The project dealt with development of a novel algorithm is for computer aided diagnosis (CAD) of Malaria which is able to diagnose Malaria parasites from the microscopic images of thin blood smear as well as thick blood smear. Additionally, the algorithm is also able to classify the stained particles like white blood cells and other 3 forms of parasite in order to estimate parasitemia. The discrepancy in the automated parasite count by the proposed algorithm is 7.14%, which is suitable for computer aided diagnosis (CAD) of malaria according to world health organization (WHO) quality control standards. Studied and implemented various computer vision techniques like image denoising, focus plane stacking, image segmentation, feature extraction techniques and machine learning algorithms in order to detect and classify malaria parasites from microscopic images.
The blue components you can see in the image is called "Red Blood Cells". And RBCs, which are infected by Malarial Parasites are detected and shown in red highlighted color.
Red Blood Cells" are completely liased in Thick blood smear and Malarial parasite detection is not easy. The detected Malarial parasites are highlighted using white rings in the results.
Results shown here is complete analysis of Microscopic image of Thick Blood smear.
The complete analysis performs following tasks:
(Full-text available)
(
Full-text available
)