Standardization of choroidal thickness measurements using enhanced depth imaging optical coherence tomography

AIM: To describe and evaluate a standardized protocol for measuring the choroidal thickness(Ch T) using enhanced depth imaging optical coherence tomography(EDI OCT).METHODS: Single 9 mm EDI OCT line scans across the fovea were used for this study. The protocol used in this study classified the EDI OCT images into four groups based on the appearance of the choroidal-scleral interface and suprachoroidal space. Two evaluation iterations of experiments were performed: first, the protocol was validated in a pilot study of 12 healthy eyes. Afterwards, the applicability of the protocol was tested in 82 eyes of patients with diabetes. Inter-observer and intra-observer agreements on image classifications were performed using Cohen’s kappa coefficient(κ). Intraclass correlation coefficient(ICC) and Bland-Altman’s methodology were used for the measurement of the Ch T.RESULTS: There was a moderate(κ=0.42) and perfect(κ =1) inter- and intra-observer agreements on image classifications from healthy eyes images and substantial(κ =0.66) and almost perfect(κ =0.86) agreements from diabetic eyes images. The proposed protocol showed excellent inter- and intra-observer agreements for the Ch T measurements on both, healthy eyes and diabetic eyes(ICC 】0.90 in all image categories). The Bland-Altman plot showed a relatively large Ch T measurement agreement in the scans that contained less visible choroidal outer boundary. CONCLUSION: A protocol to standardize Ch T measurements in EDI OCT images has been developed;the results obtained using this protocol show that the technique is accurate and reliable for routine clinical practice and research.

Automated Artery-Vein Classification in Fundus Color Images

The estimation of Arterio-Venous ratio (AVR) is an important phase in diagnosing various vascular diseases e.g. Diabetic Retinopathy. For calculating this value, it is essential to differentiate the vessels into arteries and veins. This paper presents a novel structural and automated method for artery/vein vessels classification in retinal images. Our method is tested on DRIVE database and the classification accuracy is 88.7 % for pixels and 89.07 % for vessel lines, respectively, which demonstrate the effectives of our approach. Our method will help to achieve the fundus disease surveillance on mobile and remote medical treatment. It has a remarkable social significance.

Fast segmentation of anterior segment optical coherence tomography images using graph cut

Background:Optical coherence tomography(OCT)is a non-invasive imaging system that can be used to obtain images of the anterior segment.Automatic segmentation of these images will enable them to be used to construct patient specific biomechanical models of the human eye.These models could be used to help with treatment planning and diagnosis of patients.Methods:A novel graph cut technique using regional and shape terms was developed.It was evaluated by segmenting 39 OCT images of the anterior segment.The results of this were compared with manual segmentation and a previously reported level set segmentation technique.Three different comparison techniques were used:Dice’s similarity coefficient(DSC),mean unsigned surface positioning error(MSPE),and 95%Hausdorff distance(HD).A paired t-test was used to compare the results of different segmentation techniques.Results:When comparison with manual segmentation was performed,a mean DSC value of 0.943±0.020 was achieved,outperforming other previously published techniques.A substantial reduction in processing time was also achieved using this method.Conclusions:We have developed a new segmentation technique that is both fast and accurate.This has the potential to be used to aid diagnostics and treatment planning.