Red blood cell segmentation and classification from microscopic images using machine learning

Abstract

Red blood cell morphology analysis plays an essential role in diagnosing many diseases caused by RBC disorders. This manual inspection is a long process and requires practice and experience. Since recent computer vision and image processing in the medical imaging area can provide efficient tools, it can help hematologists to automatically analyze images from a microscope in a reduced time and cost. This research presents a new method to segment and classify RBCs from blood smear images. The process started from data collection, which a new application was created for precisely labeling. The normalization was done to reduce the color space and allowed the trained model to not be biased on color. Then, overlapping cells were separated using a new method to find concave points and use direct ellipse fitting to estimate the shape of a single RBC. Lastly, classification using EfficientNet-B1 on 12 red blood cell classes was done. However, to classify multiple classes with deep learning, imbalance problems are common in medical imaging because number of normal samples is always higher than number of rare disease samples. The imbalanced handling techniques were analyzed to deal with this problem. Experimental results showed that the weight balancing technique with augmentation had the potential to deal with imbalance problems.