A deep convolutional neural network for classification of red blood cells in sickle cell anemia

Abstract

Sickle cell disease (SCD) is a hematological disorder leading to blood vessel occlusion accompanied by painful episodes and even death. Red blood cells (RBCs) of SCD patients have diverse shapes that reveal important biomechanical and bio-rheological characteristics, e.g. their density, fragility, adhesive properties, etc. Hence, having an objective and effective way of RBC shape quantification and classification will lead to better insights and eventual better prognosis of the disease. To this end, we have developed an automated, high-throughput, ex-vivo RBC shape classification framework that consists of three stages. First, we present an automatic hierarchical RBC extraction method to detect the RBC region (ROI) from the background, and then separate touching RBCs in the ROI images by applying an improved random walk method based on automatic seed generation. Second, we apply a mask-based RBC patch-size normalization method to normalize the variant size of segmented single RBC patches into uniform size. Third, we employ deep convolutional neural networks (CNNs) to realize RBC classification; the alternating convolution and pooling operations can deal with non-linear and complex patterns. Furthermore, we investigate the specific shape factor quantification for the classified RBC image data in order to develop a general multiscale shape analysis. We perform several experiments on raw microscopy image datasets from 8 SCD patients (over 7,000 single RBC images) through a 5-fold cross validation method both for oxygenated and deoxygenated RBCs. We demonstrate that the proposed framework can successfully classify sickle shape RBCs in an automated manner with high accuracy, and we also provide the corresponding shape factor analysis, which can be used synergistically with the CNN analysis for more robust predictions. Moreover, the trained deep CNN exhibits good performance even for a deoxygenated dataset and distinguishes the subtle differences in texture alteration inside the oxygenated and deoxygenated RBCs. There are many hematological disorders in the human circulation involving significant alteration of the shape and size of red blood cells (RBCs), e.g. sickle cell disease (SCD), spherocytosis, diabetes, HIV, etc. These morphological alterations reflect subtle multiscale processes taking place at the protein level and affecting the cell shape, its size, and rigidity. In SCD, in particular, there are multiple shape types in addition to the sickle shape, directly related to the sickle hemoglobin polymerization inside the RBC, which is induced by hypoxic conditions, e.g., in the post-capillary regions, in the spleen, etc. Moreover, the induced stiffness of RBCs depends on the de-oxygenation level encountered in hypoxic environments. Here, we develop a new computational framework based on deep convolutional networks in order to classify efficiently the heterogeneous shapes encountered in the sickle blood, and we complement our method with an independent shape factor analysis. This dual approach provides robust predictions and can be potentially used to assess the severity of SCD. The method is general and can be adapted to other hematological disorders as well as to screen diseased cells from healthy ones for different diseases.