Use this URL to cite or link to this record in EThOS:
Title: Automated low-cost malaria detection system in thin blood slide images using mobile phones
Author: Kareem Reni, Sauyma
ISNI:       0000 0004 5354 0246
Awarding Body: University of Westminster
Current Institution: University of Westminster
Date of Award: 2014
Availability of Full Text:
Access from EThOS:
Access from Institution:
Malaria, a deadly disease which according to the World Health Organisation (WHO) is responsible for the fatal illness in 200 million people around the world in 2010, is diagnosed using peripheral blood examination. The work undertaken in this research programme aims to develop an automated malaria parasite-detection system, using microscopic-image processing, that can be incorporated onto mobile phones. In this research study, the main objective is to achieve the performance equal to or better than the manual microscopy, which is the gold standard in malaria diagnosis, in order to produce a reliable automated diagnostic platform without expert intervention, for the effective treatment and eradication of the deadly disease. The work contributed to the field of mathematical morphology by proposing a novel method called the Annular Ring Ratio transform for blood component identification. It has also proposed an automated White Blood Cell and Red Blood Cell differentiation algorithm, which when combined with ARR transform method, has wide applications not only for malaria diagnosis but also for many blood related analysis involving microscopic examination. The research has undertaken investigations on infected cell identification which aids in the calculation of parasitemia, the measure of infection. In addition, an automated diagnostic tool to detect the sexual stage (gametocytes) of the species P.falciparum for post-treatment malaria diagnosis was developed. Furthermore, a parallel investigation was carried out on automated malaria diagnosis on fluorescent thin blood films and a WBC and infected cell differentiation algorithm was proposed. Finally, a mobile phone application based on the morphological image processing algorithms proposed in this thesis was developed. A complete malaria diagnostic unit using the mobile phones attached to a portable microscope was set up which has enormous potential not only for malaria diagnosis but also for the blood parasitological field where advancement in medical diagnostics using cellular smart phone technology is widely acknowledged.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available