Banca de QUALIFICAÇÃO: VANESSA DANTAS DE SOUTO COSTA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : VANESSA DANTAS DE SOUTO COSTA
DATE: 25/08/2023
TIME: 15:00
LOCAL: Online
TITLE:

Microservices Architecture for Malaria Classification using YOLO

KEY WORDS:

Image processing, disease classification, Malaria, YOLO, microservices

PAGES: 50
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
SPECIALTY: Processamento Gráfico (Graphics)
SUMMARY:

Malaria affects millions of people each year, predominantly in resource-limited countries. Thus, automated classification of Malaria-infected blood smear images is a critical component in improving the efficiency and accuracy of Malaria diagnosis. In this study, we propose a methodology for Malaria disease classification using the YOLO (You Only Look Once) algorithm and developed a microservices architecture using Golang language to encapsulate it. This process involved designing a modular and scalable system that efficiently handled inference requests while ensuring flexibility and maintainability. YOLO's real-time object detection capabilities make it well-suited for identifying and localizing parasitized cells within blood smear images. Our approach involves data collection, preprocessing, YOLO model configuration and training, post-processing, evaluation, and deployment. We curate a diverse dataset of blood smear images with bounding box annotations, preprocess the data for optimal model performance, and employ transfer learning to adapt the YOLO architecture for Malaria classification. The trained model is evaluated using precision, recall, and mean average precision metrics. With the ability to detect Malaria-infected cells, our proposed YOLO-based solution holds promise in advancing Malaria diagnosis and contributing to effective disease management.

COMMITTEE MEMBERS:
Presidente - 2177445 - BRUNO MOTTA DE CARVALHO
Interna - 1350250 - ANNE MAGALY DE PAULA CANUTO
Externo ao Programa - 2180207 - ITAMIR DE MORAIS BARROCA FILHO - UFRN