Progress and challenges of in vivo flow cytometry and its applications in circulating cells of eyes.

Circulating inflammatory cells in eyes have emerged as early indicators of numerous major diseases, yet the monitoring of these cells remains an underdeveloped field. In vivo flow cytometry (IVFC), a noninvasive technique, offers the promise of real-time, dynamic quantification of circulating cells. However, IVFC has not seen extensive applications in the detection of circulating cells in eyes, possibly due to the eye's unique physiological structure and fundus imaging limitations. This study reviews the current research progress in retinal flow cytometry and other fundus examination techniques, such as adaptive optics, ultra-widefield retinal imaging, multispectral imaging, and optical coherence tomography, to propose novel ideas for circulating cell monitoring.

Implementing and evaluating a fully functional AI-enabled model for chronic eye disease screening in a real clinical environment.

BACKGROUND: Artificial intelligence (AI) has the potential to increase the affordability and accessibility of eye disease screening, especially with the recent approval of AI-based diabetic retinopathy (DR) screening programs in several countries. METHODS: This study investigated the performance, feasibility, and user experience of a seamless hardware and software solution for screening chronic eye diseases in a real-world clinical environment in Germany. The solution integrated AI grading for DR, age-related macular degeneration (AMD), and glaucoma, along with specialist auditing and patient referral decision. The study comprised several components: (1) evaluating the entire system solution from recruitment to eye image capture and AI grading for DR, AMD, and glaucoma; (2) comparing specialist's grading results with AI grading results; (3) gathering user feedback on the solution. RESULTS: A total of 231 patients were recruited, and their consent forms were obtained. The sensitivity, specificity, and area under the curve for DR grading were 100.00%, 80.10%, and 90.00%, respectively. For AMD grading, the values were 90.91%, 78.79%, and 85.00%, and for glaucoma grading, the values were 93.26%, 76.76%, and 85.00%. The analysis of all false positive cases across the three diseases and their comparison with the final referral decisions revealed that only 17 patients were falsely referred among the 231 patients. The efficacy analysis of the system demonstrated the effectiveness of the AI grading process in the study's testing environment. Clinical staff involved in using the system provided positive feedback on the disease screening process, particularly praising the seamless workflow from patient registration to image transmission and obtaining the final result. Results from a questionnaire completed by 12 participants indicated that most found the system easy, quick, and highly satisfactory. The study also revealed room for improvement in the AMD model, suggesting the need to enhance its training data. Furthermore, the performance of the glaucoma model grading could be improved by incorporating additional measures such as intraocular pressure. CONCLUSIONS: The implementation of the AI-based approach for screening three chronic eye diseases proved effective in real-world settings, earning positive feedback on the usability of the integrated platform from both the screening staff and auditors. The auditing function has proven valuable for obtaining efficient second opinions from experts, pointing to its potential for enhancing remote screening capabilities. TRIAL REGISTRATION: Institutional Review Board of the Hamburg Medical Chamber (Ethik-Kommission der Ärztekammer Hamburg): 2021-10574-BO-ff.

Smartphone Eye Examination: Artificial Intelligence and Telemedicine.

Background: The current medical scenario is closely linked to recent progress in telecommunications, photodocumentation, and artificial intelligence (AI). Smartphone eye examination may represent a promising tool in the technological spectrum, with special interest for primary health care services. Obtaining fundus imaging with this technique has improved and democratized the teaching of fundoscopy, but in particular, it contributes greatly to screening diseases with high rates of blindness. Eye examination using smartphones essentially represents a cheap and safe method, thus contributing to public policies on population screening. This review aims to provide an update on the use of this resource and its future prospects, especially as a screening and ophthalmic diagnostic tool. Methods: In this review, we surveyed major published advances in retinal and anterior segment analysis using AI. We performed an electronic search on the Medical Literature Analysis and Retrieval System Online (MEDLINE), EMBASE, and Cochrane Library for published literature without a deadline. We included studies that compared the diagnostic accuracy of smartphone ophthalmoscopy for detecting prevalent diseases with an accurate or commonly employed reference standard. Results: There are few databases with complete metadata, providing demographic data, and few databases with sufficient images involving current or new therapies. It should be taken into consideration that these are databases containing images captured using different systems and formats, with information often being excluded without essential detailing of the reasons for exclusion, which further distances them from real-life conditions. The safety, portability, low cost, and reproducibility of smartphone eye images are discussed in several studies, with encouraging results. Conclusions: The high level of agreement between conventional and a smartphone method shows a powerful arsenal for screening and early diagnosis of the main causes of blindness, such as cataract, glaucoma, diabetic retinopathy, and age-related macular degeneration. In addition to streamlining the medical workflow and bringing benefits for public health policies, smartphone eye examination can make safe and quality assessment available to the population.

