Counting on AI: Tracking Mpox with Precision
Failed to add items
Add to basket failed.
Add to wishlist failed.
Remove from wishlist failed.
Adding to library failed
Follow podcast failed
Unfollow podcast failed
Counting on AI: Tracking Mpox with Precision
-
Narrated by:
-
By:
About this listen
Can deep learning help in the fight against emerging infectious diseases? In this episode of VALIANT Pulse, we explore the collaborative work led by Vanderbilt University, the NIH, and the Institut National de Recherche Biomédicale to automate mpox lesion counting using AI. Building on field data from the Democratic Republic of the Congo, the team compares leading segmentation models—including UNet++, Mask R-CNN, YOLOv8, and E2EC—to determine how well machines can count and classify skin lesions in challenging, real-world settings. Led by Dr. Eric Tkaczyk and Dr. Benoit Dawant, the project blends engineering and global health to support more accurate clinical trial endpoints and faster disease tracking. Opinions shared reflect scholarly perspectives and are not official policy.