Login / Signup

A novel iris transillumination grading scale allowing flexible assessment with quantitative image analysis and visual matching.

Chen WangFlavia BrancusiZaheer M ValivullahMichael G AndersonDenise CunninghamAdam Hedberg-BuenzBradley PowerDimitre SimeonovWilliam A GahlWadih M ZeinDavid R AdamsBrian Brooks
Published in: Ophthalmic genetics (2017)
The current standard for assessing iris transillumination is expert assessment of clinical exam findings. We adapted an image-analysis technique to generate quantitative transillumination values. Quantitative ranking was shown to be highly similar to a ranking produced by both expert and nonexpert reviewers. This finding suggests that the image characteristics used to quantify iris transillumination do not require expert interpretation. Inter-rater rankings were also highly similar, suggesting that varied methods of transillumination ranking are robust in terms of producing reproducible results.
Keyphrases
  • high resolution
  • clinical practice
  • deep learning
  • machine learning