An empirical study of preprocessing techniques with convolutional neural networks for accurate detection of chronic ocular diseases using fundus images.

Chronic Ocular Diseases (COD) such as myopia, diabetic retinopathy, age-related macular degeneration, glaucoma, and cataract can affect the eye and may even lead to severe vision impairment or blindness. According to a recent World Health Organization (WHO) report on vision, at least 2.2 billion individuals worldwide suffer from vision impairment. Often, overt signs indicative of COD do not manifest until the disease has progressed to an advanced stage. However, if COD is detected early, vision impairment can be avoided by early intervention and cost-effective treatment. Ophthalmologists are trained to detect COD by examining certain minute changes in the retina, such as microaneurysms, macular edema, hemorrhages, and alterations in the blood vessels. The range of eye conditions is diverse, and each of these conditions requires a unique patient-specific treatment. Convolutional neural networks (CNNs) have demonstrated significant potential in multi-disciplinary fields, including the detection of a variety of eye diseases. In this study, we combined several preprocessing approaches with convolutional neural networks to accurately detect COD in eye fundus images. To the best of our knowledge, this is the first work that provides a qualitative analysis of preprocessing approaches for COD classification using CNN models. Experimental results demonstrate that CNNs trained on the region of interest segmented images outperform the models trained on the original input images by a substantial margin. Additionally, an ensemble of three preprocessing techniques outperformed other state-of-the-art approaches by 30% and 3%, in terms of Kappa and F 1 scores, respectively. The developed prototype has been extensively tested and can be evaluated on more comprehensive COD datasets for deployment in the clinical setup.

Detection and Mosaicing Techniques for Low-Quality Retinal Videos.

Ideally, to carry out screening for eye diseases, it is expected to use specialized medical equipment to capture retinal fundus images. However, since this kind of equipment is generally expensive and has low portability, and with the development of technology and the emergence of smartphones, new portable and cheaper screening options have emerged, one of them being the D-Eye device. When compared to specialized equipment, this equipment and other similar devices associated with a smartphone present lower quality and less field-of-view in the retinal video captured, yet with sufficient quality to perform a medical pre-screening. Individuals can be referred for specialized screening to obtain a medical diagnosis if necessary. Two methods were proposed to extract the relevant regions from these lower-quality videos (the retinal zone). The first one is based on classical image processing approaches such as thresholds and Hough Circle transform. The other performs the extraction of the retinal location by applying a neural network, which is one of the methods reported in the literature with good performance for object detection, the YOLO v4, which was demonstrated to be the preferred method to apply. A mosaicing technique was implemented from the relevant retina regions to obtain a more informative single image with a higher field of view. It was divided into two stages: the GLAMpoints neural network was applied to extract relevant points in the first stage. Some homography transformations are carried out to have in the same referential the overlap of common regions of the images. In the second stage, a smoothing process was performed in the transition between images.

Characteristics of p.Gln368Ter Myocilin Variant and Influence of Polygenic Risk on Glaucoma Penetrance in the UK Biobank.

