Effect of segmentation error correction on optical coherence tomography angiography measurements in healthy subjects and diabetic macular oedema

Abstract

PurposeTo evaluate the impact of segmentation error on vessel density measurements in healthy eyes and eyes with diabetic macular oedema (DMO).MethodsIn this prospective, comparative, non-interventional study, enface optical coherence tomography angiography (OCTA) images of the macula from healthy eyes and eyes with DMO were acquired. Two expert graders assessed and corrected the segmentation error. The rate of segmentation error and the changes in vessel density and inner retinal thickness after correction of the segmentation error were recorded and compared between the two groups.Results20 eyes with DMO and 24 healthy eyes were evaluated. Intergrader agreement was excellent (intraclass correlation coefficient ≥0.9) for all parameters in both groups. The rate of segmentation error was 33% and 100% in healthy and diabetic eyes, respectively (p<0.001). Nine healthy eyes (37.5%) and all eyes with DMO (100%) were noted to exhibit a change in at least one of the foveal or parafoveal vessel density measurements. The rate of any change in foveal and parafoveal vessel densities in both the superficial and deep capillary plexus was statistically significantly higher in the diabetic group (all p<0.001). No statistically significant change was observed in mean vessel density (superficial and deep capillary plexuses) after correction of the segmentation error in healthy and DMO eyes (All p>0.05). However, the mean absolute change in the vessel density measurements was statistically significantly higher in the diabetic group (all p<0.05). The mean absolute change in superficial and deep inner retinal thickness was statistically significantly higher in DMO (p=0.02 and p=0.002, respectively).ConclusionsIn this study, misidentification of retinal layers and consequent vessel density measurement error occurred in all eyes with DMO and in one-third of healthy eyes. The segmentation error should be checked and manually corrected in the OCTA vessel density measurements, especially in the presence of macular oedema.

Guidelines on Optical Coherence Tomography Angiography Imaging: 2020 Focused Update

“…Segmentation errors are common in pathological conditions [12]. As an example, eyes with diabetic macular edema are frequently characterized by segmentation errors, as recently demonstrated by Ghasemi Falavarjani and colleagues [16]. A recent study using convolutional neural networks (CNNs) has demonstrated the utility of this algorithm to improve segmentation of OCTA data [17].…”

“…Segmentation errors represent a significant and recurring OCTA artifact [12,15,16]. As discussed above, en face OCTA images are displayed by locating two boundaries throughout the retinal and/or choroidal structure, and vessels are therefore visualized using different available algorithms.…”

“…In addition, the 2D OCTA analysis may also overestimate perfusion in cases where retinal vessels or vascular abnormalities (e.g., microaneurysms) cross two consecutive slabs and are thus visualized twice (on two different en face OCTA images) [41,45]. Finally, en face images may be significantly affected by segmentation errors, especially in pathological conditions [1,16].…”

Optical Coherence Tomography Angiography in Diabetes and Diabetic Retinopathy

“…The occurrence of segmentation error was 11% in the non-proliferative DR category and increased to 50% in the proliferative DR category [179]. Furthermore, high rates of segmentation error, particularly in eyes with diabetic macular edema, that may affect vascular density measurements, were reported [180]. Correction of these segmentation errors can be made manually with the built-in software.…”

Quantification of diabetic macular ischemia using novel three‐dimensional optical coherence tomography angiography metrics

“…In addition, the 2D en face visualization may also overestimate perfusion in cases where retinal vessels or vascular abnormalities (eg, microaneurysms) cross two consecutive slabs and are thus visualized twice (on two different en face images) [22,23]. Finally, en face images may be altered because of segmentation errors which may limit their utility, especially in pathological tissue [6,24]. Conversely, a 3D illustration does not require flattening of flow data and also permits rotation of the vessels on the three axes which further reduces limitations by vessel foreshortening and overlapping anatomy [22,25].…”