Artificial intelligence-based grading of human cataracts: A feasibility study

Catharina Latz, Franziska Rothen, Annika Licht, Katharina A Ponto, Alireza Mirshahi · 2026

Read Artificial intelligence-based grading of human cataracts: A feasibility study by Catharina Latz, Franziska Rothen, Annika Licht, Katharina A Ponto, Alireza Mirshahi (2026) 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/plos-pone-0355969.txt.

Description

Catharina Latz and colleagues tested whether artificial intelligence can grade cataracts from eye scans without a doctor's grading. Cataracts cloud the lens, and grading guides surgery decisions. Their 2026 feasibility study trained a neural network on about eighteen hundred scan images from just over nine hundred eyes.

Human grades from a standard scale served as the reference. The system graded one cataract type, at the back of the lens, with fairly high accuracy. It graded clouding of the lens centre much less well, at about three in five correct. Most errors there landed in a neighbouring grade. Latz and colleagues call the results promising but preliminary, a base for larger and more careful validation.

Catalog record

CREATORCatharina Latz, Franziska Rothen, Annika Licht, Katharina A Ponto, Alireza Mirshahi
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE18382
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355969

Browse the full library · About the Tower of Babel