A Novel Automatic Method to Estimate Visual Acuity and Analyze the Retinal Vasculature in Retinal Vein Occlusion Using Swept Source Optical Coherence Tomography Angiography

Disentangled Representation Learning for OCTA Vessel Segmentation With Limited Training Data

Optical coherence tomography angiography (OCTA) is an imaging modality that can be used for analyzing retinal vasculature. Quantitative assessment of en face OCTA images requires accurate segmentation of the capillaries. Using deep learning approaches for this task faces two major challenges. First, acquiring sufficient manual delineations for training can take hundreds of hours. Second, OCTA images suffer from numerous contrast-related artifacts that are currently inherent to the modality and vary dramatically across scanners. We propose to solve both problems by learning a disentanglement of an anatomy component and a local contrast component from paired OCTA scans. With the contrast removed from the anatomy component, a deep learning model that takes the anatomy component as input can learn to segment vessels with a limited portion of the training images being manually labeled. Our method demonstrates state-of-the-art performance for OCTA vessel segmentation.

Intraoperative bowel perfusion quantification with hyperspectral imaging: a guidance tool for precision colorectal surgery

BACKGROUND

Poor anastomotic perfusion can cause anastomotic leaks (AL). Hyperspectral imaging (HSI), previously validated experimentally, provides accurate, real-time, contrast-free intestinal perfusion quantification. Clinical experience with HSI is limited. In this study, HSI was used to evaluate bowel perfusion intraoperatively.

METHODS

Fifty-two patients undergoing elective colorectal surgeries for neoplasia (n = 40) or diverticular disease (n = 12), were enrolled. Intestinal perfusion was assessed with HSI (TIVITA®, Diaspective Vision, Am Salzhaff, Germany). This device generates a perfusion heat map reflecting the tissue oxygen saturation (StO2) amount. Prior to anastomose creation, the clinical transection line (CTL) was highlighted on the proximal bowel and imaged with HSI. Upon StO2 heat map evaluation, the hyperspectral transection line (HTL) was identified. In case of CTL/HTL discrepancy > 5 mm, the bowel was always resected at the HTL. HSI outcomes were compared to the clinical ones.

RESULTS

AL occurred in one patient who underwent neoadjuvant radiochemotherapy and ultralow anterior resection for rectal cancer. HSI assessment was feasible in all patients, and StO2-values were significantly higher at proximal segments than distal ones. Twenty-six patients showed CTL/HTL discrepancy, and these patients had a lower mean StO2 (54.55 ± 21.30%) than patients without discrepancy (65.10 ± 21.30%, p = 0.000). Patients undergoing neoadjuvant radiochemotherapy showed a lower StO2 (51.41 ± 23.41%) than non-neoadjuvated patients (60.51 ± 24.98%, p = 0.010).

CONCLUSION

HSI is useful in detecting intraoperatively marginally perfused segments, for which the clinical appreciation is unreliable. Intestinal vascular supply is lower in patients undergoing neoadjuvant radiochemotherapy, and this novel finding together with the clinical impact of HSI perfusion quantification deserves further investigation in larger trials.

Estimation of best corrected visual acuity based on deep neural network

In this study, we investigated a convolutional neural network (CNN)-based framework for the estimation of the best-corrected visual acuity (BCVA) from fundus images. First, we collected 53,318 fundus photographs from the Gyeongsang National University Changwon Hospital, where each fundus photograph is categorized into 11 levels by retrospective medical chart review. Then, we designed 4 BCVA estimation schemes using transfer learning with pre-trained ResNet-18 and EfficientNet-B0 models where both regression and classification-based prediction are taken into account. According to the results of the study, the predicted BCVA by CNN-based schemes is close to the actual value such that 94.37% of prediction accuracy can be achieved when 3 levels of difference can be tolerated during prediction. The mean squared error and [Formula: see text] score were measured as 0.028 and 0.654, respectively. These results indicate that the BCVA can be predicted accurately for extreme cases, i.e., the level of BCVA is close to either 0.0 or 1.0. Moreover, using the Guided Grad-CAM, we confirmed that the macula and the blood vessel surrounding the macula are mainly utilized in the prediction of BCVA, which validates the rationality of the CNN-based BCVA estimation schemes since the same area is also exploited during the retrospective medical chart review. Finally, we applied the t-distributed stochastic neighbor embedding to examine the characteristics of CNN-based BCVA estimation schemes. The developed BCVA estimation schemes can be employed to obtain the objective measurement of BVCA as well as the medical screening of people with poor access to medical care through smartphone-based fundus imaging.

