Macular Hole Detection Using a New Hybrid Method: Using Multilevel Thresholding and Derivation on Optical Coherence Tomographic Images

Application of optical coherence tomography angiography in the assessment of diabetic macular edema staging and laser photocoagulation efficacy

OBJECTIVE

This study aimed to analyze the effect of optical coherence tomography angiography (OCTA) on diabetic macular edema (DME) staging and assess the efficacy of laser photocoagulation.

METHODS

Eighty-six patients (141 eyes) with suspected DME who visited our hospital from August 2019 to March 2022 were selected and underwent fundus angiography and OCTA. The two examination methods were compared in terms of their efficacy in macular edema staging. Subsequently, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of OCTA in diagnosing DME were assessed using fundus angiography as the gold standard. In patients with clinically significant macular edema (CSME) treated with laser photocoagulation, the central concave non-perfused zone (FAZ), vascular density (VD), central macular retinal thickness (CRT), whole retinal blood flow density (FD-300), superficial capillary plexus (SCP), and deep capillary plexus (DCP) were measured using the OCTA 3 mm × 3 mm mode before treatment, at 3 months after treatment, and at 6 months after treatment. SCP, deep capillary plexus (DCP), blood flow density (VD), best corrected visual acuity (BCVA), and central retinal thickness (CRT) were recorded before treatment, 3 months after treatment, and 6 months after treatment. The correlation between BCVA and pre-treatment OCTA parameters at 6 months after treatment was analyzed using Pearson's correlation.

RESULTS

Fundus angiography was performed in 86 patients (141 eyes) with suspected DME. Of the 141 eyes, 44 had no leakage, 52 had diffuse edema, 40 had focal macular edema, and 5 had eyes ischemia. A total of 97 eyes showed CSME on fundus angiography. Using fundus angiography as the gold standard, OCTA exhibited a sensitivity of 97.94 %, a specificity of 63.64 %, and an accuracy of 87.23 % in diagnosing CSME. The Kappa value between OCTA and fundus angiography was 0.674. The receiver operating characteristic curve revealed that the area under the curve (AUC) of OCTA in diagnosing CSME was 0.808 (95 % confidence interval: 0.717-0.899). The BCVA was higher, while the CRT was lower in CSME patients at 3 and 6 months after treatment (P<0.05). No significant difference was observed in the OCTA parameters in CSME patients at 3 months after treatment compared with that before treatment (P>0.05). Similarly, no significant difference was found in the FD300 of CSME patients at 6 months after treatment compared with that before treatment (P>0.05). However, the FAZ area, DCP-VD (overall, central concave, and paracentral concave), and SCP-VD (overall, central concave, and paracentral concave) were higher in CSME patients at 6 months after treatment compared with that before treatment (P<0.05). Pearson's correlation showed that BCVA was positively correlated with pre-treatment FAZ area, DCP-VD, and SCP-VD (r>0, P<0.05), and negatively associated with CRT (r<0, P<0.05).

CONCLUSION

OCTA exhibited high sensitivity and specificity in diagnosis and staging DME. It adeptly captures the microvascular and visual changes in the central macular recess before and after laser photocoagulation therapy, which can quantitatively guide the follow-up treatment of DME.

Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography

BACKGROUND

Automated identification of spectral domain optical coherence tomography (SD-OCT) features can improve retina clinic workflow efficiency as they are able to detect pathologic findings. The purpose of this study was to test a deep learning (DL)-based algorithm for the identification of Idiopathic Full Thickness Macular Hole (IFTMH) features and stages of severity in SD-OCT B-scans.

METHODS

In this cross-sectional study, subjects solely diagnosed with either IFTMH or Posterior Vitreous Detachment (PVD) were identified excluding secondary causes of macular holes, any concurrent maculopathies, or incomplete records. SD-OCT scans (512 × 128) from all subjects were acquired with CIRRUS™ HD-OCT (ZEISS, Dublin, CA) and reviewed for quality. In order to establish a ground truth classification, each SD-OCT B-scan was labeled by two trained graders and adjudicated by a retina specialist when applicable. Two test sets were built based on different gold-standard classification methods. The sensitivity, specificity and accuracy of the algorithm to identify IFTMH features in SD-OCT B-scans were determined. Spearman's correlation was run to examine if the algorithm's probability score was associated with the severity stages of IFTMH.

RESULTS

Six hundred and one SD-OCT cube scans from 601 subjects (299 with IFTMH and 302 with PVD) were used. A total of 76,928 individual SD-OCT B-scans were labeled gradable by the algorithm and yielded an accuracy of 88.5% (test set 1, 33,024 B-scans) and 91.4% (test set 2, 43,904 B-scans) in identifying SD-OCT features of IFTMHs. A Spearman's correlation coefficient of 0.15 was achieved between the algorithm's probability score and the stages of the 299 (47 [15.7%] stage 2, 56 [18.7%] stage 3 and 196 [65.6%] stage 4) IFTMHs cubes studied.

CONCLUSIONS

The DL-based algorithm was able to accurately detect IFTMHs features on individual SD-OCT B-scans in both test sets. However, there was a low correlation between the algorithm's probability score and IFTMH severity stages. The algorithm may serve as a clinical decision support tool that assists with the identification of IFTMHs. Further training is necessary for the algorithm to identify stages of IFTMHs.