Comparative Analysis of different types of Malaria Diseases using First Order Features

Abstract

Malaria is majorly caused by three parasitic organisms namely, P. malaria, P. vivax, P. falciparum. Physician (Microbiologists, Laboratory technicians, Medical Practitioners, and medical experts) examines erythrocytes under light microscope to study the color and morphological changes toward malaria diagnosis. Assessment accuracy depends on the physician-pathological understanding. To help physicians in cases where they may be wrong, developing a computer assisted malaria parasite detection tool has helped modern pathological services where a physician is able to get assistance in order to quickly make better decision toward malaria diagnosis. Segmentation of medical images helps in identifying features that are needed for clinical diagnosis. First order features always give accurate information about the medical image and useful for identification and analysis. In this work, first order features which entails the mean, median, mode, standard deviation, energy, Skewness, kurtosis, area, entropy were extracted from the infected malaria images. The corresponding results show a significant steady value which could be useful during classification of medical images. The work is ongoing, the aim of the work is to classify the malaria parasite and to come up with a diagnostic system that will be able to diagnose tissue and blood cell based diseases like malaria, Ebola etc.

Malaria Parasite Identification from Red Blood Cell Images Using Transfer Learning Models

“…The last phase often entails the identification and segmentation (outlining) of specific blood cells as well as any other items that may be seen, such as parasites or platelets in a blood slide picture. All segmentation techniques that have been utilized to diagnose microscopic malaria are summarized in the section, such as Binocolor microscopy, Polarized microscopy, Fluorescent microscopy, Serial block-face scanning electron microscopy (SBFSEM), Image-based cytometer, SightDx digital imaging scanning, Fiber array-based Raman imaging, Multi-spectral and multi-modal microscopy, Scanning electron microscopy (SEM), Quantitative cartridge-scanner system, Quantitative phase imaging (QPI) and Sub-pixel resolving optofluidic microscopy (SROFM) [12][13][14][15][16][17].…”

The Role of Quality Assessment for Development of Sustainable Bus Service in Mid-sized Cities of India: A Case Study of Patna

“…Image Processing techniques were introduced to remove pertaining noise, correct illumination, normalize edge segmentation, and eradicate artifacts from cell images to render them useful for automated examination. Mean [7], Median [8], Geometric Mean [9], and Wiener filtering [10] are notable image denoising methods that operate in the pixel's neighbourhood for image impulse noise removal and edge preservation. Savkare et al [11] introduced a novel method to enhance malarial image resolution through Laplacian filtering and Adaptive Histogram Equalization.…”