Using artificial intelligence for automatic choroidal segmentation
Australian researchers have applied deep learning to OCT scans in order to automatically define the boundaries of the choroid and the retina
Scientists at the Queensland University of Technology (QUT) have used artificial intelligence technology to automatically define the boundaries of the choroid.
For their work, published in Nature Scientific Reports, researchers collected optical coherence tomography (OCT) chorio-retinal eye scans from an 18-month study of 101 children with good vision.
These images were used to train an algorithm to recognise choroid boundaries.
The performance of the algorithm was then compared to standard image analysis methods, with the researchers highlighting that the algorithm was more reliable and accurate.
QUT senior research fellow, Dr David Alonso-Caneiro, shared: “We feel our methods could provide a way to better map and monitor changes in choroid tissue, and potentially diagnose eye diseases earlier.”
Image credit: Queensland University of Technology