OCTA Multilayer and Multisector Peripapillary Microvascular Modeling for Diagnosing and Staging of Glaucoma

Abstract

To develop and assess an automatic procedure for classifying and staging glaucomatous vascular damage based on optical coherence tomography angiography (OCTA) imaging. Methods: OCTA scans (Zeiss Cirrus 5000 HD-OCT) from a random eye of 39 healthy subjects and 82 glaucoma patients were used to develop a new classification algorithm based on multilayer and multisector information. The averaged circumpapillary retinal nerve fiber layer (RNFL) thickness was also collected. Three models, support vector machine (SVM), random forest (RF), and gradient boosting (xGB), were developed and optimized for classifying between healthy and glaucoma patients, primary open-angle glaucoma (POAG) and normal-tension glaucoma (NTG), and glaucoma severity groups. Results: All the models, the SVM (area under the receiver operating characteristic [AUROC] 0.89 ± 0.06), the RF (AUROC 0.86 ± 0.06), and the xGB (AUROC 0.85 ± 0.07), with 26, 22, and 29 vascular features obtained after feature selection, respectively, presented a similar performance to the RNFL thickness (AUROC 0.85± 0.06) in classifying healthy and glaucoma patients. The superficial vascular plexus was the most informative layer with the infero temporal sector as the most discriminative region of interest. No significant differentiation was obtained in discriminating the POAG from the NTG group. The xGB model, after feature selection, presented the best performance in classifying the severity groups (AUROC 0.76± 0.06), outperforming the RNFL (AUROC 0.67± 0.06). Conclusions: OCTA multilayer and multisector information has similar performance to RNFL for glaucoma diagnosis, but it has an added value for glaucoma severity classification, showing promising results for staging glaucoma progression. Translational Relevance: OCTA, in its current stage, has the potential to be used in clinical practice as a complementary imaging technique in glaucoma management.

The Role of Optical Coherence Tomography Angiography in Glaucoma

“…As this technology has progressed, a broad range of OCTA metrics were introduced to quantify microvasculature and aid in the diagnosis of glaucoma. Specifically, density parameters are used to track disease progression [18,[30][31][32][33] and more recent work has explored how changes in the macular regions, foveal avascular zone (FAZ), and deep retinal layer microvasculature contribute to disease severity [9].…”

The Development and Clinical Application of Innovative Optical Ophthalmic Imaging Techniques

“…The standard modality of assessing structure, though, is OCT imaging; algorithms can provide assessment of the anterior chamber angle as well as segmentation of the RNFL adjusted for other parameters (age, gender, and eye biometry metrics) to improve the accuracy of the measurements ( 344 – 346 ). Studies have focused on many parameters of the retina and ONH (RNFL, prelaminar area, RPE, choroid, peripapillary sclera, Bruch membrane opening, and minimum rim width), and their performance was highly accurate in identifying glaucomatous eyes (>94%); AI analysis of OCT-A vascular abnormalities of the ONH also yields excellent results ( 347 – 354 ). When comparing various ML classifiers, Wu et al showed that ganglion cell layer measurements were important in early glaucoma detection, whereas RNFL metrics were more useful during disease progression; in fact, Shin et al showed that wide-field SS-OCT scans can even outperform the conventional parameter-based methods ( 355 – 357 ).…”

Automatic Segmentation and Classification Methods Using Optical Coherence Tomography Angiography (OCTA): A Review and Handbook

“…The Otsu method [17] is a commonly used automatic thresholding technique for OCTA images [18][19][20][21][22][23] and is based on finding a threshold that minimizes the intraclass variance of the thresholded black and white pixels. Other global thresholding methods are based on finding a specific percentile of the image intensity histogram [24], the progressive weighted mean of the image intensity histogram [25,26], or by simply fine-tuning a specific gray level [27]. Many analyzed studies employed a global thresholding technique without specifying exactly how the final threshold was determined [22,[28][29][30][31][32][33][34].…”

“…The most common machine learning method that was found for OCTA image classification was the support vector machine (SVM) [85]. This classifier was used for single disease detection, such as DR [70,84] and glaucoma [24,29], and was also employed for more complex classification tasks, such as DR staging [33] and distinguishing between different retinopathies [42]. The other classifiers that were used were NNs [32,83,86], k-means clustering [42], logistic regression [84], and a gradient boosting tree (XGBoost) [84].…”