Jancarlo Ferreira Gomes

Automatic Segmentation and Classification of Human Intestinal Parasites From Microscopy Images

Human intestinal parasites constitute a problem in most tropical countries, causing death or physical and mental disorders. Their diagnosis usually relies on the visual analysis of microscopy images, with error rates that may range from moderate to high. The problem has been addressed via computational image analysis, but only for a few species and images free of fecal impurities. In routine, fecal impurities are a real challenge for automatic image analysis. We have circumvented this problem by a method that can segment and classify, from bright field microscopy images with fecal impurities, the 15 most common species of protozoan cysts, helminth eggs, and larvae in Brazil. Our approach exploits ellipse matching and image foresting transform for image segmentation, multiple object descriptors and their optimum combination by genetic programming for object representation, and the optimum-path forest classifier for object recognition. The results indicate that our method is a promising approach toward the fully automation of the enteroparasitosis diagnosis.

A new laboratorial method for the diagnosis of gastrointestinal parasites in dogs

In this study, we aimed to introduce a new technique called TF-Test Modified∕Dog for the diagnosis of gastrointestinal parasites in dogs. Fecal samples from 106 dogs were processed by the technique TF-Test Modified∕Dog and the techniques of centrifugation-flotation in zinc sulfate, simple-flotation by saturated solution of sodium chloride, direct microscopy exam and TF-Test Conventional. Sensitivity was higher in the TF-Test Modified∕Dog (98.41%), followed by flotation in saturated zinc sulfate (77.78%), TF-Test Conventional (73.02%), flotation by saturated sodium chloride (55.55%), and direct microscopy exam (30.16%). The diagnostic efficiency varied from 58.49% to 99.06%, with the highest value also obtained by the new proposed technique. Efficiency level of 99.06% with kappa index 0.979 (almost perfect) was obtained with the TF-Test Modified∕Dog. These results represent significant statistical gains (P < 0.05) of 20.63% in sensitivity and 12.27% in efficiency over the best among the other techniques - flotation by saturated zinc sulfate, whose kappa index was 0.738, much lower than that of the TF-Test Modified∕Dog. All techniques presented 100% specificity. In this sense, the high sensitivity of the TF-Test Modified∕Dog makes it suitable for epidemiological surveys of gastrointestinal parasitosis in dogs, zoonoses control and preventive surveillance programs.

An active learning paradigm based on a priori data reduction and organization

Abstract In the past few years, active learning has been reasonably successful and it has drawn a lot of attention. However, recent active learning methods have focused on strategies in which a large unlabeled dataset has to be reprocessed at each learning iteration. As the datasets grow, these strategies become inefficient or even a tremendous computational challenge. In order to address these issues, we propose an effective and efficient active learning paradigm which attains a significant reduction in the size of the learning set by applying an a priori process of identification and organization of a small relevant subset. Furthermore, the concomitant classification and selection processes enable the classification of a very small number of samples, while selecting the informative ones. Experimental results showed that the proposed paradigm allows to achieve high accuracy quickly with minimum user interaction, further improving its efficiency.

A data reduction and organization approach for efficient image annotation

The labor-intensive and time-consuming process of annotating data is a serious bottleneck in many pattern recognition applications when handling massive datasets. Active learning strategies have been sought to reduce the cost on human annotation, by means of automatically selecting the most informative unlabeled samples for annotation. The critical issue lies on the selection of such samples. As an effective solution, we propose an active learning approach that preprocesses the dataset, efficiently reduces and organizes a learning set of samples and selects the most representative ones for human annotation. Experiments performed on real datasets show that the proposed approach requires only a few iterations to achieve high accuracy, keeping user involvement to a minimum.

First description of Cryptosporidium hominis GP60 genotype IkA20G1 and Cryptosporidium parvum GP60 genotypes IIaA18G3R1 and IIaA15G2R1 in foals in Brazil

The present study focuses on Cryptosporidium infections of foals in Brazil. A total of 92 animals of different breeds from 11 farms in the vicinity of Araçatuba in the state of São Paulo, were examined. According to PCR targeting the 18S rRNA gene, Cryptosporidium sp. DNA was detected in 21.7% (20/92) of foals. Good quality 18S rRNA, actin, HSP70 and gp60 genes nPCR amplicons were obtained from five fecal samples. PCR amplification and sequencing of a fragment of the GP60 sporozoite surface glycoprotein gene revealed C. parvum genotypes IIaA18G3R1, IIaA15G2R1. Interestingly, we also detected in two foals a GP60 genotype related to the human parasite C. hominis.

Robust active learning for the diagnosis of parasites

We have developed an automated system for the diagnosis of intestinal parasites from optical microscopy images. The objects (species of parasites and impurities) segmented from these images form a large dataset. We are interested in the active learning problem of selecting a reasonably small number of objects to be labeled under an experts supervision for use in training a pattern classifier. However, impurities are very numerous, constitute several clusters in the feature space, and can be quite similar to some species of parasites, leading to a significant challenge for active learning methods. We propose a technique that pre-organizes the data and then properly balances the selection of samples from all classes and uncertain samples for training. Early data organization avoids reprocessing of the large dataset at each learning iteration, enabling the halting of sample selection after a desired number of samples per iteration, yielding interactive response time. We validate our method by comparing it with state-of-the-art approaches, using a previously labeled dataset of almost 6000 objects. Moreover, we report results from experiments on a very realistic scenario, consisting of a dataset with over 140,000 unlabeled objects, under unbalanced classes, the absence of some classes, and the presence of a very large set of impurities. HighlightsA robust active learning method, called RDS, based on a priori data organization.RDS properly balances sample diversity and uncertainty for useful sample selection.It provides high classification accuracy for the automated diagnosis of parasites.Comparisons with different clustering, classification and other literature methods.RDS was evaluated by an experienced expert in parasitology using a realistic scenario.

