Label‐Free Imaging Flow Cytometry for Cell Classification Based on Multiple Interferometric Projections Using Deep Learning

Abstract

A new label‐free imaging flow cytometry method for noninvasive and automated biological cell classification is presented. Each cell is rolled during flow, and its off‐axis holograms from multiple viewpoints are acquired. Using the reconstructed quantitative phase profiles of the cell projections, highly discriminating features, enabling cell detection, classification, and differentiation, are extracted via a modified ResNet‐18 deep convolutional neural network architecture. The model is first validated by classifying metastatic breast carcinoma cells (MCF‐7) and normal human mammary epithelial cells (MCF‐10A). An increase in classification accuracy by 1% is achieved when processing five interferometric projections versus processing a single interferometric projection. This model is further tested on four types of white blood cells and exhibits an accuracy increase of 5% when processing 12 interferometric projections versus processing a single interferometric projection. This approach is shown to be superior to that of using conventional 2D‐rotation augmentation, and can be used to decrease substantially the number of cell examples needed for training the classification model without impairing the results. This novel concept has great potential to be incorporated into label‐free imaging flow cytometry and improve cell classification, and be used to detect various types of medical conditions and diseases.

Grading of glioma tumors using digital holographic microscopy

“…The combination of AI algorithms and DHM has shown significant potential in addressing various biomedical tasks such as red-blood cell segmentation [ 45 ], phenotypic cancer cell classification as epithelial or mesenchymal cell types [ 46 ], as well as the detection of pathogens [ 21 ]. Optical phase features extracted from the QPIs (such as phase volume, dry mass density, texture parameters, anisotropy) improved the cells’ classification accuracy [ 47 ] and cancerous tissue detection [ 38 ], without chemicals for staining and with quick turnaround time. Automatic classification showed good performance metrics even when small data sets were used [ 48 ].…”

Analyzing Blood Cells of High-Risk Myelodysplastic Syndrome Patients Using Interferometric Phase Microscopy and Fluorescent Flow Cytometry

“…IPM technologies have been used to distinguish different types of cells by our group and others, for example, to distinguish between normal and abnormal sperm cells [ 15 ], between different leucocytes [ 16 ] including T cells of different activation modes [ 17 ], and between normal and pathological hematopoietic cells such as acute myeloid leukemia (AML) and myeloproliferative neoplasm (MPN) [ 18 ]. IPM combined with flow cytometry was previously used for the classification of different types of leucocytes [ 17 , 18 ].…”