Publications by authors named "D Sukumarran"
Article Synopsis
- Malaria is a critical global health issue requiring fast and accurate diagnosis to control its spread, prompting the need for automated diagnostic tools that can quickly identify infected cells.
- This study modifies the YOLOv4 deep learning model through layer pruning and backbone replacement, enhancing its performance for malaria diagnosis while reducing computation time and model size.
- The modified YOLOv4-RC3_4 model shows significant improvement, achieving a 90.70% mean accuracy precision and outperforming the original model by over 9%, demonstrating its effectiveness in detecting infected cells.
Timely and rapid diagnosis is crucial for faster and proper malaria treatment planning. Microscopic examination is the gold standard for malaria diagnosis, where hundreds of millions of blood films are examined annually. However, this method's effectiveness depends on the trained microscopist's skills.
View Article and Find Full Text PDF