Framework for quantitative three-dimensional choroidal vasculature analysis using optical coherence tomography

Semi-supervised contrast learning-based segmentation of choroidal vessel in optical coherence tomography images

Objective.Choroidal vessels account for 85% of all blood vessels in the eye, and the accurate segmentation of choroidal vessels from optical coherence tomography (OCT) images provides important support for the quantitative analysis of choroid-related diseases and the development of treatment plans. Although deep learning-based methods have great potential for segmentation, these methods rely on large amounts of well-labeled data, and the data collection process is both time-consuming and laborious.Approach.In this paper, we propose a novel asymmetric semi-supervised segmentation framework called SSCR, based on a student-teacher model, to segment choroidal vessels in OCT images. The proposed framework enhances the segmentation results with uncertainty-aware self-integration and transformation consistency techniques. Meanwhile, we designed an asymmetric encoder-decoder network called Pyramid Pooling SegFormer (APP-SFR) for choroidal vascular segmentation. The network combines local attention and global attention information to improve the model's ability to learn complex vascular features. Additionally, we proposed a boundary repair module that enhances boundary confidence by utilizing a repair head to re-predict selected fuzzy points and further refines the segmentation boundary.Main results.We conducted extensive experiments on three different datasets: the ChorVessel dataset with 400 OCT images, the Meibomian Glands (MG) dataset with 400 images, and the U2OS Cell Nucleus Dataset with 200 images. The proposed method achieved an average Dice score of 74.23% on the ChorVessel dataset, which is 2.95% higher than the fully supervised network (U-Net) and outperformed other comparison methods. In both the MG dataset and the U2OS cell nucleus dataset, our proposed SSCR method achieved average Dice scores of 80.10% and 87.26%, respectively.Significance.The experimental results show that our proposed methods achieve better segmentation accuracy than other state-of-the-art methods. The method is designed to help clinicians make rapid diagnoses of ophthalmic diseases and has potential for clinical application.

Outcome Measures for Disease Monitoring in Intraocular Inflammatory and Infectious Diseases (OCTOMERIA): Understanding the Choroid in Uveitis with Optical Coherence Tomography (OCT)

PURPOSE

To compare imaging modalities for the choroid of the eye, and evaluate various choroidal changes in uveitides entities.

METHODS

A comprehensive systematic literature review was conducted looking at current imaging modalities available to assess choroid architecture and commonly used parameters available to qualify and quantify choroidal changes, before looking at specific uveitides entities with choroidal involvement which have been broadly separated into non-infectious and infectious in etiology.

RESULTS

We describe the various modalities currently available to evaluate the choroid of the eye such as Ultrasound B Scan, ICGA, and OCT. Choroidal changes in various ocular and systemic diseases such as Behcet's Disease, Sarcoidosis, Syphillis, Tuberculosis, and many more have been reported and published.

CONCLUSION

Multiple choroidal tomographic and angiotomographic findings have been demonstrated for evaluation in uveitis. These findings can manifest in multiple ocular and systemic diseases, and can be illustrated using the various imaging modalities at present. Future advancements in choroidal imaging would help to adapt these findings into parameters for clinical practice to properly evaluate these ocular and systemic diseases.

Depth-resolved visualization and automated quantification of hyperreflective foci on OCT scans using optical attenuation coefficients

An automated depth-resolved algorithm using optical attenuation coefficients (OACs) was developed to visualize, localize, and quantify hyperreflective foci (HRF) seen on OCT imaging that are associated with macular hyperpigmentation and represent an increased risk of disease progression in age related macular degeneration. To achieve this, we first transformed the OCT scans to linear representation, which were then contrasted by OACs. HRF were visualized and localized within the entire scan by differentiating HRF within the retina from HRF along the retinal pigment epithelium (RPE). The total pigment burden was quantified using the en face sum projection of an OAC slab between the inner limiting membrane (ILM) to Bruch's membrane (BM). The manual total pigment burden measurements were also obtained by combining manual outlines of HRF in the B-scans with the total area of hypotransmission defects outlined on sub-RPE slabs, which was used as the reference to compare with those obtained from the automated algorithm. 6×6 mm swept-source OCT scans were collected from a total of 49 eyes from 42 patients with macular HRF. We demonstrate that the algorithm was able to automatically distinguish between HRF within the retina and HRF along the RPE. In 24 test eyes, the total pigment burden measurements by the automated algorithm were compared with measurements obtained from manual segmentations. A significant correlation was found between the total pigment area measurements from the automated and manual segmentations (P < 0.001). The proposed automated algorithm based on OACs should be useful in studying eye diseases involving HRF.

Value of Combining Optical Coherence Tomography with Fundus Photography in Screening Retinopathy in Patients with High Myopia

Objective

To explore the value of combining optical coherence tomography (OCT) with fundus photography in screening retinopathy in patients with high myopia.

