Logo: to the web site of Uppsala University

Purpose

Glaucoma leads to pathological loss of axons in the retinal nerve fibre layer at the optic nerve head (ONH). This study aimed to develop a strategy for the estimation of the cross-sectional area of the axons in the ONH. Furthermore, improving the estimation of the thickness of the nerve fibre layer, as compared to a method previously published by us.

Methods

In the 3D-OCT image of the ONH, the central limit of the pigment epithelium and the inner limit of the retina, respectively, were identified with deep learning algorithms. The minimal distance was estimated at equidistant angles around the circumference of the ONH. The cross-sectional area was estimated by the computational algorithm. The computational algorithm was applied on 16 non-glaucomatous subjects.

Results

The mean cross-sectional area of the waist of the nerve fibre layer in the ONH was 1.97 ± 0.19 mm². The mean difference in minimal thickness of the waist of the nerve fibre layer between our previous and the current strategies was estimated as CIμ (0.95) 0 ± 1 μm (d.f. = 15).

Conclusions

The developed algorithm demonstrated an undulating cross-sectional area of the nerve fibre layer at the ONH. Compared to studies using radial scans, our algorithm resulted in slightly higher values for cross-sectional area, taking the undulations of the nerve fibre layer at the ONH into account. The new algorithm for estimation of the thickness of the waist of the nerve fibre layer in the ONH yielded estimates of the same order as our previous algorithm.

Glaucoma is a chronic progressive disease that causes loss of retinal ganglion cells, which impairs the visual field. In optic coherence tomography (OCT) image, the retinal ganglion cell (RGC) axons in the optic nerve head (ONH) can be quantified as the minimal thickness from the ONH Pigmental epithelium Central Limit (OPCL) to the Inner limit of the Retina Closest Point (IRCP). Alternatively, the minimal cross-sectional surface area can be measured. In peripapillary atrophy, the morphometry of the retinal pigmental epithelium is affected.

Purpose: To design and test a new computational algorithm for estimation of Pigment epithelium to Inner limit of the Retina Minimal Area (PIMA) and evaluate a new method to estimate the Pigment epithelium to Inner limit of the Retina Minimal Distance (PIMD). OPCL can be detected and annotated by a deep learning algorithm in individuals with peripapillary atrophy.

Methods: A deep learning algorithm has been trained to automatically detect OPCL, IRCP and calculate PIMD. A new computational algorithm was developed to estimate PIMA in OCT images of young adults. The mean between the first and second version of estimating PIMD was evaluated. The difference of distance between the ONH center-OPCL and ONH center-atrophic edge was estimated in eyes with peripapillary atrophy.

Results: A 95% confidence interval for PIMA-2π was estimated to 1.97 ± 0.19 mm2 (df = 15). A confidence interval for the difference between PIMDv1-2π and PIMDv2-2π was 0 ± 1 μm (df = 15). A 95 % confidence interval for the mean difference between ONH-OPCL and ONH-atrophic edge was estimated to 692 ± 192 µm (df = 5).

Conclusions: The computational algorithm for estimation of PIMA was developed and applied. An initial analysis indicated the capacity of the deep learning algorithm to detect OPCL in subjects with PPA.

Keywords: deep learning, optic nerve head, ONH, retinal pigmental epithelium, RPE, PIMD, PIMD-2π, minimal distance, PIMA, PIMA-2π, minimal area, peripapillary atrophy, PPA, optic coherence tomography, OCT, glaucoma, quantification, retinal ganglion cell axons