Retinal and choroidal microvascular alterations in Behcet’s disease without ocular manifestations: A systematic review and meta-analysis

Purpose

We performed a systematic review and meta-analysis to examine the microvascular alterations in non-ocular Behcet’s disease (BD) using optical coherence tomography angiography (OCTA).

Methods

A comprehensive search was performed in Pubmed, Embase and Cochrane databases for eligible studies from inception to February 2022. Detailed clinical demographics were extracted from each study by two independent reviewers. The weighted mean difference (WMD) and 95% confidence intervals (CI) were used to compare the OCTA parameters between non-ocular BD and healthy controls. Stata 12.0 was adopted to conduct statistical analyses.

Results

Ten cross-sectional studies involving 386 eyes in non-ocular BD and 418 eyes in healthy volunteers were ultimately included in the present analysis. When considering superficial capillary plexus (SCP) and deep capillary plexus (DCP), no significant differences of vessel densities in the whole enface image, fovea and perifovea were evaluated between two groups. Significantly reduced parafoveal vessel density of SCP was observed in non-ocular BD in comparison with healthy group (WMD = −1.33, 95%CI: −1.78, −0.89; I2 = 0.6%), while slightly decreased parafoveal vessel density was assessed in DCP (WMD = −1.47, 95%CI: −3.30, 0.35; I2 = 89.3%). Significantly increasing foveal avascular zone (FAZ) area was observed in non-ocular BD when compared to healthy controls (WMD = 0.11, 95%CI: 0.03, 0.19; I2 = 95.3%). There was no significant difference in flow area of choriocapillaris between non-ocular BD and control group (WMD = 0.06, 95%CI: −0.19, 0.32; I2 = 0%).

Conclusion

Based on current analysis, our results demonstrated significantly lower parafoveal vessel density of SCP and lager FAZ area in full vasculature in non-ocular BD. The retinal microvascular alterations appear before the emergence of ocular manifestations.

Systematic Trial Registration

[https://www.crd.york.ac.uk/PROSPERO/], identifier [CRD42021244856].

Topological Data Analysis for Eye Fundus Image Quality Assessment

The objective of this work is to perform image quality assessment (IQA) of eye fundus images in the context of digital fundoscopy with topological data analysis (TDA) and machine learning methods. Eye health remains inaccessible for a large amount of the global population. Digital tools that automize the eye exam could be used to address this issue. IQA is a fundamental step in digital fundoscopy for clinical applications; it is one of the first steps in the preprocessing stages of computer-aided diagnosis (CAD) systems using eye fundus images. Images from the EyePACS dataset were used, and quality labels from previous works in the literature were selected. Cubical complexes were used to represent the images; the grayscale version was, then, used to calculate a persistent homology on the simplex and represented with persistence diagrams. Then, 30 vectorized topological descriptors were calculated from each image and used as input to a classification algorithm. Six different algorithms were tested for this study (SVM, decision tree, k-NN, random forest, logistic regression (LoGit), MLP). LoGit was selected and used for the classification of all images, given the low computational cost it carries. Performance results on the validation subset showed a global accuracy of 0.932, precision of 0.912 for label "quality" and 0.952 for label "no quality", recall of 0.932 for label "quality" and 0.912 for label "no quality", AUC of 0.980, F1 score of 0.932, and a Matthews correlation coefficient of 0.864. This work offers evidence for the use of topological methods for the process of quality assessment of eye fundus images, where a relatively small vector of characteristics (30 in this case) can enclose enough information for an algorithm to yield classification results useful in the clinical settings of a digital fundoscopy pipeline for CAD.

