Real-time plasmodium falciparum parasitemia using natural neighbor interpolation
Abstract:
This paper focuses on the development of an attachment to an Olympus CX21 microscope capable of automating the process of the parasitemia of P. Falciparum, one of the most common parasitic strains of malaria. The device uses a camera module attached to the eyepiece of the microscope to analyze the slide, and a set of stepper motors attached to the stage control to adjust the position of the mechanical stage. The flood-fill algorithm is used to analyze each field of view (FOV) of the slide to count the number of red blood cells and infected cells. Furthermore, while manual differential counting includes the analysis of hundreds of fields of views, the device uses the numerical method, natural neighbor interpolation (NNI), to reduce the number of slides to be examined, thereby making the process much more efficient. The results of the various tests yielded an accuracy rate of more than 90% for the automation of the process and a percent difference of no more than 20% for the application of NNI.
Año de publicación:
2019
Keywords:
- Near Neighbor Interpolation
- Raspberry PI
- P. Falciparum
- Manual Differential Count
- Flood-fill Algorithm
Fuente:

Tipo de documento:
Conference Object
Estado:
Acceso restringido
Áreas de conocimiento:
- Parasitología
- Aprendizaje automático
- Optimización matemática
Áreas temáticas:
- Microorganismos, hongos y algas
- Medicina y salud
- Enfermedades