Methods

By means of retrospective study, 40 high myopia patients with retinopathy treated in our hospital from January 2020 to January 2021 were selected as the study group, and 40 healthy individuals in the same period were included in the control group. All patients received traditional ophthalmic examination, and accepted fundus fluorescence imaging, OCT, and fundus photography examination step by step by the same operator. After that, three physicians read the slides by the double blind method, and took the results of fundus fluorescence imaging as the gold standard to analyze the diagnostic efficacy of OCT, fundus photography and their combination.

Results

The clinical data and examination results showed that no statistical differences in general data including patients' mean age, gender ratio, and educational degree between the study group and the control group were observed (P > 0.05), and the nerve thickness above/below the optic disk and temporal/nasal nerve thickness of the optic disk of the study group were significantly different from those of the control group (P < 0.001); the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy rate of diagnosis of combining OCT with fundus photography were respectively 95.0%, 97.5%, 97.4%, 95.1%, and 96.3%, which were significantly higher than OCT or fundus photography alone (P < 0.05); and for combined examination, AUC (95%CI) = 0.963 (0.000–1.000).

Conclusion

Combining OCT with fundus photography can effectively identify high myopia patients with retinopathy, which is conducive to improving clinical positive ratio and providing objective basis for treatment.

Application of Deep Learning Methods for Binarization of the Choroid in Optical Coherence Tomography Images

Purpose

The purpose of this study was to develop a deep learning model for automatic binarization of the choroidal tissue, separating choroidal blood vessels from nonvascular stromal tissue, in optical coherence tomography (OCT) images from healthy young subjects.

Methods

OCT images from an observational longitudinal study of 100 children were used for training, validation, and testing of 5 fully semantic networks, which provided a binarized output of the choroid. These outputs were compared with ground truth images, generated from a local binarization technique after manually optimizing the analysis window size for each individual image. The performance was evaluated using accuracy and repeatability metrics. The methods were also compared with a fixed window size local binarization technique, which has been commonly used previously.

Results

The tested deep learning methods provided a good performance in terms of accuracy and repeatability. With the U-Net and SegNet networks showing >96% accuracy. All methods displayed a high level of repeatability relative to the ground truth. For analysis of the choroidal vascularity index (a commonly used metric derived from the binarized image), SegNet showed the closest agreement with the ground truth and high repeatability. The fixed window size showed a reduced accuracy compared to other methods.

Conclusions

Fully semantic networks such as U-Net and SegNet displayed excellent performance for the binarization task. These methods provide a useful approach for clinical and research applications of deep learning tools for the binarization of the choroid in OCT images.

Translational Relevance

Deep learning models provide a novel, robust solution to automatically binarize the choroidal tissue in OCT images.

The quantitative measurements of choroidal thickness and volume in diabetic retinopathy using optical coherence tomography and optical coherence tomography angiography; correlation with vision and foveal avascular zone

BACKGROUND

To represent choroidal thickness (CT) and choroidal volume (CV) databases in diabetic retinopathy (DR) patients and healthy control participants using optical coherence tomography (OCT) and enhanced depth imaging OCT (EDI-OCT). No study had evaluated CT at all main stages of diabetic retinopathy in a single study.

METHODS

The study included 176 eyes from 93 patients (39-80 years old; 42% females) who were divided into three groups based on DR severity and normal control group: 39 eyes no DR, 64 eyes NPDR, 33 eyes PDR, and 40 eyes normal control. The CT and CV were measured and statistically analyzed. Intra-observer and inter-observer coefficients of repeatability were calculated.

RESULTS

Subfoveal CT showed persistent thinning from normal group (322.50 ± 69.24) to no-diabetic retinopathy (NDR, 308.33 ± 74.45) to nonproliferative diabetic retinopathy (NPDR, 283.45 ± 56.50) group and then thickening as the patient progressed to proliferative diabetic retinopathy (PDR, 295.17 ± 95.69) (P = 0.087). A significant difference was found between the control group and the NDR, NPDR, and PDR groups in nearly all CT and CV of Early Treatment Diabetic Retinopathy Study macular subfields. Fasting blood sugar (FBS = 189.08 ± 51.3 mg/dl) and diabetes mellitus (DM) duration (13.6 ± 6.5 years) had no noticeable effect on CT. In patients with diabetes, the best-corrected visual acuity (BCVA), diabetic macular edema (DME), and foveal avascular zone (FAZ) were not affected by CT and CV.

CONCLUSIONS

The choroidal thickness decreases from the early stages of diabetic retinopathy up to the NPDR stage, with a subsequent modest rise in CT during the PDR stage. There was no correlation between FBS, diabetes duration, BCVA, DME, and FAZ, and CT.