Methods for using artificial neural network analysis on flow cytometry data for cancer diagnosis

A computer-implemented method of applying artificial neural networks to a plurality of events of interest in a biological sample to generate a classification of the biological sample, comprising:

• (a) performing, by a computer, analysis of the biological sample, the analysis comprising:
• obtaining measurements of a plurality of event features for the plurality of events of interest from a flow cytometer instrument,
• applying a gating algorithm ensemble to the measurements of the plurality of event features to selectively focus on the measurements of the plurality of event features for a subset of the plurality of events of interest,
• using four or more flow cytometer measurement channels to define a feature coordinate space, the feature coordinate space comprising four or more axes, each axis corresponding to a different channel of the four or more flow cytometer measurement channels, wherein each of the four or more flow cytometer measurement channels produces measurements of the plurality of event features, and
• using the measurements of the plurality of event features for the subset of the plurality of events of interest to define locations for the subset of the plurality of events of interest in the feature coordinate space to form a distribution in the feature coordinate space indicative of an event population of interest;
• (b) applying, by the computer, an artificial neural network detection structure to the distribution in the feature coordinate space indicative of the event population of interest, the detection structure employing an artificial neural network to correlate the distribution in the feature coordinate space indicative of the event population of interest with a distribution in a reference feature coordinate space indicative of a reference event population;
• (c) determining, by the computer, whether the biological sample contains cells indicative of the classification;
• and
• (d) automatically generating, by the computer, a report comprising the classification, wherein classification comprises assigning at least one category to the biological sample,
• wherein the distribution in the feature coordinate space indicative of the event population of interest is formed by:
• (a) dividing each axis of the feature coordinate space into a plurality of segments, thereby dividing the feature coordinate space into a plurality of hypervoxels, and
• (b) for a hypervoxel of the plurality of hypervoxels, determining a count of a number of events of interest comprising an event feature value that locates the event of interest in the hypervoxel.