Red blood cell phenotyping from 3D confocal images using artificial neural networks

The investigation of cell shapes mostly relies on the manual classification of 2D images, causing a subjective and time consuming evaluation based on a portion of the cell surface. We present a dual-stage neural network architecture for analyzing fine shape details from confocal microscopy recordings in 3D. The system, tested on red blood cells, uses training data from both healthy donors and patients with a congenital blood disease, namely hereditary spherocytosis. Characteristic shape features are revealed from the spherical harmonics spectrum of each cell and are automatically processed to create a reproducible and unbiased shape recognition and classification. The results show the relation between the particular genetic mutation causing the disease and the shape profile. With the obtained 3D phenotypes, we suggest our method for diagnostics and theragnostics of blood diseases. Besides the application employed in this study, our algorithms can be easily adapted for the 3D shape phenotyping of other cell types and extend their use to other applications, such as industrial automated 3D quality control.Author summary: Microscopy offers the advantage of a direct visualization of the object under study. The observation of cell shapes can provide important information, such as the presence of a pathology. An application example relates to hematology, where the examination of blood smears gives first information on the diagnosis of a blood disease. At the same time, image analysis has been developing towards automation in order to provide objective, high-throughput and systematic results. Automated image recognition more and more tends towards sophisticated artificial-intelligence based methods. We here present a deep learning-based approach to classify the 3D shape of cells with accurate recognition of their fine surface details. Our system first performs a rough, discrete classification of cell shape, and second, a detailed morphological characterization by means of linear regression. Especially the latter task is impossible to be performed manually. We demonstrate the efficiency and the advantages of automated 3D shape evaluation over the traditional methods making use of 2D blood smear micrographs.