Utility of noninvasive imaging modalities in a retina practice

Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis

The automatic diagnosis of various retinal diseases from fundus images is important to support clinical decision-making. However, developing such automatic solutions is challenging due to the requirement of a large amount of human-annotated data. Recently, unsupervised/self-supervised feature learning techniques receive a lot of attention, as they do not need massive annotations. Most of the current self-supervised methods are analyzed with single imaging modality and there is no method currently utilize multi-modal images for better results. Considering that the diagnostics of various vitreoretinal diseases can greatly benefit from another imaging modality, e.g., FFA, this paper presents a novel self-supervised feature learning method by effectively exploiting multi-modal data for retinal disease diagnosis. To achieve this, we first synthesize the corresponding FFA modality and then formulate a patient feature-based softmax embedding objective. Our objective learns both modality-invariant features and patient-similarity features. Through this mechanism, the neural network captures the semantically shared information across different modalities and the apparent visual similarity between patients. We evaluate our method on two public benchmark datasets for retinal disease diagnosis. The experimental results demonstrate that our method clearly outperforms other self-supervised feature learning methods and is comparable to the supervised baseline. Our code is available at GitHub.

Clinical applications of the retinal functional imager: A brief review

The advances in treating blinding conditions often depends on the development of new techniques that allows early detection, treatment, and follow-up of the disease. Functional changes often precede structural changes in many retinal disorders. Therefore, detecting these changes helps in early diagnosis and management, with the intention of preventing permanent morbidity. The Retinal Functional Imager (RFI) is a non-invasive imaging system that allows us to assess the various functional parameters of the retina. The RFI quantitatively measures the retinal blood-flow velocity, oxygen saturation, metabolic demand and generates a non-invasive capillary perfusion map that provides details similar to a fluorescein angiography. All of these parameters correlate with the health of the retina, and are known to get deranged in retinal disease. This article is a brief review of published literature on the clinical utility of the RFI.

The clinical relevance of visualising the peripheral retina

Recent developments in imaging technologies now allow the documentation, qualitative and quantitative evaluation of peripheral retinal lesions. As wide field retinal imaging, capturing both the central and peripheral retina up to 200° eccentricity, is becoming readily available the question is: what is it that we gain by imaging the periphery? Based on accumulating evidence it is clear that findings in the periphery do not always associate to those observed in the posterior pole. However, the newly acquired information may provide useful clues to previously unrecognised disease features and may facilitate more accurate disease prognostication. In this review, we explore the anatomy and physiology of the peripheral retina, focusing on how it differs from the posterior pole, recount the history of peripheral retinal imaging, describe various peripheral retinal lesions and evaluate the overall relevance of peripheral retinal findings to different diseases.

A Mini Review of Clinical and Research Applications of the Retinal Function Imager

PURPOSE

To review the clinical applications and diagnostic value of the retinal function imager (RFI), briefly compare RFI to other optical imaging devices, and to describe recent developments.

METHODS

The search words "Retinal Functional Imager," "optical imaging," "retina angiography," "avascular zone," "foveal avascular zone," and other closely related terms were used in PubMed to review current literature involving the RFI.

RESULTS

The functions of the RFI were utilized in over 44 microvascular studies, which reported that the microvasculature may alter in velocity, morphology, and oximetry when affected by a number of ocular, neurological, or systemic diseases. Recently developed automatic algorithms for noninvasive angiography of large retinal regions, segmenting vessels, measuring blood flow, blood velocity, vessel diameter, and oximetry may enhance the clinical applications of the RFI.

CONCLUSION

The RFI has been used to characterize the retinal microvasculature under various conditions of all prevalent retinal diseases in addition to some central nerve system (CNS) and systemic diseases. Applying the RFI in research and clinical settings should help earlier diagnosis, support disease prevention, and improve treatment management.

Noninvasive, High-Resolution Functional Macular Imaging in Subjects With Retinal Vein Occlusion

BACKGROUND AND OBJECTIVES

Several imaging modalities have been developed to characterize ischemia inherent in retinal vascular diseases. This study aims to predict the impact and to better establish the mechanisms of visual deterioration. A high-resolution functional imaging device is used, yielding quantitative data for macular blood flow and capillary network features in healthy eyes and in eyes with central retinal vein occlusion (CRVO) or branch retinal vein occlusion (BRVO).

PATIENTS AND METHODS

This prospective, cross-sectional, comparative case series measured blood flow velocities (BFVs) and noninvasive capillary perfusion maps (nCPMs) in macular vessels in patients with BRVO/CRVO and in healthy controls using the Retinal Function Imager (RFI; Optical Imaging, Rehovot, Israel).

RESULTS

Twenty-two eyes of 21 subjects were studied (eight with CRVO, five with BRVO, and nine controls). A significant decrease was observed in the BFVs of both arterioles and venules in the affected macular region of patients with CRVO and BRVO (2.84 ± 1.21 mm/s and 2.67 ± 1.43 mm/s in CRVO/BRVO arterioles, respectively, vs. 4.23 ± 1.04 mm/s in healthy controls, P < .001; and 1.64 ± 0.51 mm/s and 1.60 ± 0.41 mm/s in CRVO/BRVO venules, respectively, vs. 2.88 ± 0.93 mm/s in healthy controls, P < .001). BFVs in non-affected macular regions of patients with BRVO were not statistically different from BFVs in healthy eyes (3.84 ± 1.04 mm/s and 3.17 ± 1.39 mm/s in BRVO patients vs. 4.23 ± 1.04 mm/s and 2.88 ± 0.93 mm/s in healthy controls' arterioles and venules, respectively; P ≥ .1). nCPMs allowed high-resolution imaging of the macular vasculature and successfully demonstrated ischemic areas in the RVO groups.

CONCLUSIONS

The RFI provided high-resolution functional imaging of the retinal microvasculature and enabled quantitative measurement of BFVs in patients with RVO. Diminished flow velocity in arterioles and venules raises the possibility that RVO represents a panvascular compromise not confined to just venous stasis or its secondary arteriolar effects. The RFI offers potential to help with diagnosis and management of RVO cases. [Ophthalmic Surg Lasers Imaging Retina. 2017;48:799-809.].