Non-invasive anemia detection from conjunctiva and sclera images using vision transformer with attention map explainability

Oscar Ramos-Soto, Jorge Ramos-Frutos, Ezequiel Perez-Zarate, Diego Oliva, Seyed Jalaleddin Mousavirad, Sandra E. Balderas-Mata · 2025

Read Non-invasive anemia detection from conjunctiva and sclera images using vision transformer with attention map explainability by Oscar Ramos-Soto, Jorge Ramos-Frutos, Ezequiel Perez-Zarate, Diego Oliva, Seyed Jalaleddin Mousavirad, Sandra E. Balderas-Mata (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12717107.txt.

Description

Oscar Ramos-Soto and five co-authors spot anemia from photos of the eye in a 2025 paper. Low iron anemia is common world wide, yet its firm test needs a blood draw. The white of the eye and its inner lid turn pale when blood runs thin, a clue a camera can catch.

A vision transformer, a model that reads images in patches, learned to sort eye photos into anemia or not. It hit accuracy near ninety-eight and a half percent. Marks on the image show where the model looked, so a doctor can judge its reasons. The team compares it with older machine methods on the same task.

Catalog record

CREATOROscar Ramos-Soto, Jorge Ramos-Frutos, Ezequiel Perez-Zarate, Diego Oliva, Seyed Jalaleddin Mousavirad, Sandra E. Balderas-Mata
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE64 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12717107

Browse the full library · About the Tower of Babel