Malaria detection in blood Sample image using Python
Abstract : Malaria is one of the deadliest diseases ever exists in this planet. Automated evaluation process can notably decrease the time needed for diagnosis of the disease. This will result in early onset of treatment saving many lives. As it poses a serious global health problem, we approached to develop a model to detect malaria parasite accurately from giemsa blood sample with the hope of reducing death rate because of malaria. In this work, we developed a model by using color based pixel discrimination technique and Segmentation operation to identify malaria parasites from thin smear blood images. Various segmentation techniques like watershed segmentation, HSV segmentation have been used in this method to decrease the false result in the area of malaria detection. We believe that, our malaria parasite detection method will be helpful wherever it is difficult to find the expert In microscopic analysis of blood report and also limits the human error while detecting the presence of parasites in the blood sample.
Malaria is a curable disease if the patients have access to early diagnosis and prompt treatment. Antigen-based rapid diagnostic tests (RDTs) have an important role at the periphery of health services capability because none of the rural clinics has the ability to diagnose malaria on-site due to a lack of microscopes and trained technicians to evaluate blood films. Furthermore, in regions where the disease is not endemic laboratory technologists have very limited experience in detecting and identifying malaria parasites. An ever increasing numbers of travelers from temperate areas each year visit tropical countries and many of them return with a malaria infection.
The disadvantages of thick blood smears are that the parasites are not viewed in situ within the erythrocyte, are bunched up and less morphologically recognizable, may be hidden behind or above leukocytes, and may be more easily confused withtheartifact. If a smaller volume (approximately 2 mL) of blood is spread into a monolayer in the preparation of a traditional blood smear and briefly immersed in methanol, the erythrocytes are fixed and will not subsequently lyse during staining.
In the proposed methodology, image processing techniques are used for detection of malaria from microscopic images of Giemsa stained thin blood smear. Here, blood smear images are analyzed based on two methods. First, by extracting SIFT features from preprocessed images and lead to the classifier for recognition. A comparative analysis of SVM (Support Vector Machine) and ANN (Artificial Neural Network) is carried out for recognition of extracted SIFT features. Second method comprises of leading the image directly without any preprocessing to CNN based network.
? Edge detection optimizes RBC count detection.
? Labeling algorithm has been introduced which reduces the error rate of detection in state of art method.
? Bio medical application in Detection of Malaria.
|