A COCO-Formatted Instance-Level Dataset for Plasmodium Falciparum Detection in Giemsa-Stained Blood Smears

arXiv — cs.CVMonday, November 17, 2025 at 5:00:00 AM
  • A new dataset has been developed to improve the detection of Plasmodium falciparum in blood smears, which is vital for malaria diagnosis in developing countries. The dataset enhances the existing NIH malaria dataset with COCO
  • This development is significant as it addresses the challenge of limited datasets with detailed annotations, which has hindered the adoption of automated malaria diagnosis methods. The high F1 score achieved indicates the potential for improved diagnostic accuracy.
  • While there are no directly related articles, the emphasis on deep learning
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Ready to build your own newsroom?

Subscribe to unlock a personalised feed, podcasts, newsletters, and notifications tailored to the topics you actually care about