Chagas Parasite Detection in Blood Images Using AdaBoost

Abstract

The Chagas disease is a potentially life-threatening illness caused by the protozoan parasite, Trypanosoma cruzi. Visual detection of such parasite through microscopic inspection is a tedious and time-consuming task. In this paper, we provide an AdaBoost learning solution to the task of Chagas parasite detection in blood images. We give details of the algorithm and our experimental setup. With this method, we get 100% and 93.25% of sensitivity and specificity, respectively. A ROC comparison with the method most commonly used for the detection of malaria parasites based on support vector machines (SVM) is also provided. Our experimental work shows mainly two things: (1) Chagas parasites can be detected automatically using machine learning methods with high accuracy and (2) AdaBoost + SVM provides better overall detection performance than AdaBoost or SVMs alone. Such results are the best ones known so far for the problem of automatic detection of Chagas parasites through the use of machine learning, computer vision, and image processing methods.

Deep Convolutional Neural Network applied to Chagas Disease Parasitemia Assessment

“…Accuracy values were 96.4% on the validation set and 72.0% on an independent test set. Although precision and sensitivity are below those reported in [3] (the image analysis methods based on the joint application of boosting and support-vector machines have been previously reported to yield accuracy values around 99%), up to our knowledge, the present paper is the first one to report an application of deep neural networks to Chagas disease diagnosis. As we seek to improve the performance of the currently proposed classifier, in future work, we will look into complexity comparisons with the boosting approach.…”

“…Parasite size varies from 20 µm length and 1 µm width, for thin shapes, to 15 µm length and 4 µm width, for thick shapes [2]. Diagnosis during the acute phase is important, because it makes cure possible as long as treatment is started [3]. At the chronic phase, the diagnosis is based on serology, blood culture, xenodiagnosis and complementary exams such as chest x-ray or electrocardiogram [4], and treatment during the chronic phase generally does not lead to cure.…”

“…Previous works about the application of machine learning to T. cruzi detection are [3], [5] (Gaussian discriminant), and [6] (classifier based on k-nearest neighbors). In [3], the authors apply Adaboost and support vector machines, and report 100% sensitivity and 93.3% specificity (i.e. precision).…”

Unsupervised Scoliosis Diagnosis via a Joint Recognition Method with Multifeature Descriptors and Centroids Extraction

“…We make the first attempt to use the cascade gentle AdaBoost detector with multifeature fusion to detect vertebrae. The classifier with the cascade structure is essentially a degenerated decision tree, which arranges a series of strong AdaBoost classifiers from simple to complex [ 19 ]. By continuously training, each strong classifier will have a higher detection rate and lower false-positive rate.…”

La inteligencia artificial, una herramienta para la Salud Digital

“…En este estudio se analizaron las muestras sanguíneas de 700 participantes para la detección de parásitos P. falciparum y P. vivax, encontrando que el rendimiento diagnóstico de Autoscope estuvo a la par con la microscopía óptica cuando los portaobjetos tenían un volumen de sangre adecuado para cumplir con los supuestos de diseño (Figura 7). Un uso similar de IA fue aplicado por Uc-Cetina et al, (2015), los cuales analizaron imágenes de muestras de sangre para la detección del parásito T. cruzi, responsable de la enfermedad de chagas, mediante la herramienta de aprendizaje automático AdaBoost, previamente entrenada con características específicas. En este estudio, se cuantificaron una sensibilidad del 100% y una especifidad de 93% (Figura 8) Figura 7.…”