Comparison of Texture Features Used for Classification of Life Stages of Malaria Parasite

Bairagi, Vinayak K.; Charpe, Kshipra C.

doi:10.1155/2016/7214156

Cited by 21 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To achieve this, a segmentation procedure in different color spaces based on manual image thresholding, was analyzed. Different components of the RGB and HSV color spaces were used, based on previous results obtained in the literature in the area of image-based malaria diagnosis [18], [19], [20], [16], [13], [14], [15], [21], [22], [23], [24].…”

Section: Image-based Criteria Of Quality: Background Segmentationmentioning

confidence: 99%

Image features for quality analysis of thick blood smears employed in malaria diagnosis

Suárez¹,

Luna²,

Cortés³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: The World Health Organization (WHO) provides protocols for the diagnosis of malaria. One of them is related to the staining process of blood samples to guarantee the correct parasite visualization. Ensuring the quality of the staining procedure on thick blood smears (TBS) is a dicult task, especially in rural centers, where there are factors that can a ect the smear quality (e.g. types of reagents employed, place of sample preparation, among others). This work presents an analysis of an image-based approach to evaluate the coloration quality of the staining process of TBS used for malaria diagnosis. Methods: According to the WHO, there are di erent coloration quality descriptors of smears. Among those, the background color is one of the best indicators of how well the staining process was conducted. An image database with 420 images (corresponding to 42 TBS samples) was created for analyzing and testing image-based algorithms to detect the quality of the coloration of TBS. Background segmentation techniques were explored (based on RGB and HSV color spaces) to separate the background and foreground (leukocytes, platelets, parasites) information. Then, di erent features (PCA, correlation, Histograms, variance) were explored as image criteria of coloration quality on the extracted background information; and evaluated according to their capability to classify images as with Good or Bad coloration quality from TBS. Results: For background segmentation, a thresholding-based approach in the SV components of the HSV color space was selected. It provided robustness separating the background information independently of its coloration quality. On the other hand, as image criteria of coloration quality, among the 19 feature vectors explored, the best one corresponds to the 15-bins histogram of the Hue component with classi cation rates of > 97%. Conclusions: An analysis of an image-based approach to describe the coloration quality of TBS was presented. It was demonstrated that if a robust background segmentation is conducted, the histogram of the H component from the HSV color space is the best feature vector to discriminate the coloration quality of the smears. These results are the baseline for automating the estimation of the coloration quality, which is a key component for automating malaria diagnosis of TBS, that has not been studied before.

show abstract

Section: Image-based Criteria Of Quality: Background Segmentationmentioning

confidence: 99%

Image features for quality analysis of thick blood smears employed in malaria diagnosis

Suárez¹,

Luna²,

Cortés³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Diaz et al [31] used a template matching method by sliding a template over the clump region to separate the cells. Watershed transform method for clump splitting has been used by Preedanan et al [22] and Bairagi et al [32] (with Euclidian distance transform).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Bairagi et al [32] have use Otsu thresholding on RGB and HSV colour channels. Histogram thresholding is performed by authors Chandra et al [20] while author Preedanan et al [22] have adopted adaptive histogram thresholding for segmentation.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Authors Savkare et al [34], [26] implemented SVM (with colour, texture and shape features) for classification of parasite and normal red blood cells and Suryawanshi et al [39], used Euclidian Distance Classifier and SVM for classifying infected and non-infected cells. Similarly, Preedanan et al [22] used Statistical features from grayscale image and SVM with RBF kernel for classification, while Bairagi et al [32] employed Statistical and Texture based features with SVM classifier. Colour and Texture features with SVM classifier is used by Rosado et al [21].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Malaria Parasitaemia Estimation � A new perspective (Preprint)

Bandyopadhyay¹,

Nag²,

Basu³

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Sıtma hastalığının sınıflandırılmasında ve tespitinde literatürde birçok yöntem kullanılmıştır. Bunlar; Destek Vektör Makine (DVM) [6], k-En Yakın Komşuluk algoritması (k-Ek) [7], Yapay Sinir Ağları (YSA) [8], AdaBoost algoritması [9], Otsu metodu [2], Çok Katmanlı Algılayıcı (ÇKA) [10], İstatistiksel olarak geliştirilmiş kural tabanlı sınıflandırma metodu [11], Radyal tabanlı fonksiyon sınıflandırıcı [12], İnce ayarlı Evrişimsel Sinir Ağları (ESA) modeli [13] ve literatürde birçok alanda kullanılan Derin öğrenme algoritmaları [5,14]. Aynı zamanda son yıllarda, literatürde popüler hale gelen derin öğrenme yöntemi, sıtma hastalığının sınıflandırılmasında olduğu gibi, birçok alanda kullanılmaktadır [15,16].…”

Section: Introductionunclassified

Sıtma Hastalığının Sınıflandırılmasında Evrişimsel Sinir Ağlarının Performanslarının Karşılaştırılması

Di̇ker

2020

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

ÖzSıtma, Plasmodium adlı bir kan parazitinin neden olduğu ciddi bir hastalıktır. Sıtmayı teşhis etmenin standart yolu, parazit bulaşmış kırmızı kan hücreleri için kan bulaşmalarını mikroskop altında uzmanlar tarafından görsel olarak incelenmesidir. Bu yöntem verimsizdir ve tanı, muayeneyi yapan kişinin deneyimine ve bilgisine bağlıdır. Daha önce teşhis için sıtma kan hücrelerine makine öğrenimine dayalı otomatik görüntü tanıma teknolojileri uygulanmıştır. Bu çalışmanın amacı, sıtma hücrelerinin parazit veya enfekte olmayan olarak ayırmaktır. Ek olarak çalışmada, önceden eğitilmiş evrişimsel sinir ağlarına dayalı bütünleşik bir tanı sistemi önerilmiştir. Bu çalışmada sıtma hücrelerini sınıflandırmak için Ulusal Sağlık Enstitüleri'nden (NIH) elde edilen toplam 27558 imge kullanılmıştır. Deneysel çalışmalar sonucunda, sıtma hücrelerinin sınıflandırılmasında, sırasıyla AlexNet, GoogleNet, SqueezeNet, ShuffleNet ESA modelleri ile % 95.77, % 96.31, % 95.95, % 96.44 ve 0.9880, 0.9887, 0.9888, 0.9923 EAA performans değerleri elde edilmiştir. Sıtma hücrelerinin sınıflandırılmasında en iyi sonuca, %96.44 Doğruluk değeri ile ShuffleNet CNN modeli kullanılarak ulaşılmıştır.

show abstract

Comparison of Texture Features Used for Classification of Life Stages of Malaria Parasite

Cited by 21 publications

References 9 publications

Image features for quality analysis of thick blood smears employed in malaria diagnosis

Image features for quality analysis of thick blood smears employed in malaria diagnosis

Malaria Parasitaemia Estimation � A new perspective (Preprint)

Sıtma Hastalığının Sınıflandırılmasında Evrişimsel Sinir Ağlarının Performanslarının Karşılaştırılması

Contact Info

Product

Resources

About