Computer Vision Identification of Trachomatous Inflammation-Follicular Using Deep Learning

The Journal of Cornea and External Disease

By 
Ashlin S. Joye, 
Marissa G. Firlie, 
Dionna M. Wittberg, 
Solomon Aragie, 
Scott D. Nash, 
Zerihun Tadesse, 
Adane Dagnew, 
Dagnachew Hailu, 
Fisseha Admassu, 
Bilen Wondimteka, 
Habib Getachew, 
Endale Kabtu, 
Social Beyecha, 
Meskerem Shibiru, 
Banchalem Getnet, 
Tibebe Birhanu, 
Seid Abdu, 
Solomon Tekew, 
Thomas M. Lietman, 
Jeremy D. Keenan, 
and Travis K. Redd

Trachoma surveys are used to estimate the prevalence of trachomatous inflammation-follicular (TF) to guide mass antibiotic distribution. These surveys currently rely on human graders, introducing a significant resource burden and potential for human error. This study describes the development and evaluation of machine learning models intended to reduce cost and improve reliability of these surveys.

Read the full article(opens in new window)

Subcategory: Tools

Related Tags