PURPOSE: MYOC (myocilin) mutations account for 3% to 5% of primary open-angle glaucoma (POAG) cases. We aimed to understand the true population-wide penetrance and characteristics of glaucoma among individuals with the most common MYOC variant (p.Gln368Ter) and the impact of a POAG polygenic risk score (PRS) in this population. DESIGN: Cross-sectional population-based study. PARTICIPANTS: Individuals with the p.Gln368Ter variant among 77 959 UK Biobank participants with fundus photographs (FPs). METHODS: A genome-wide POAG PRS was computed, and 2 masked graders reviewed FPs for disc-defined glaucoma (DDG). MAIN OUTCOME MEASURES: Penetrance of glaucoma. RESULTS: Two hundred individuals carried the p.Gln368Ter heterozygous genotype, and 177 had gradable FPs. One hundred thirty-two showed no evidence of glaucoma, 45 (25.4%) had probable/definite glaucoma in at least 1 eye, and 19 (10.7%) had bilateral glaucoma. No differences were found in age, race/ethnicity, or gender among groups (P > 0.05). Of those with DDG, 31% self-reported or had International Classification of Diseases codes for glaucoma, whereas 69% were undiagnosed. Those with DDG had higher medication-adjusted cornea-corrected intraocular pressure (IOPcc) (P < 0.001) vs. those without glaucoma. This difference in IOPcc was larger in those with DDG with a prior glaucoma diagnosis versus those not diagnosed (P < 0.001). Most p.Gln368Ter carriers showed IOP in the normal range (≤21 mmHg), although this proportion was lower in those with DDG (P < 0.02) and those with prior glaucoma diagnosis (P < 0.03). Prevalence of DDG increased with each decile of POAG PRS. Individuals with DDG demonstrated significantly higher PRS compared with those without glaucoma (0.37 ± 0.97 vs. 0.01 ± 0.90; P = 0.03). Of those with DDG, individuals with a prior diagnosis of glaucoma had higher PRS compared with undiagnosed individuals (1.31 ± 0.64 vs. 0.00 ± 0.81; P < 0.001) and 27.5 times (95% confidence interval, 2.5-306.6) adjusted odds of being in the top decile of PRS for POAG. CONCLUSIONS: One in 4 individuals with the MYOC p.Gln368Ter mutation demonstrated evidence of glaucoma, a substantially higher penetrance than previously estimated, with 69% of cases undetected. A large portion of p.Gln368Ter carriers, including those with DDG, have IOP in the normal range, despite similar age. Polygenic risk score increases disease penetrance and severity, supporting the usefulness of PRS in risk stratification among MYOC p.Gln368Ter carriers.

A smartphone based method for mouse fundus imaging.

Noninvasive in vivo imaging of the mouse retina is essential for eye research. However, imaging the mouse fundus is challenging due to its small size and requires specialized equipment, maintenance, and training. These issues hinder the routine evaluation of the mouse retina. In this study, we developed a noncontact imaging system consisting of a smartphone, a 90D condensing lens, a homemade light diaphragm, a tripod, and a Bluetooth remote. With minimal training, examiners were able to capture fundus images from the mouse retina. We also found that fundus images captured using our system from wild type mice, mice with laser-induced retinal injury, and a mouse model of retinitis pigmentosa showed a quality similar to those captured using a commercial fundus camera. These images enabled us to identify normal structures and pathological changes in the mouse retina. Additionally, fluorescein angiography was possible with the smartphone system. We believe that the smartphone imaging system is low cost, simple, accessible, easy to operate, and suitable for the routine screening and examination of the mouse eye.

Clinically useful smartphone ophthalmic imaging techniques.

Imaging devices in ophthalmology are numerous, and most of them are sophisticated and specialized for specific regions of the eye. In addition, these are fixed and involve close interaction of the patient and the examiner; therefore, simple, portable and tele facility-imbibed imaging tools can be considered optimal alternatives to routine exercises. In the last 10 years, utility of smartphones in ophthalmology is being continuously explored to unearth their potential benefits. In this direction, a smartphone device with/without simple attachments has been noted to aid in detailed, high-quality imaging of the ocular adnexa, cornea, angle, iris, lens, optic disc, and the retina including its periphery. In addition, such utility has also been extended in strabismology workup and intraocular pressure measurements. Hence, using these clinician friendly tools and techniques or by devising newer and more comprehensive tool kits, ophthalmic care can be well-managed with apt use of technology. Also, the smartphone companies are encouraged to collaborate with the medical experts to endeavor more, and help and serve the people better.

Comparison of two ultra-widefield imaging for detecting peripheral retinal breaks requiring treatment.

