Identification of plasmodium falciparum and plasmodium vivax on digital image of thin blood films gf

Hanung Adi Nugroho, Made Satria Wibawa, Noor Akhmad Setiawan, E. Elsa Herdiana Murhandarwati, Ratna Lestari Budiani Buana


Observing presence of Plasmodium parasite of stained thick or thin blood films through microscopic examination is a gold standard for malaria diagnosis.  Although the microscopic examination has been extensively used, misidentification might occur caused by human factors.  In order to overcome misidentification problem, several studies have been conducted to develop a computer-aided malaria diagnosis (CADx) to assist paramedics in decision-making.  This study proposes an approach to identify species and stage of Plasmodium falciparum and Plasmodium vivax on thin blood films collected from the Laboratory of Parasitology, Faculty of Medicine, Universitas Gadjah Mada.  Adaptive k-means clustering is applied to segment Plasmodium parasites.  A total of 39 features consisting of shape and texture features are extracted and then selected by using wrapper-based forward and backward directions.  Classification is evaluated in two schemes.  The first scheme is to classify the species of parasite into two classes. The second scheme is to classify the species and stage of parasite into six classes.  Three classifiers applied are k-nearest neighbour (KNN), support vector machine (SVM) and multi-layer perceptron (MLP).  Furthermore, to facilitate the multiclass classification, one-versus-one (OVO) and one-versus-all (OVA) methods are implemented.  The first scheme achieves the accuracy of 88.70% based on MLP classifier using three selected features.  While the accuracy gained by the second scheme is 95.16% based on OVO and MLP classifier using 29 selected features.  These results indicate that the proposed approach successfully identifies the species and stage of parasite on thin blood films and has potential to be implemented in the CADx system for assisting paramedics in diagnosing malaria.


Plasmodium falciparum, Plasmodium vivax, Adaptive k-means clustering, Wrapper feature selection

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics