A protozoan parasite extraction scheme for digital microscopic images

Lai, Cheng-Chou; Yu, Shyr-Shen; Tseng, Hsiao-Yun; Tsai, Meng‐Hsiun

doi:10.1016/j.compmedimag.2009.07.008

Cited by 20 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have reported the automated segmentation from the image background step as being very inconvenient, and had to rely on manual segmentation [5], on automatic segmentation using threshold operations [8, 9, 11, 18] or with successive steps combining different filters [15, 19]. In this study, the images of the parasites were captured with a high background, directly from fecal samples without any preprocessing.…”

Section: Discussionmentioning

confidence: 99%

Mathematical algorithm for the automatic recognition of intestinal parasites

et al. 2017

View full text Add to dashboard Cite

Parasitic infections are generally diagnosed by professionals trained to recognize the morphological characteristics of the eggs in microscopic images of fecal smears. However, this laboratory diagnosis requires medical specialists which are lacking in many of the areas where these infections are most prevalent. In response to this public health issue, we developed a software based on pattern recognition analysis from microscopi digital images of fecal smears, capable of automatically recognizing and diagnosing common human intestinal parasites. To this end, we selected 229, 124, 217, and 229 objects from microscopic images of fecal smears positive for Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica, respectively. Representative photographs were selected by a parasitologist. We then implemented our algorithm in the open source program SCILAB. The algorithm processes the image by first converting to gray-scale, then applies a fourteen step filtering process, and produces a skeletonized and tri-colored image. The features extracted fall into two general categories: geometric characteristics and brightness descriptions. Individual characteristics were quantified and evaluated with a logistic regression to model their ability to correctly identify each parasite separately. Subsequently, all algorithms were evaluated for false positive cross reactivity with the other parasites studied, excepting Taenia sp. which shares very few morphological characteristics with the others. The principal result showed that our algorithm reached sensitivities between 99.10%-100% and specificities between 98.13%- 98.38% to detect each parasite separately. We did not find any cross-positivity in the algorithms for the three parasites evaluated. In conclusion, the results demonstrated the capacity of our computer algorithm to automatically recognize and diagnose Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica with a high sensitivity and specificity.

show abstract

Section: Discussionmentioning

confidence: 99%

Mathematical algorithm for the automatic recognition of intestinal parasites

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Host antibodies detection can also discriminate different malarial infection, but the antibodies remain in the blood system after the infection has been cured; making it unreliable if used to test otherwise healthy people [15], [16]. Malaria gene detection can detect mixed infection between more than one malaria species, but needs elaborate sample preparation [10], [17], [18]. Microscopic image detection is fast and cheap method, but unable to detect drug resistance developed by the malaria and unable to capture and use malaria genomic information [7].…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Color Cascading Framework on Two Different Classifiers in Malaria Detection

Angkoso¹,

Hendrawan²,

Kusumaningsih³

et al. 2018

EECSI

View full text Add to dashboard Cite

Malaria, as a dangerous disease globally, can be reduced its number of victims by finding a method of infection detection that is fast and reliable. Computer-based detection methods make it easier to identify the presence of plasmodium in blood smear images. This kind of methods is suitable for use in locations far from the availability of health experts. This study explores the use of two methods of machine learning on Color Cascading Framework, i.e. Backpropagation Neural Network and Support Vector Machine. Both methods were used as classifier in detecting malaria infection. From the experimental results it was found that Color Cascading Framework improved the classifier performance for both in Support Vector Machine and Backpropagation Neural Network.

show abstract