AIM: To compare the sensitivity of Optomap Panoramic 200 and Clarus 500 in detecting peripheral retinal breaks that required treatment. METHODS: This prospective study enrolled consecutive patients undergoing laser for treatment-requiring peripheral retinal breaks from May 2019 to July 2019. The patients first underwent indirect ophthalmoscopy examination with scleral indentation by a retinal consultant and then ultra-widefield imaging by a single trained technician on Optomap 200 and Clarus 500 in all nine ocular gazes. The images were analysed by two independent investigators to look for the number and location of the breaks. The sensitivity of each platform was calculated as the number of treatment-requiring breaks identified by the system divided by the number of breaks identified on clinical examination. RESULTS: Clinical examination of 49 eyes (41 patients) showed 116 treatment-requiring breaks. Overall sensitivity for identifying such breaks for Optomap and Clarus was 80.2% (n = 93) and 74.1% (n = 86) respectively (p = 0.274). The sensitivities in superior (p = 0.665), temporal (p = 0.146) and inferior (p = 0.889) quadrants were statistically similar for both the platforms. The sensitivity of Optomap was slightly higher than Clarus in emmetropic (p = 0.046) and phakic (p = 0.061) eyes, but similar in myopic (p = 0.448) and pseudophakic (p = 0.191) eyes. CONCLUSION: The ability to detect treatment-requiring retinal breaks is similar for both Optomap and Clarus systems.

Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study.

PURPOSE: To investigate the detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus imaging system (Optos) with convolutional neural network technology. METHODS: This study included 1500 Optos color images for tessellated fundus confirmation and peripheral retinal lesion (lattice degeneration, retinal breaks, and retinal detachment) assessment. Three retinal specialists evaluated all images and proposed the reference standard when an agreement was achieved. Then, 722 images were used to train and verify a combined deep-learning system of 3 optimal binary classification models trained using seResNext50 algorithm with 2 preprocessing methods (original resizing and cropping), and a test set of 189 images were applied to verify the performance compared to the reference standard. RESULTS: With optimal preprocessing approach (original resizing method for lattice degeneration and retinal detachment, cropping method for retinal breaks), the combined deep-learning system exhibited an area under curve of 0.888, 0.953, and 1.000 for detection of lattice degeneration, retinal breaks, and retinal detachment respectively in tessellated eyes. The referral accuracy of this system was 79.8% compared to the reference standard. CONCLUSION: A deep-learning system is feasible to detect lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field images. And this system may be considered for screening and telemedicine.

Low retinal toxicity of intravitreal carboplatin associated with good retinal tumour control in transgenic murine retinoblastoma.

BACKGROUND: Retinoblastoma is a rare intraocular malignancy in children. Current treatments have many adverse effects. New therapeutic approaches like intravitreal injections of chemotherapies are currently being developed but their toxicities need to be evaluated on animal models. This study compares the efficacy and toxicity of intravitreal melphalan, topotecan and carboplatin, alone or in combination (sequential administration), in the LHBetaTag retinoblastoma mice. METHODS: Mice were divided into nine groups: control, carboplatin 1.5 and 4 µg, melphalan 0.1 and 1 µg, topotecan 0.1 and 1 µg, carboplatin 4 µg/topotecan 0.1 µg and melphalan 1 µg/topotecan 0.1 µg. The follow-up was performed using fundus imaging and optical coherence tomography combined with histopathological analysis. Absence of tumour and presence of calcified tumours were the criteria for therapeutic response assessment. Ocular complications were assessed after four weekly injections. Retinal toxicity was defined by the decrease of retinal thickness and of the number of retinal layers. RESULTS: Topotecan was inactive on retinal tumours. Melphalan (1 µg) led to a complete tumour control in 91.7% of eyes. Carboplatin strongly decreased the tumour burden (85.7-93.8% of eyes without retinal tumour). The intravitreal injection itself led to ocular complications (25% of media opacities and 45.7% of retinal detachment). Only melphalan at 1 µg showed a strong retinal toxicity. The two combinations showed a good efficacy in reducing the number of eyes with retinal tumours with a reduced retinal toxicity. CONCLUSIONS: This preclinical study suggests that intravitreal injection of carboplatin has a low toxicity and could be evaluated in clinical practice to treat patients suffering from retinoblastoma.

