A new approach for malaria diagnosis in thick blood smear images. (September 2022)

• Record Type: Journal Article
• Authors: de Souza Oliveira, Anne; Guimarães Fernandes Costa, Marly; das Graças Vale Barbosa, Maria; Ferreira Fernandes Costa Filho, Cicero
• Is Part Of: Biomedical signal processing and control. Volume 78(2022)
• Publication Date: 2022-09
• Subjects: Malaria -- Convolutional neural networks -- Thick blood smear image; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103931
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: Segment foreground objects using pixel classifiers, as MLP, decision trees of logistic regression, and HSV components. Delimit a parasite patch (objects that made up a parasite) using pixel classifiers, as MLP, decision trees of logistic regression, and HSV components. Separate malaria parasite from other foreground objects, form WBCs, platelets and artifacts, using a convolution neural network (CNN) trained from scratch. Evaluate the malaria parasite detection performance with image sets containing different parasite sizes. Block diagram of the new approach proposed for detecting malaria parasites in thick blood film slides. Abstract: This paper presents a new approach for detecting malaria parasites in full images of thick blood smear using pixel classifiers for obtaining foreground objects and delimiting parasite-stained objects. For both processes, the HSV components were used as input variables of the following pixel classifiers: multilayer perceptron and a decision tree. The obtained patches were classified using a deep neural network with 34 layers, trained from scratch. The image dataset used was divided into sets with different parasite sizes. This enables characterizing performance metrics (accuracy, sensitivity, specificity, precision, and F1-score) for parasite detection with varying parasite sizes. The best metric values were obtained in images with large parasite sizes. For image sets 1 and 2, with large parasite sizes, precision rates of 91.71% and 93.14% were obtained. For image sets 3 and 4, with small parasite sizes, precision rates of 76.58% and 71.58% were obtained. As shown by the literature review, these results are comparable to others previously published. Nevertheless, a rigorous comparison could not be done, as different works use different datasets.