Celso Tetsuo Nagase Suzuki

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 discrete approach for supervised pattern recognition

We present an approach for supervised pattern recognition based on combinatorial analysis of optimum paths from key samples (prototypes), which creates a discrete optimal partition of the feature space such that any unknown sample can be classified according to this partition. A training set is interpreted as a complete graph with at least one prototype in each class. They compete among themselves and each prototype defines an optimum-path tree, whose nodes are the samples more strongly connected to it than to any other. The result is an optimumpath forest in the training set. A test sample is assigned to the class of the prototype which offers it the optimum path in the forest. The classifier is designed to achieve zero classification errors in the training set, without over-fitting, and to learn from its errors. A comparison with several datasets shows the advantages of the method in accuracy and efficiency with respect to support vector machines.

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.

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.

TF-Test Modified: New Diagnostic Tool for Human Enteroparasitosis.

Intestinal parasitosis is highly prevalent worldwide, being among the main causes of illness and death in humans. Currently, laboratory diagnosis of the intestinal parasites is accomplished through manual technical procedures, mostly developed decades ago, which justifies the development of more sensitive and practical techniques. Therefore, the main objective of this study was to develop, evaluate, and validate a new parasitological technique referred to as TF‐Test Modified, in comparison to three conventional parasitological techniques: TF‐Test Conventional; Rugai, Mattos & Brisola; and Helm Test/Kato‐Katz. For this realization, we collected stool samples from 457 volunteers located in endemic areas of Campinas, São Paulo, Brazil, and statistically compared the techniques. Intestinal protozoa and helminths were detected qualitatively in 42.23% (193/457) of the volunteers by TF‐Test Modified technique, against 36.76% (168/457) by TF‐Test Conventional, 5.03% (23/457) by Helm Test/Kato‐Katz, and 4.16% (19/457) by Rugai, Mattos & Brisola. Furthermore, the new technique presented “almost perfect kappa” agreement in all evaluated parameters with 95% (P < 0.05) of estimation. The current study showed that the TF‐Test Modified technique can be comprehensively used in the diagnosis of intestinal protozoa and helminths, and its greater diagnostic sensitivity should help improving the quality of laboratory diagnosis, population surveys, and control of intestinal parasites.

Comparative study of five techniques for the diagnosis of canine gastrointestinal parasites.

Differences in the efficacy of diagnostic techniques employed in the parasitological examination of feces are a limiting factor of this laboratory procedure in the field of Veterinary Parasitology. To verify advances in this type of examination in dogs, we conducted a study using a new technique (TFGII/Dog). Fifty naturally infected dogs were housed in individual stalls, and their feces were evaluated comparatively using this technique and four other conventional techniques. The TFGII/Dog showed high levels of sensitivity and efficiency, surpassing the diagnostic accuracy of the other techniques with a kappa concordance index of 0.739 (Substantial), as opposed to 0.546 (Moderate), 0.485 (Moderate), 0.467 (Moderate), and 0.325 (Fair) of the Spontaneous-Sedimentation, Centrifugal-Flotation in Saturated Zinc Sulfate Solution, Centrifugal-Flotation in Saturated Sugar Solution, and Spontaneous-Flotation in Saturated Sodium Chloride Solution techniques, respectively. The combination of positive results of all techniques comprises eight genera of parasites, with Ancylostoma spp. predominating among helminths, and Cystoisospora spp. among protozoa. The TFGII/Dog technique showed better diagnostic performance, and can therefore be considered an important tool for optimizing the results of laboratory routines and for the control of canine gastrointestinal parasites.

Tf-test Modified: New Diagnostic Tool For Human Enteroparasitosis.

Intestinal parasitosis is highly prevalent worldwide, being among the main causes of illness and death in humans. Currently, laboratory diagnosis of the intestinal parasites is accomplished through manual technical procedures, mostly developed decades ago, which justifies the development of more sensitive and practical techniques. Therefore, the main objective of this study was to develop, evaluate, and validate a new parasitological technique referred to as TF‐Test Modified, in comparison to three conventional parasitological techniques: TF‐Test Conventional; Rugai, Mattos & Brisola; and Helm Test/Kato‐Katz. For this realization, we collected stool samples from 457 volunteers located in endemic areas of Campinas, São Paulo, Brazil, and statistically compared the techniques. Intestinal protozoa and helminths were detected qualitatively in 42.23% (193/457) of the volunteers by TF‐Test Modified technique, against 36.76% (168/457) by TF‐Test Conventional, 5.03% (23/457) by Helm Test/Kato‐Katz, and 4.16% (19/457) by Rugai, Mattos & Brisola. Furthermore, the new technique presented “almost perfect kappa” agreement in all evaluated parameters with 95% (P < 0.05) of estimation. The current study showed that the TF‐Test Modified technique can be comprehensively used in the diagnosis of intestinal protozoa and helminths, and its greater diagnostic sensitivity should help improving the quality of laboratory diagnosis, population surveys, and control of intestinal parasites.

Validation of a new technique to detect Cryptosporidium spp. oocysts in bovine feces

Due to its important zoonotic potential, cryptosporidiosis arouses strong interest in the scientific community, because, it was initially considered a rare and opportunistic disease. The parasitological diagnosis of the causative agent of this disease, the protozoan Cryptosporidium spp., requires the use of specific techniques of concentration and permanent staining, which are laborious and costly, and are difficult to use in routine laboratory tests. In view of the above, we conducted the feasibility, development, evaluation and intralaboratory validation of a new parasitological technique for analysis in optical microscopy of Cryptosporidium spp. oocysts, called TF-Test Coccidia, using fecal samples from calves from the city of Araçatuba, São Paulo. To confirm the aforementioned parasite and prove the diagnostic efficiency of the new technique, we used two established methodologies in the scientific literature: parasite concentration by centrifugal sedimentation and negative staining with malachite green (CSN-Malachite) and Nested-PCR. We observed good effectiveness of the TF-Test Coccidia technique, being statistically equivalent to CSN-Malachite. Thus, we verified the effectiveness of the TF-Test Coccidia parasitological technique for the detection of Cryptosporidium spp. oocysts and observed good concentration and morphology of the parasite, with a low amount of debris in the fecal smear.