Automated diagnosis of human intestinal parasites using optical microscopy images

Intestinal parasitosis constitutes a serious health problem in most tropical countries. The diagnosis of enteroparasites in laboratory routine relies on the examination of stool samples using optical microscopy and the error rates usually range from moderate to high. Approaches based on automatic image analysis have been proposed, but the methods are usually specific for some species, some of them are computationally expensive, and image acquisition and focus are manual. We present a solution to automate the diagnosis of the 15 most common species of enteroparasites in Brazil, using a sensitive parasitological technique, a motorized microscope with digital camera for automatic image acquisition and focus, and fast image analysis methods. The results indicate that our solution is effective and suitable for laboratory routine, in which the exam must be concluded in a few minutes.

Coprotest® quantitativo: quantificação de ovos de helmintos em amostras fecais utilizando-se sistema de diagnóstico comercial

The formol ethyl acetate concentration technique was applied for the quantification of helminth eggs in fecal samples. The proposed quantitative method was standardized through the use of a commercial kit, Coprotest®, and fecal samples with different counts of Ascaris lumbricoides eggs. For the comparison of the quantitative Coprotest® with other methods of egg quantification, a series of fecal samples was prepared in laboratory, with decreasing number of A. lumbricoides, Trichuris trichiura and Schistosoma mansoni eggs. It is discussed the advantages of a method that is able of detecting different helminth and also protozoa species, allowing, in concomitance, to estimate in the populations the intensity of S. mansoni and geohelminth infections. The quantitative Coprotest® showed to be feasible, providing results that were comparable to the other quantitative methods already described in the literature.

First description of Cryptosporidium parvum in carrier pigeons (Columba livia)

The carrier pigeon and the domestic pigeon are different breeds of the species Columba livia. Carrier pigeons are used for recreational activities such as bird contests and exhibitions. Due to the close contact with humans, these birds may potentially represent a public health risk, since they can host and disseminate zoonotic parasites, such as those belonging to the genus Cryptosporidium (phylum Apicomplexa). The purpose of this work was the detection by microscopic and molecular techniques of Cryptosporidium spp. oocysts in fecal samples of carrier pigeons, and subsequently to sequence the 18S ribosomal RNA marker of positive samples to identify the species. A total of 100 fecal samples were collected individually in two pigeon breeding facilities from Formiga and Araçatuba, cities located in Minas Gerais state and São Paulo state, Brazil, respectively. The age of the birds ranged from one to 12 years; 56 were females and 44 males. Fecal smears were stained with negative malachite green, whereas the molecular characterization was based on the sequence of a ∼800bp fragment of the 18S rRNA gene. Microscopic examination of fecal smears revealed 4% (4/100) oocyst positivity. On the other hand, 7% (7/100) of positivity were found using nested PCR. Three samples were 99% to 100% similar to Cryptosporidium parvum 18S rDNA type A (Genbank AH006572) and the other three samples had 99% to 100% similarity to C. parvum 18S rDNA type B (Genbank AF308600). To our knowledge, this is the first report of C. parvum oocysts in carrier pigeons.

HIGH PREVALENCE OF Blastocystis spp. INFECTION IN CHILDREN AND STAFF MEMBERS ATTENDING PUBLIC URBAN SCHOOLS IN SÃO PAULO STATE, BRAZIL

After a gastroenteritis outbreak of unknown etiology in the municipality of Sebastião da Grama, SãoPaulo, Brazil, we conducted a parasitological survey to establish the epidemiological profile of enteroparasitosis in children and staff members attending the public urban schools in operation in town. The cross-sectional study evaluated 172 children aged 11 months to 6 years old and 33 staff members aged 19 to 58 years old. Overall, 96 (55.81%) children and 20 (60.61%) staff members were mono-parasitized, while 58 (33.72%) children and 4 (12.12%) workers were poly-parasitized. Protozoa (88.37%; 72.73%) was more prevalent than helminthes (3.48%; 0%) in children and staff members respectively.Blastocystis spp. was the most prevalent parasite in children (86.63%) and staff members (66.67%). The age of 1 year old or less was found to be associated with increased prevalence of giardiasis [OR = 13.04; 95%CI 2.89-58.91; p = 0.00] and public garbage collection was identified as a protective factor against intestinal helminth infections [OR = 0.06; 95%CI 0.00-0.79; p = 0.03]. Although most of the children tested positive for Blastocystis spp. and also presented clinical signs/symptoms (62.2%), this association was not statistically significant [OR = 1.35; 95%CI 0.53-3.44; p = 0.51]. Intestinal parasites still represent a public health concern and this study underscores the importance of further investigations to better understand the pathogenic role of Blastocystis spp.