Glaucoma is a global disease that leads to blindness due to pathological loss of retinal ganglion cell axons in the optic nerve head (ONH). The presented project aims at improving a computational algorithm for estimating the thickness and surface area of the waist of the nerve fiber layer in the ONH. Our currently developed deep learning AI algorithm meets the need for a morphometric parameter that detects glaucomatous change earlier than current clinical follow-up methods. In 3D OCT image volumes, two different AI algorithms identify the Optic nerve head Pigment epithelium Central Limit (OPCL) and the Inner limit of the Retina Closest Point (IRCP) in a 3D grid. Our computational algorithm includes the undulating surface area of the waist of the ONH, as well as waist thickness. In 16 eyes of 16 non-glaucomatous subjects aged [20;30] years, the mean difference in minimal thickness of the waist of the nerve fiber layer between our previous and the current post-processing strategies was estimated as CI mu(0.95) 0 +/- 1 mu m (D.f. 15). The mean surface area of the waist of the nerve fiber layer in the optic nerve head was 1.97 +/- 0.19 mm(2). Our computational algorithm results in slightly higher values for surface areas compared to published work, but as expected, this may be due to surface undulations of the waist being considered. Estimates of the thickness of the waist of the ONH yields estimates of the same order as our previous computational algorithm.

The present project aims at developing a fully automatic software for estimation of the waist of the nerve fiber layer in the Optic Nerve Head (ONH) angularly resolved in the frontal plane as a tool for morphometric monitoring of glaucoma. The waist of the nerve fiber layer is here defined as Pigment epithelium central limit –Inner limit of the retina – Minimal Distance, (PIMD). 3D representations of the ONH were collected with high resolution OCT in young not glaucomatous eyes and glaucomatous eyes. An improved tool for manual annotation was developed in Python. This tool was found user friendly and to provide sufficiently precise manual annotation. PIMD was automatically estimated with a software consisting of one AI model for detection of the inner limit of the retina and another AI model for localization of the Optic nerve head Pigment epithelium Central limit (OPCL). In the current project, the AI model for OPCL localization was retrained with new data manually annotated with the improved tool for manual annotation both in not glaucomatous eyes and in glaucomatous eyes. Finally, automatic annotations were compared to 3 annotations made by 3 independent annotators in an independent subset of both the not glaucomatous and the glaucomatous eyes. It was found that the fully automatic estimation of PIMD-angle overlapped the 3 manual annotators with small variation among the manual annotators. Considering interobserver variation, the improved tool for manual annotation provided less variation than our original annotation tool in not glaucomatous eyes suggesting that variation in glaucomatous eyes is due to variable pathological anatomy, difficult to annotate without error. The small relative variation in relation to the substantial overall loss of PIMD in the glaucomatous eyes compared to the not glaucomatous eyes suggests that our software for fully automatic estimation of PIMD-angle can now be implemented clinically for monitoring of glaucoma progression.

Purpose: To verify that a deep learning model developed by our research group does not wrongly identify the outer edge of the atrophic zone in eyes with peripapillary atrophy (PPA) rather than a point adjacent to the external limit of the minimal waist of the nerve fiber bundles in the ONH.

Methods: Subjects with at least one eye with PPA were included. The ONH of the eye with PPA was imaged with colour photography, and the three-dimensional structure of the ONH was captured three times at one occasion with SS-OCT (Topcon Triton, Japan). Each capture was exported to a custom-made software for analysis. The custom-made software, AutoPimd, allowed fully automatic localization of the external limit of the minimal waist of the nerve fiber layer in space using deep learning-model. An en face visualization of the frontal plane of the ONH and user measurement in the en face view is possible. The en face view in the OCT volume was verified to render PPA as imaged in the photograph. The distance between the ONH center and the extreme edge of the PPA was measured in the en face view of the OCT. Then, the frontal plane distance between the ONH center and the fully automatically detected external limit of the minimal waist of the nerve fiber layer in the ONH was measured along the same frontal plane angle.

Results: A 95 % confidence interval for the mean difference between the distance from center of the ONH to the extreme edge of the PPA, and the distance from the center of the ONH to the corresponding fully automatically detected outer limit of the minimal waist of the nerve fiber layer was estimated to 692 ± 192 μm (d.f = 5).

Conclusion: Our AI model does not wrongly localize the outer limit of PPA as the external limit of the minimal waist of the nerve fiber layer. The structural representation of the external limit of the minimal waist of the nerve fiber bundles localized by our fully automatic AI model in eyes with PPA remains to be identified.