TY - GEN
T1 - Focal edge association to glaucoma diagnosis
AU - Cheng, Jun
AU - Liu, Jiang
AU - Wong, Damon Wing Kee
AU - Tan, Ngan Meng
AU - Lee, Beng Hai
AU - Cheung, Carol
AU - Baskaran, Mani
AU - Wong, Tien Yin
AU - Aung, Tin
PY - 2011
Y1 - 2011
N2 - Glaucoma is an optic nerve disease resulting in the loss of vision. There are two common types of glaucoma: open angle glaucoma and angle closure glaucoma. Glaucoma type classification is important in glaucoma diagnosis. Clinically, ophthalmologists examine the iridocorneal angle between iris and cornea to determine the glaucoma type as well as the degree of closure. However, manual grading of the iridocorneal angle images is subjective and often time consuming. In this paper, we propose focal edge for automated iridocorneal angle grading. The iris surface is located to determine focal region and focal edges. The association between focal edges and angle grades is built through machine learning. A modified grading system with three grades is adopted. The experimental results show that the proposed method can correctly classify 87.3% open angle and 88.4% closed angle. Moreover, it can correctly classify 75.0% grade 1 and 77.4% grade 0 for angle closure cases.
AB - Glaucoma is an optic nerve disease resulting in the loss of vision. There are two common types of glaucoma: open angle glaucoma and angle closure glaucoma. Glaucoma type classification is important in glaucoma diagnosis. Clinically, ophthalmologists examine the iridocorneal angle between iris and cornea to determine the glaucoma type as well as the degree of closure. However, manual grading of the iridocorneal angle images is subjective and often time consuming. In this paper, we propose focal edge for automated iridocorneal angle grading. The iris surface is located to determine focal region and focal edges. The association between focal edges and angle grades is built through machine learning. A modified grading system with three grades is adopted. The experimental results show that the proposed method can correctly classify 87.3% open angle and 88.4% closed angle. Moreover, it can correctly classify 75.0% grade 1 and 77.4% grade 0 for angle closure cases.
UR - http://www.scopus.com/inward/record.url?scp=84055217309&partnerID=8YFLogxK
U2 - 10.1109/IEMBS.2011.6091111
DO - 10.1109/IEMBS.2011.6091111
M3 - Conference contribution
C2 - 22255334
AN - SCOPUS:84055217309
SN - 9781424441211
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 4481
EP - 4484
BT - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
T2 - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Y2 - 30 August 2011 through 3 September 2011
ER -
