Deep Learning-Based Cell Detection and Extraction in Thin Blood Smears for Malaria Diagnosis

Abstract

Malaria is a major health threat caused by Plasmodium parasites that infect the red blood cells. Two predominant types of Plasmodium parasites are Plasmodium vivax ( P . vivax ) and Plasmodium falciparum ( P . falciparum ). Diagnosis of malaria typically involves visual microscopy examination of blood smears for malaria parasites. This is a tedious, error-prone visual inspection task requiring microscopy expertise which is often lacking in resource-poor settings. To address these problems, attempts have been made in recent years to automate malaria diagnosis using machine learning approaches. Several challenges need to be met for a machine learning approach to be successful in malaria diagnosis. Microscopy images acquired at different sites often vary in color, contrast, and consistency caused by different smear preparation and staining methods. Moreover, touching and overlapping cells complicate the red blood cell detection process, which can lead to inaccurate blood cell counts and thus incorrect parasitemia calculations. In this work, we propose a red blood cell detection and extraction framework to enable processing and analysis of single cells for follow-up processes like counting infected cells or identifying parasite species in thin blood smears. This framework consists of two modules: a cell detection module and a cell extraction module. The cell detection module trains a modified Channel-wise Feature Pyramid Network for Medicine (CFPNet-M) deep learning network that takes the green channel of the image and the color-deconvolution processed image as inputs, and learns a truncated distance transform image of cell annotations. CFPNet-M is chosen due to its low resource requirements, while the distance transform allows achieving more accurate cell counts for dense cells. Once the cells are detected by the network, the cell extraction module is used to extract single cells from the original image and count the number of cells. Our preliminary results based on 193 patients (including 148 P . Falciparum infected patients, and 45 uninfected patients) show that our framework achieves cell count accuracy of 92.2%.

Multiclass malaria parasite recognition based on transformer models and a generative adversarial network

“…In the classification of malaria cell images, the addition of Neighborhood Components Analysis (NCA) has been observed to enhance the performance of classifiers. Ufuktepe et al 18 presented a channel-wise feature pyramid network specifically designed for medical applications, which utilizes the green channel of input images to detect parasite cells and classify them as infected or non-infected. They expanded their approach by introducing an additional class for P. falciparum and training the network to categorize different types of infected parasites.…”

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

“…A number of AI models have been developed for the automated detection of Plasmodium parasites, the causative agent of malaria, which may be highly beneficial in affected regions. CNN using transfer learning has been proposed to automatically detect and quantify Plasmodium falciparum at different cellular stages of infection, where diagnostic accuracy is heavily dependent on the expertise of the microscopist [ 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 ]. In their study, Oliveria et al has applied multilayer perceptron and decision tree as a new approach for detecting malaria parasites in full images of thick blood smears using pixel classifiers.…”