Malaria is a leading cause of death and disease in many developing countries. In 2015, there were an estimated 214 million cases of malaria, which caused approximately 438 000 deaths. Around 90% of malaria cases occurred in Africa, where the lack of access to malaria diagnosis is largely due to a shortage of expertise. Thus, the importance to develop new tools that facilitate the rapid and easy diagnosis of malaria for areas with limited access to healthcare services cannot be overstated.
Image processing for malaria diagnosis can bring several advantages, like potentially reduce the dependence of manual microscopic examination, which is an exhaustive and time consuming activity, simultaneously requiring a considerable expertise of the laboratory technician.
The goal of this master thesis is to perform a statistical comparison of different machine learning approaches for malaria parasites detection in microscopic images, and find the approach that ensures the best performance. Beyond the conventionally used classifiers, new classification approaches should also be explored like Deep Learning Algorithms and Fuzzy Logics. Moreover, multi-classifier approaches should also be explored, i.e. combining different classifiers in order to find the machine learning approach with the best performance for malaria parasites detection in microscopic images.
For any additional information regarding this project, please contact us using the inquiries form.