A Novel Two-Stage Thresholding Method for Segmentation of Malaria Parasites in Microscopic Blood Images

Abstract

Developing computerized diagnostic tool for the detection of malaria infected cells in microscopic blood images can help to reduce malaria-induced mortality. Segmentation of malaria infected cells is a key step in the automated malaria diagnosis pipeline. In this paper, a novel two-stage thresholding method for segmentation of malaria parasites in microscopic blood images for diagnosis is presented. The RGB microscopic image is converted into YUV color space and luminance component is considered for single channel processing. The infected parasites are segmented by the proposed threshold method, which is carried out in two stages by maximizing between-class variance of an original image and consequently by an iterative threshold selection from a stage-one threshold image with suitable stopping criteria. The experimental results on benchmark dataset that comprise more than 300 images show that the proposed method successfully detects malaria parasites with no prior knowledge of the contents of the image without parameter tuning.

Malaria parasite segmentation using U-Net: Comparative study of loss functions

“…Dave et al [8] use adaptive thresholding methods and morphology operations such as erosion and dilation on thin blood smear images. Rosado et al [9] also applied adaptive segmentation and erosion, Somasekar et al [10] also applied thresholding and morphology operators such as dilation and closing to close segmentation holes. Devi et al [11] proposed a Plasmodium segmentation system using a controlled watershed marker with a minimum internal marker.…”