Quality and Feasibility of Automated Digital Retinal Imaging in the Emergency Department.

BACKGROUND: Emergency physicians (EPs) frequently evaluate patients at risk for sight-threatening conditions but may have difficulty performing direct ophthalmoscopy effectively. Digital fundus photography offers a potential alternative. OBJECTIVE: We sought to assess the performance of an automated digital retinal imaging platform in a real-world emergency department. METHODS: We performed a prospective, observational study of emergency department patients who were at risk for acute, nontraumatic, posterior segment pathology. Photographs were obtained using an automated digital retinal camera and were subsequently reviewed by an ophthalmologist. We recorded the number of attempts required, total time required, patient comfort, and findings on EP-performed direct ophthalmoscopy, if performed. RESULTS: Of 123 participants completing the study, 93 (75.6%) had ≥1 eye with a diagnostically useful image, while 29 (23.6%) had no photographs of diagnostic value. The mean number of attempts required to obtain images was 1.45 (range 1-3) and the mean elapsed time required to complete photography was 109.6 s. The mean patient comfort score was 4.6 on a 5-point scale, where 5 was the most comfortable. Direct ophthalmoscopy was performed by an emergency department provider for 19 (15.4%) patients. Acute findings were noted in 14 patients during expert review of fundus photographs, though in only 2 of these cases was direct ophthalmoscopy performed by an EP with only 1 finding ultimately identified correctly. CONCLUSIONS: Automated digital imaging of the ocular fundus is rapidly performed, is well tolerated by patients, and can be used to obtain diagnostic quality images without the use of pharmacologic pupillary dilation in most emergency department patients who are at risk for acute posterior segment pathology.

Alterations of retinal vessels in patients with sepsis.

To compare the retinal vasculature of septic patients with age-matched healthy volunteers. This is a single-centre prospective observational study from January 2018 to May 2019 in a third-level ICU. We performed a single fundus imaging using a hand-held digital fundus camera in patients with sepsis or septic shock (n = 40) during the first 24 h after ICU admission and compared these data with age-matched healthy controls (n  =  20). Semi-automated image analysis was performed. The average retinal arteriolar and venular caliber were calculated and summarized as the central retinal arteriolar equivalent (CRAE) and central retinal venular equivalent (CRVE). Arteriole:venular ratio (AVR) was defined as the ratio of CRAE:CRVE. The vascular length density of segmented retinal vessels was = defined as the skeletonized vessel area/total area × 100%. Median CRAE of septic patients was significantly higher in comparison to healthy controls (165[149-187] vs. 146[142-158] µm, p = 0.002). However, median CRVE and AVR of septic patients did not differ with healthy controls (247[223-282] vs. 244[215-272], p = 0.396 and 0.64[0.58-0.74] vs. 0.61[0.55-0.68], p = 0.145) respectively. Patients with sepsis showed a significant decrease in retinal vascular length density compared with healthy subjects (p < 0.001). Retinal observation using a hand-held fundus imaging device showed signs of arteriolar vasodilation with decreased vascular density in septic patients in comparison to healthy controls.

[A Simplifed Model Eye for Testing Fundus Imaging Device].

Based on the Gullstrand I model eye, a simplified model eye for testing fundus imaging device is designed. The model eye can reach the following requirements:(1) The refractive characteristics of the ocular refractive tissue are simulated, and the equivalent focal length in air is 17 mm; (2) The differences between relative refractive index differences of the adjacent materials of the simplified model eye and relative refractive index differences of any adjacent two layers (cornea and aqueous humor, aqueous humor and lens, lens and vitreous body) of the Gullstrand I model eye are not more than 1%; (3) In the case of the incident aperture diameter of 3 mm, the differences of radii of the diffuse spots formed by the paraxial light and the axial light are not more than 15%; (4) The differences of angles of chief ray and tangent line of the fundus are not more than 1°; (5) In the case of the incident aperture diameter of 3 mm, the differences of MTF values of the near axis light are not more than 0.1. The simplified model eye can be expected to be used for testing fundus imaging device instead of the test method in ISO 10940:2009 Ophthalmic instruments-Fundus cameras.

Diabetic retinopathy screening programme utilising non-mydriatic fundus imaging in slum populations of New Delhi, India.

