Dataset for a novel AI-powered diagnostic tool for Plasmodium parasite detection authors

Area of Science:

• Medical diagnostics
• Parasitology
• Artificial Intelligence in healthcare

Background:

• Malaria is a significant public health issue, especially in Sub-Saharan Africa.
• Early malaria detection and treatment are vital for reducing illness and death.

Purpose of the Study:

• To create an innovative, accurate, and efficient diagnostic tool for malaria parasite identification.
• To utilize automated image processing and an AI-based system for faster and more standardized malaria diagnosis.

Main Methods:

• Collection, curation, and annotation of 881 blood smear images.
• Development of an Artificial Intelligence system for analyzing Plasmodium species in images.
• Automated image processing for malaria parasite identification.

Main Results:

• A curated dataset of 881 blood smear images (positive and negative for malaria).
• Development of an AI system for automated malaria parasite identification from images.

Conclusions:

• The developed AI system shows potential for simple, accurate, and efficient malaria diagnosis.
• Automated image processing can significantly shorten diagnosis times and improve standardization in endemic regions.