A transfer learning pupil detector, RAPDNet, is shown to detect relative afferent pupillary defect from headset videos with 90.6% sensitivity and specificity over 64 cases, outperforming three handcrafted algorithms.
Eye Disease Statistics ,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Relative Afferent Pupillary Defect Screening through Transfer Learning
A transfer learning pupil detector, RAPDNet, is shown to detect relative afferent pupillary defect from headset videos with 90.6% sensitivity and specificity over 64 cases, outperforming three handcrafted algorithms.