Limits...
Chagas parasite detection in blood images using AdaBoost.

Uc-Cetina V, Brito-Loeza C, Ruiz-Piña H - Comput Math Methods Med (2015)

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: Facultad de Matemáticas, Universidad Autónoma de Yucatán, Anillo Periférico Norte, Tablaje Catastral, 13615 Mérida, YUC, Mexico.

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.

Show MeSH

Related in: MedlinePlus

ROC curves using AdaBoost and SVMs with three different types of kernel: linear, polynomial, and RBFs.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4377374&req=5

fig10: ROC curves using AdaBoost and SVMs with three different types of kernel: linear, polynomial, and RBFs.

Mentions: Looking at the values provided in Table 2, we see that AdaBoost methods are as good as SVM methods in terms of sensitivity, with mean value of 1 and standard deviation of 0. All five methods were trained to detect every parasite in the test sets. In terms of specificity, AdaBoost + Postprocessing is clearly the winner among the five methods being compared, with mean value of 0.9325 and standard deviation of 0.0496, as given in Table 3. Tables 4 and 5 also show that AdaBoost + Postprocessing is superior to the others, in terms of F-measures. In Figure 8, we illustrate the result of our AdaBoost algorithm for Chagas parasite detection. These results were obtained with a cascade of weak classifiers of 11 stages. Figure 9 provides the ROC curves for SVMs using different degrees of polynomial kernels and Figure 10 compares the ROC curves for AdaBoost and SVMs methods using different types of kernels.


Chagas parasite detection in blood images using AdaBoost.

Uc-Cetina V, Brito-Loeza C, Ruiz-Piña H - Comput Math Methods Med (2015)

ROC curves using AdaBoost and SVMs with three different types of kernel: linear, polynomial, and RBFs.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4377374&req=5

fig10: ROC curves using AdaBoost and SVMs with three different types of kernel: linear, polynomial, and RBFs.
Mentions: Looking at the values provided in Table 2, we see that AdaBoost methods are as good as SVM methods in terms of sensitivity, with mean value of 1 and standard deviation of 0. All five methods were trained to detect every parasite in the test sets. In terms of specificity, AdaBoost + Postprocessing is clearly the winner among the five methods being compared, with mean value of 0.9325 and standard deviation of 0.0496, as given in Table 3. Tables 4 and 5 also show that AdaBoost + Postprocessing is superior to the others, in terms of F-measures. In Figure 8, we illustrate the result of our AdaBoost algorithm for Chagas parasite detection. These results were obtained with a cascade of weak classifiers of 11 stages. Figure 9 provides the ROC curves for SVMs using different degrees of polynomial kernels and Figure 10 compares the ROC curves for AdaBoost and SVMs methods using different types of kernels.

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: Facultad de Matemáticas, Universidad Autónoma de Yucatán, Anillo Periférico Norte, Tablaje Catastral, 13615 Mérida, YUC, Mexico.

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.

Show MeSH
Related in: MedlinePlus