A combination of optimized threshold and deep learning-based approach to improve malaria detection and segmentation on PlasmoID dataset

Abstract

Malaria is a life-threatening parasitic disease transmitted to humans by infected female Anopheles mosquitoes. Early and accurate diagnosis is crucial to reduce the high mortality rate of the disease, especially in eastern Indonesia, where limited health facilities and resources contribute to the effortless spread of the disease. In rural areas, the lack of trained parasitologists presents a significant challenge. To address this issue, a computer-aided detection (CAD) system for malaria is needed to support parasitologists in evaluating hundreds of blood smear slides every month. This study proposes a hybrid automated malaria parasite detection and segmentation method using image processing and deep learning techniques. First, an optimized double-Otsu method is proposed to generate malaria parasite patch candidates. Then, deep learning approaches are applied to recognize and segment the parasites. The proposed method is evaluated on the PlasmoID dataset, which consists of 468 malaria-infected microscopic images containing 691 malaria parasites from Indonesia. The results demonstrate that our proposed approach achieved an F1-score of 0.91 in parasite detection. Additionally, it achieved better performance in terms of sensitivity, specificity, and F1-score for parasite segmentation compared to original semantic segmentation methods. These findings highlight the potential of this study to be implemented in CAD malaria detection, which could significantly improve malaria diagnosis in resource-limited areas.