Malaria parasite detection from human blood smear images using deep learning techniques
Malaria is a deadly disease caused by a parasite that is transmitted to humans through the bite of an infected mosquito. The standard method of diagnosing malaria involves a graphic examination of human blood smears under a microscope by medical experts to determine parasite-infected red blood ce...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/6047/1/fyp_CS_2023_TYJ.pdf http://eprints.utar.edu.my/6047/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Malaria is a deadly disease caused by a parasite that is transmitted to humans through
the bite of an infected mosquito. The standard method of diagnosing malaria involves
a graphic examination of human blood smears under a microscope by medical experts
to determine parasite-infected red blood cells. However, this method is ineffective,
and the diagnosis is dependent on the knowledge and experience of the examiner
which is still lack in some places especially in rural area. Faultless identification of
medical imaging has become a crucial factor in medical diagnosis and decisionmaking
with the significant development in deep learning research. Even though
malaria can be fatal, most cases of illness and fatalities are frequently preventable if
there is an accurate detection. Therefore, automated parasite detection technologies
are highly needed to decrease the rate of false detection.
The aim of this study is to investigate various deep learning methods that can be
employed to identify the presence of the malaria parasite in human blood cells.
Additionally, the objective is to develop a convolutional neural network (CNN) based
on deep learning techniques to detect malaria in medical cell images through image
classification. This paper covers various aspects of malaria detection, including image
pre-processing, feature extraction, and classification.
Finally, the study discusses the potential for future research in deep learning-based
malaria detection, including the use of transfer learning, ensemble models, and other
deep learning techniques. Overall, the study highlights the promising results of deep
learning-based malaria detection and its potential to revolutionize malaria diagnosis. |
|---|