OBJECTIVES: To develop and implement a community-based programme for screening of diabetic retinopathy (DR) in urban populations of Delhi. METHODS: Known diabetics (KDs) aged 40 years and older were identified through house-to-house surveys, volunteers and publicity. All KDs were referred to DR screening camps organised locally where procedures included brief medical history, ocular examination and non-mydriatic fundus photography using portable handheld camera. Fundal images were graded on the spot by trained optometrists for DR. Patients with DR were referred to tertiary centre for management. RESULTS: A total of 11 566 KDs were identified, of whom 9435 (81.6%) visited DR screening camps and 8432 (89.4%) had DR gradable images. DR was identified in 13.5% of subjects; 351 cases were mild NPDR, 567 moderate, 92 severe. Seventy-seven had PDR, and 49 had DME, and 2.7% of participants were blind (presenting visual acuity <3/60 in better eye). Non-use of lifestyle management, presence of systemic complications, BMI <18.5 kg/m2 , disease duration of >5 years and uncontrolled diabetes were associated with increased odds of DR. All cases with DR were referred, and 420 (37%) successful referrals to base hospital were observed. CONCLUSION: The programme of creating awareness about DR, identifying KDs and optometrist-led DR screening using non-mydriatic fundus camera based in slums was successful.

Retinal findings in a patient of French ancestry with CABP4-related retinal disease.

INTRODUCTION: CABP4-related retinal dysfunction is a cone-rod synaptic transmission disorder with electronegative electroretinogram (ERG) waveform. It is a rare retinal dysfunction that can be classified into the incomplete form of congenital stationary night blindness. Absent foveal reflex and overall foveal thinning were previously reported, but in most cases the fundus appearance was described as nearly normal. We report here peculiar macular changes in a patient of French ancestry harbouring CABP4 mutations. METHODS: Complete ocular examination and full-field ERG were performed at the initial presentation and follow-up. Multimodal fundus imagining, including spectral-domain optical coherence tomography, colour, infrared reflectance and short-wavelength autofluorescence photographs, was performed during follow-up visits. RESULTS: A 7-month-old infant was addressed to our department for visual unresponsiveness and nystagmus. ERG had an electronegative waveform, even for light-adapted stimuli, thus supporting the diagnosis of photoreceptor-bipolar cell transmission disorder. Genetic investigations discovered a compound heterozygous mutation in CABP4: c.646C > T, p.Arg216*/c.673C > T, p.Arg225*. Multimodal fundus imaging, performed at follow-up visits, showed fine radial folds at the vitreomacular interface and dark foveal dots in both eyes. Optic coherence tomography revealed a focal foveal ellipsoid zone gap. DISCUSSION: Initial presentation was misleading with Leber congenital amaurosis. The electronegative ERG waveform reoriented the genetic investigations and thus establishing a correct diagnosis. To the best of our knowledge, the peculiar fundus changes observed in our patient were never reported before. We hypothesized that a foveal ellipsoid zone interruption discovered in our patient could reflect mostly a cone dysfunction. It was unclear whether the fine radial folds in both maculae were linked with high hyperopia or were an intrinsic feature of the retinal disease. CONCLUSION: CABP4-related retinal disease is a cone-rod system disorder with possible foveal abnormalities.

Changes in retinal vessels related to varicocele: a pilot investigation.

The aim of this study was to investigate whether retinal vasculature changes had occurred (retinal artery diameter, retinal vein diameter and artery/vein ratio) in patients with varicocele. This pilot study included 50 healthy subjects with any eye disease apart from slight refractive errors and 55 patients with varicocele. Retinal arteriolar and venular diameters were measured and summarised as central retinal arteriolar equivalent (CRAE) and central retinal venular equivalent (CRVE). Retinal microvascular diameters and the arteriolar-to-venular ratio (AVR) were assessed with a digital retinal camera. All measurements and calculations were performed using a computer-based program. The mean CRAE value was 151.8 ± 3.6 µm in the study group and 150.4 ± 4.5 µm in the control group. Mean CRVE value was 209.4 ± 5.9 µm in the study group and 200.1 ± 8.7 µm in the control group. AVR was found 0.72 ± 0.02 in the study group and 0.75 ± 0.03 in the control group. There were significant differences between groups in terms of CRVE and AVR. There were no significant differences between groups in terms of CRAE. The results of this study showed that the patients with varicocele showed significant changes on retinal vascular diameter.

