webinar register page

Webinar banner
PhD Public Defence for Candidate Rose NAKASI
PhD Public Defence for Candidate Rose NAKASI
Date: 21 December, 2021 10h:00 - 14h00 Kampala

Thesis title: Automated Diagnosis of Malaria in Thick Blood Smear Films: Deep Neural Network Approach

Dr. Aminah Zawedde
Dr. Ernest Mwebaze

Malaria, a mosquito-borne life-threatening disease, is one of the major health hazards in Sub-Saharan Africa. To improve disease control, accurate and timely diagnosis of malaria is required for prompt interventions. A key challenge faced in Uganda and in Sub-Sahara Africa is inadequate microscopy diagnosis for suspected patients. This is largely due to the lack of enough skilled technicians to operate microscopy labs. A study in Ghana found that there were more microscopes per lab technologist by a ratio of 1.72 to 0.85 per 100,000 population.
This thesis undertook the development of practical Deep Neural Network (DNNs) approaches for automation of microscopic diagnosis of malaria in thick blood smear slide images. DNNs are a class of machine learning that can automatically learn from input data without manual hand engineering of features. To this end, the work in this thesis contributed to an end-to-end solution in the field of microscopy image analysis by proposing a novel classification and object detection method based on DNNs for malaria diagnosis in thick blood smear images.
Firstly, we captured and assessed the quality of thick blood smear film datasets for our machine learning tasks. Secondly, an automated Convolutional-Neural-Network-based classification model for the differentiation of malaria positive patches (parts of an image with parasites) from the negative patches (parts of an image without parasites) was developed. The experiments achieved a ROC accuracy of 100% with malaria parasite detection using our approach in comparison to 94% ROC AUC with the conventional machine learning technique, randomized extra trees.

Dec 21, 2021 10:00 AM in Nairobi

Webinar logo
Webinar is over, you cannot register now. If you have any questions, please contact Webinar host: Liliane Maureen Ayebale.