network described here offers the advantages of 1) adaptability to changing conditions and 2) potential real-time analysis. High accuracy and processing speed near that required for real-time classification have been achieved in a software simulation of the neural network on a Macintosh SE personal computer.

ir laser induced fluorescence cell for multiple photon processes.

An efficient, easy to construct, long-path laser-induced fluorescence cell is described which is useful in studies of multiple ir photon induced phenomena.