Quantitative analysis of retinal vessel density and thickness changes in diabetes mellitus evaluated using optical coherence tomography angiography: a cross-sectional study

Background

Diabetic retinopathy is the most common microvascular complication of diabetes; however, early changes in retinal microvessels are difficult to detect clinically, and a patient’s vision may have begun to deteriorate by the time a problem is identified. Optical coherence tomography angiography (OCTA) is an innovative tool for observing capillaries in vivo. The aim of this study was to analyze retinal vessel density and thickness changes in patients with diabetes.

Methods

This was a retrospective, observational cross-sectional study. Between August 2018 and February 2019, we collected OCTA data from healthy participants and diabetics from the First Affiliated Hospital of Harbin Medical University. Analyzed their retinal vessel density and thickness changes.

Results

A total of 97 diabetic patients with diabetes at different severity stages of diabetic retinopathy and 85 controls were involved in the experiment. Diabetic patients exhibited significantly lower retinal VD (particularly in the deep vascular complexes), thickening of the neurosensory retina, and thinning of the retinal pigment epithelium compared with controls. In the control group, nondiabetic retinopathy group and mild diabetic retinopathy group, superficial VD was significantly correlated with retinal thickness (r = 0.3886, P < 0.0001; r = 0.3276, P = 0.0019; r = 0.4614, P = 0.0024, respectively).

Conclusions

Patients with diabetes exhibit ischemia of the retinal capillaries and morphologic changes in vivo prior to vision loss. Therefore, OCTA may be useful as a quantitative method for the early detection of diabetic retinopathy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12886-021-01988-2.

Retinal applications of swept source optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA)

The advent of optical coherence tomography (OCT) revolutionized both clinical assessment and research of vitreoretinal conditions. Since then, extraordinary advances have been made in this imaging technology, including the relatively recent development of swept-source OCT (SS-OCT). SS-OCT enables a fast scan rate and utilizes a tunable swept laser, thus enabling the incorporation of longer wavelengths than conventional spectral-domain devices. These features enable imaging of larger areas with reduced motion artifact, and a better visualization of the choroidal vasculature, respectively. Building on the principles of OCT, swept-source OCT has also been applied to OCT angiography (SS-OCTA), thus enabling a non-invasive in depth-resolved imaging of the retinal and choroidal microvasculature. Despite their advantages, the widespread use of SS-OCT and SS-OCTA remains relatively limited. In this review, we summarize the technical details, advantages and limitations of SS-OCT and SS-OCTA, with a particular emphasis on their relevance for the study of retinal conditions. Additionally, we comprehensively review relevant studies performed to date to the study of retinal health and disease, and highlight current gaps in knowledge and opportunities to take advantage of swept source technology to improve our current understanding of many medical and surgical chorioretinal conditions. We anticipate that SS-OCT and SS-OCTA will continue to evolve rapidly, contributing to a paradigm shift to more widespread adoption of new imaging technology to clinical practice.

Automatic Visual Acuity Estimation by Means of Computational Vascularity Biomarkers Using Oct Angiographies

Optical Coherence Tomography Angiography (OCTA) constitutes a new non-invasive ophthalmic image modality that allows the precise visualization of the micro-retinal vascularity that is commonly used to analyze the foveal region. Given that there are many systemic and eye diseases that affect the eye fundus and its vascularity, the analysis of that region is crucial to diagnose and estimate the vision loss. The Visual Acuity (VA) is typically measured manually, implying an exhaustive and time-consuming procedure. In this work, we propose a method that exploits the information of the OCTA images to automatically estimate the VA with an accurate error of 0.1713.