Automated detection of plasmodium falciparum from Giemsa-stained thin blood films

Preedanan, Wongsakorn; Phothisonothai, Montri; Senavongse, Wongwit; Tantisatirapong, Suchada

doi:10.1109/kst.2016.7440501

Cited by 15 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously, the authors proposed the framework of automated detection of malaria parasites in Giemsastained thin blood films [10]. Firstly, we used local adaptive thresholding to separate the erythrocyte from the background image.…”

Section: Related Studiesmentioning

confidence: 99%

Texture Based Classification of Malaria Parasites from Giemsa-Stained Thin Blood Films

Tantisatirapong¹,

Preedanan²

2020

ECTI-EEC

Self Cite

View full text Add to dashboard Cite

Quantification of parasitaemia is an important part of a microscopic malaria diagnosis. Giemsastained thin blood smear is the gold standard method for detecting malaria parasite enumeration. However, manual counting reveals the limitations of human inconsistency and fatigue, as well as the unreliability of accuracy and non-reproducibility. In this paper, the texture-based classification approach is investigated. The methods consist of the following processes: pre-processing, segmentation, feature extraction and the classification of erythrocytes. The preprocessing is applied for image conversion and enhancement. The segmentation combines local adaptive thresholding, morphological process and watershed transform to extract red blood cells, separate touching and overlapping cells. Texture analysis is performed to establish parameters obtained from first-order, second-order and higher-order statistical analysis and wavelet transform. Two feature selection approaches, the sequential forward selection method and sequential backward selection method, integrated with a support vector machine classifier are examined to obtain the optimal feature set for identifying the Plasmodium falciparum stages. We found that graylevel co-occurrence matrices based textural features were highly selected. The proposed method produces 98.87% accuracy for binary classification, 99.56% accuracy for ring stage classification, and 99.48% accuracy for tropozoite stage classification.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Texture Based Classification of Malaria Parasites from Giemsa-Stained Thin Blood Films

Tantisatirapong¹,

Preedanan²

2020

ECTI-EEC

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tek et al [14] [15], used image subtraction from a known image whereas Das et al [6] adapted the 'Gray World assumption' for illumination correction. To achieve noise elimination, Median filtering has been adapted by most authors like, Ruberto et al [16], Ross et al [17], Anggraini et al [18], Das et al [6], Sutkar et al [19], Chandra et al [20], Rosado et al [21], Predanan et al [22], Bahendwar et al [23] and Nugroho et al [24]. Authors Dave et al [25] and Savkare et al [26] have used a combination of Median filtering with Laplacian filter for noise removal along with enhancement of the edge region.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Diaz et al [31] used a template matching method by sliding a template over the clump region to separate the cells. Watershed transform method for clump splitting has been used by Preedanan et al [22] and Bairagi et al [32] (with Euclidian distance transform).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Histogram thresholding is performed by authors Chandra et al [20] while author Preedanan et al [22] have adopted adaptive histogram thresholding for segmentation. The authors, Savkare et al [34], [26], Mehrjou [35], in there research citations have implemented Watershed transform with distance transform for segmentation of red blood cells.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Authors Savkare et al [34], [26] implemented SVM (with colour, texture and shape features) for classification of parasite and normal red blood cells and Suryawanshi et al [39], used Euclidian Distance Classifier and SVM for classifying infected and non-infected cells. Similarly, Preedanan et al [22] used Statistical features from grayscale image and SVM with RBF kernel for classification, while Bairagi et al [32] employed Statistical and Texture based features with SVM classifier. Colour and Texture features with SVM classifier is used by Rosado et al [21].…”

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations