Purchase this article with an account.
Jay Chhablani, Sushmita Rao Uppugunduri, Mohammed Abdul Rasheed, Ashutosh Richhariya, Soumya Jana, Kiran Vupparaboina; Automated Quantification of Haller's Layer in Choroid using Swept-source Optical Coherence Tomography. Invest. Ophthalmol. Vis. Sci. 2018;59(9):1674.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
To develop an algorithm for automated quantification of Haller's layer in choroid using swept-source optical coherence tomography.
The primary contribution of this work involves defining the approachfor detecting the boundaries of Haller's and Sattler's layer. In brief, the proposedalgorithm extracts the choroidal vessel cross-sections using novel exponentiation-basedbinarization. Subsequently, it detects the large choroidal vessels based on statisticallydefined median criteria. Finally, the desired boundary is obtained by extrapolating andsmoothening the innermost points of the large vessel cross-sections. On 50 OCT B-scansof 50 healthy subjects, algorithm is validated, both qualitatively and quantitatively,vis-a-vis intra-observer variability. A thorough statistical analysis has been performedusing various metrics including Dice coefficient (DC), correlation coefficient (CC) andabsolute difference (AD).
The proposed algorithm achieves a mean DC of 89.48% (SD:5.03%) which isin close agreement with corresponding intra-observer repeatability value of 89.12%(SD:5.68%). Similarly, proposed algorithm achieves mean AD and mean CC of 17.54 m(SD:16.45 m) and 98.10% (SD:1.60%) which are close to corresponding intra-observerrepeatability values of 19.19 m (SD:17.69 m) and 98.58% (SD:1.12%), respectively.
Our study demonstrates high correlation between algorithmic andmanual delineations and can be deployed for further clinical applications to analyzechoroid in greater depth, especially in diseased eyes.
This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.
This PDF is available to Subscribers Only