Chagas parasite classification in blood sample images using different machine learning architectures.

Area of Science:

• Medical Parasitology
• Computational Biology
• Machine Learning in Healthcare

Background:

• Chagas disease is a significant public health concern in Latin America.
• Early diagnosis and treatment are crucial for managing Chagas disease and improving patient outcomes.
• Current diagnostic methods can be improved with advanced computational approaches.

Purpose of the Study:

• To develop and evaluate deep learning models for classifying Chagas parasites in blood smear images.
• To identify the most effective deep learning architecture for accurate Chagas parasite detection.
• To compare the performance of the proposed model against other machine learning techniques.

Main Methods:

• Utilized deep learning classification models, including architectures based on residual networks and separable convolutions.
• Trained and tested models on blood smear sample images for parasite identification.
• Implemented a Support Vector Machine (SVM) as the final classifier in the optimized model (Res2_SVM).

Main Results:

• The Res2_SVM model demonstrated superior performance in Chagas parasite classification.
• Achieved high accuracy, precision, recall, and F1-score on the test dataset.
• The optimized model, Res2_SVM, achieved [Formula: see text] accuracy, [Formula: see text] precision, [Formula: see text] recall, and [Formula: see text] F1-score.

Conclusions:

• Deep learning, specifically the Res2_SVM model, offers a promising approach for the early and accurate diagnosis of Chagas disease.
• The Res2_SVM model provides an efficient and effective tool for identifying Chagas parasites in blood samples.
• This advancement can contribute to better management and reduced mortality rates associated with Chagas disease.