Microscopia Automatizada e Inteligente com Deep Learning para Detecção de Malária

Jesus Dourado de Albuquerque; Elloá B. Guedes

doi:10.20906/SBAI-SBSE-2023/3829

Jesus Dourado de Albuquerque Grupo de Pesquisa em Sistemas Inteligentes, Universidade do Estado do Amazonas (UEA)
Elloá B. Guedes Grupo de Pesquisa em Sistemas Inteligentes, Universidade do Estado do Amazonas (UEA)

DOI: https://doi.org/10.20906/SBAI-SBSE-2023/3829

Keywords: Automated and Intelligent Microscopy, Computer Vision, Object Detection, Deep Learning, Malaria

Abstract

This study presents experimental results on the use of YOLO-based Regional Convolutional Neural Networks for the detection of malaria-causing protozoa in microscopic images. The analysis of the experimental results highlighted YOLOv7 X as the benchmark solution, achieving an F-Score of 80.24%, which validates the proposed strategy on a realistic dataset and contributes to the development of Automated and Intelligent Microscopy.