RT Journal Article
T1 On the analysis of local and global features for hyperemia grading
A1 Sánchez Brea, Luisa
A1 Barreira, Noelia
A1 Sánchez, Noelia
A1 Mosquera, Antonio
A1 Pena Verdeal, Hugo
A1 Yebra-Pimentel Vilar, Eva
K1 Hyperemia grading
K1 Optometry
K1 Feature selection
K1 Regression
K1 Medical imaging
AB In optometry, hyperemia is the accumulation of blood flow in the conjunctival tissue. Dry eye syndrome or allergic conjunctivitis are two of its main causes. Its main symptom is the presence of a red hue in the eye that optometrists evaluate according to a scale in a subjective manner. In this paper, we propose an automatic approach to the problem of hyperemia grading in the bulbar conjunctiva. We compute several image features on images of the patients' eyes, analyse the relations among them by using feature selection techniques and transform the feature vector of each image to the value in the adequate range by means of machine learning techniques. We analyse different areas of the conjunctiva to evaluate their importance for the diagnosis. Our results show that it is possible to mimic the experts' behaviour through the proposed approach.
PB Society of Photo-Optical Instrumentation Engineers (SPIE)
YR 2016
FD 2016
LK http://hdl.handle.net/10347/32798
UL http://hdl.handle.net/10347/32798
LA eng
NO L. Sánchez, N. Barreira, N. Sánchez, A. Mosquera, H. Pena-Verdeal, and E. Yebra-Pimentel "On the analysis of local and global features for hyperemia grading", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103411T (17 March 2017)
DS Minerva
RD 24 abr 2026