A simple method for panretinal imaging with the slit lamp.

Slit lamp biomicroscopy of the retina with a convex lens is a key procedure in clinical practice. The methods presented enable ophthalmologists to adequately image large and peripheral parts of the fundus using a video-slit lamp and freely available stitching software. A routine examination of the fundus with a slit lamp and a +90 D lens is recorded on a video film. Later, sufficiently sharp still images are identified on the video sequence. These still images are imported into a freely available image-processing program (Hugin, for stitching mosaics together digitally) and corresponding points are marked on adjacent still images with some overlap. Using the digital stitching program Hugin panoramic overviews of the retina can be built which can extend to the equator. This allows to image diseases involving the whole retina or its periphery by performing a structured fundus examination with a video-slit lamp. Similar images with a video-slit lamp based on a fundus examination through a hand-held non-contact lens have not been demonstrated before. The methods presented enable those ophthalmologists without high-end imaging equipment to monitor pathological fundus findings. The suggested procedure might even be interesting for retinological departments if peripheral findings are to be documented which might be difficult with fundus cameras.

Assessing spectral effectiveness in color fundus photography for deep learning classification of retinopathy of prematurity.

Significance: Retinopathy of prematurity (ROP) poses a significant global threat to childhood vision, necessitating effective screening strategies. This study addresses the impact of color channels in fundus imaging on ROP diagnosis, emphasizing the efficacy and safety of utilizing longer wavelengths, such as red or green for enhanced depth information and improved diagnostic capabilities. Aim: This study aims to assess the spectral effectiveness in color fundus photography for the deep learning classification of ROP. Approach: A convolutional neural network end-to-end classifier was utilized for deep learning classification of normal, stage 1, stage 2, and stage 3 ROP fundus images. The classification performances with individual-color-channel inputs, i.e., red, green, and blue, and multi-color-channel fusion architectures, including early-fusion, intermediate-fusion, and late-fusion, were quantitatively compared. Results: For individual-color-channel inputs, similar performance was observed for green channel (88.00% accuracy, 76.00% sensitivity, and 92.00% specificity) and red channel (87.25% accuracy, 74.50% sensitivity, and 91.50% specificity), which is substantially outperforming the blue channel (78.25% accuracy, 56.50% sensitivity, and 85.50% specificity). For multi-color-channel fusion options, the early-fusion and intermediate-fusion architecture showed almost the same performance when compared to the green/red channel input, and they outperformed the late-fusion architecture. Conclusions: This study reveals that the classification of ROP stages can be effectively achieved using either the green or red image alone. This finding enables the exclusion of blue images, acknowledged for their increased susceptibility to light toxicity.

Clinical Applications and Future Directions of Smartphone Fundus Imaging.

The advent of smartphone fundus imaging technology has marked a significant evolution in the field of ophthalmology, offering a novel approach to the diagnosis and management of retinopathy. This review provides an overview of smartphone fundus imaging, including clinical applications, advantages, limitations, clinical applications, and future directions. The traditional fundus imaging techniques are limited by their cost, portability, and accessibility, particularly in resource-limited settings. Smartphone fundus imaging emerges as a cost-effective, portable, and accessible alternative. This technology facilitates the early detection and monitoring of various retinal pathologies, including diabetic retinopathy, age-related macular degeneration, and retinal vascular disorders, thereby democratizing access to essential diagnostic services. Despite its advantages, smartphone fundus imaging faces challenges in image quality, standardization, regulatory considerations, and medicolegal issues. By addressing these limitations, this review highlights the areas for future research and development to fully harness the potential of smartphone fundus imaging in enhancing patient care and visual outcomes. The integration of this technology into telemedicine is also discussed, underscoring its role in facilitating remote patient care and collaborative care among physicians. Through this review, we aim to contribute to the understanding and advancement of smartphone fundus imaging as a valuable tool in ophthalmic practice, paving the way for its broader adoption and integration into medical diagnostics.