Título / Title

IMPACT OF MANUAL CORRECTION OVER AUTOMATED SEGMENTATION OF SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY.

Introdução / Purpose

To study the automated segmentation of retinal layers using spectral domain Optical coherence tomography (OCT) and the impact of manual correction over segmentation mistakes

Material e Método / Methods

This was a retrospective, cross-sectional, comparative study in which the automated segmentation of macular thickness using Spectralis™ OCT technology (Heidelberg Engineering, Heidelberg, Germany) was compared to manual segmentation in eyes with no macular changes, macular cystoid edema (CME) and choroidal neovascularization (CNV). Manual correction of automated segmentation of macular thickness was performed by two independent examiners and reanalyzed by them together in case of disagreement.

Resultados / Results

551 eyes of 360 consecutive patients were evaluated. There were no statistically significant differences between automated and manual macular thickness measurement in patients with normal macula and CME, while there was statistically significant difference in central thickness in patients with CNV. Segmentation mistakes in macular OCTs were present in 5.5% (5 of 90) in normal macula group, 17.14% (24 of 140) in the CME group and 66.19% (47 of 71) in CNV group. A difference between automated and manual macular thickness was higher than 10% in 1.4% (2 of 140) in the CME group and in 28.17% (20 of 71) in the CNV group. There was no error higher than 10% in the normal group.

Discussão e Conclusões / Conclusion

The evaluation of automated segmented OCT images revealed appropriate delimitation of macular thickness in patients with no macular changes and CME, since the frequency and magnitude of the segmentation mistakes had low impact over clinical evaluation of the images. On the other hand, automated macular thickness segmentation in patients with CNV showed high frequency and magnitude of mistakes, with potential impact over clinical analysis.

Palavras Chave

optical coherence tomography - OCT - segmentation error