Automated Diagnosis of Lymphatic Filariasis: A Robust Approach for Microfilariae Detection using Image Processing and Stacking Classifier
Priyanka Kumar, Kanojia Sindhuben Babulal · 2023
Lymphatic Filariasis (LF) is a debilitating disease that results from bites by disease-carrying vectors. It leads to severe physical deformities and disabilities in affected individuals. Presently, the detection of LF relies on the visual identification of microfilariae parasites in peripheral blood samples, a procedure performed by trained hematologists. Nevertheless, this manual investigation approach poses the potential for inconsistent results. The primary goal of this research paper is to introduce an automated diagnostic approach designed to detect the presence of microfilariae in blood smear samples, with a particular emphasis on identifying cases of Lymphatic Filariasis. The methodology consists of introducing some pre-processing techniques like Color space conversion and the use of a Median filter. Further, the images are segmented to mark the region of interest on microfilariae dropping its background noises. A diverse range of textural features is extracted, serving as input to the stacking classifier, resulting in an impressive accuracy rate of 95%. The achieved accuracy rate provides strong confidence in the viability and applicability of the proposed methodology for real-world diagnostics.