Computational approach for diagnosis of malaria through classification of malaria parasite from microscopic image of blood smear

Abstract

Malaria is disease which is affecting millions of people and it is generally detected by examining the Red Blood Corpuscles (RBC) manually using microscope. However, the manual microscopic approach is time consuming, and lack of experts in the rural area, makes diagnosis of malaria very challenging one. The reported image processing approch extent the modern digital facilities to address the demand of automation, by developing a computerised facility for the detection of malaria using image processing technique. And this technological development could be a significant part of a modern digital telepathology. Proposed technology helps diagnose through the digital slide. Here the screening of microscopic images of a blood sample is achieved with color image processing approach that involves Red blood corpuscles (RBC) Segmentation, color space conversion, segmentation of the parasite, feature extraction and classification of malarial sample. The presented work detects plasmodium parasites from leishman stained microscopic blood images which in turn support pathologists for faster diagnosis. Neural network and rule based classifiers were used for the classification of blood images. The images belonging to malarial and non-malarial classes.

Extrinsic parameter's adjustment and potential implications in Plasmodium falciparum malaria diagnosis

“…Niranjana et al's classification process involves extracting statistical, textural, and geometric features from the segmented greyscale images. The geometrical features used are mean, variance, and standard deviation (Sampathila, Shet, & Basu, 2018). A grey‐level co‐occurrence matrix was created to extract the texture features.…”

“…The obtained accuracy for hybrid classifier, Naive Bayes, SVM, k‐NN, and ANN are 96.54, 84.92, 89.84, 93.15, and 94.15%, respectively (Devi et al, 2018). Sampathila et al (2018) acquired thin blood smear stained by Leishman and digitized. The digitized image is preprocessed using gray world normalization and an adaptive median filter to remove unwanted illumination artifacts, respectively.…”

“…Later on, more textural, size and geometrical features are extracted. The rule‐based classifier ANN is used for classification and results in an accuracy of 96.7% (Sampathila et al, 2018).…”

“…Conclusive remarks and future scope are given in Section 5. (Sampathila, Shet, & Basu, 2018). A grey-level co-occurrence matrix was created to extract the texture features.…”

Detection and stage classification of Plasmodium falciparum from images of Giemsa stained thin blood films using random forest classifiers

“…Previous studies applied methods based on histogram thresholding (color similarity, Otsu, local and adaptive thresholding etc. ), and morphological operations as given in Table 2 and [4][5][6][7][8][9][10][11][12]. Most studies used only the green color channel for detection of parasites.…”