Deep learning of diffraction image patterns for accurate classification of five cell types.

Abstract

Development of label-free methods for accurate classification of cells with high throughput can yield powerful tools for biological research and clinical applications. We have developed a deep neural network of DINet for extracting features from cross-polarized diffraction image (p-DI) pairs on multiple pixel scales to accurately classify cells in five types. A total of 6185 cells were measured by a polarization diffraction imaging flow cytometry (p-DIFC) method followed by cell classification with DINet on p-DI data. The averaged value and SD of classification accuracy were found to be 98.9% ± 1.00% on test data sets for 5-fold training and test. The invariance of DINet to image translation, rotation, and blurring has been verified with an expanded p-DI data set. To study feature-based classification by DINet, two sets of correctly and incorrectly classified cells were selected and compared for each of two prostate cell types. It has been found that the signature features of large dissimilarities between p-DI data of correctly and incorrectly classified cell sets increase markedly from convolutional layers 1 and 2 to layers 3 and 4. These results clearly demonstrate the importance of high-order correlations extracted at the deep layers for accurate cell classification.