Purpose To quantitatively evaluate the inter-annotator variability of clinicians tracing the contours of anatomical layers of the iridocorneal angle on digital gonio photographs, thus providing a baseline for the validation of automated analysis algorithms. Methods Using a software annotation tool on a common set of 20 images, five experienced ophthalmologists highlighted the contours of five anatomical layers of interest: iris root (IR), ciliary body band (CBB), scleral spur (SS), trabecular meshwork (TM), and cornea (C). Inter-annotator variability was assessed by (1) comparing the number of times ophthalmologists delineated each layer in the dataset; (2) quantifying how the consensus area for each layer (i.e., the intersection area of observers’ delineations) varied with the consensus threshold; and (3) calculating agreement among annotators using average per-layer precision, sensitivity, and Dice score. Results The SS showed the largest difference in annotation frequency (31%) and the minimum overall agreement in terms of consensus size (∼28% of the labeled pixels). The average annotator's per-layer statistics showed consistent patterns, with lower agreement on the CBB and SS (average Dice score ranges of 0.61–0.7 and 0.73–0.78, respectively) and better agreement on the IR, TM, and C (average Dice score ranges of 0.97–0.98, 0.84–0.9, and 0.93–0.96, respectively). Conclusions There was considerable inter-annotator variation in identifying contours of some anatomical layers in digital gonio photographs. Our pilot indicates that agreement was best on IR, TM, and C but poorer for CBB and SS. Translational Relevance This study provides a comprehensive description of inter-annotator agreement on digital gonio photographs segmentation as a baseline for validating deep learning models for automated gonioscopy.
Tackling visual impairment remains an important public health issue. Due to limited resources and the increasing demand on hospital eye services (HES), delivery of quality eye care within the community is essential. Training of clinical ophthalmic specialists and allied health-care professionals in the detection and management of common eye conditions can thus help to reduce the burden of eye disease and improve prognostic outcomes. Digital imaging has become a useful tool in facilitating eye-care delivery in both the community and hospital setting. In the last decade, the advent of electronic image exchange via a centralized referral unit in Scotland has revolutionized screening for ophthalmic disease, referrals, and shared care between community and HES clinicians. A government-led initiative known as the Scottish Eyecare Integration Project introduced electronic transfer of digital images within referrals from community optometrists to HES, which greatly reduced outpatient waiting times and improved patient satisfaction. The catalogue of live clinical information and digital images that resulted from the project led to the creation of a virtual learning platform through the University of Edinburgh. Participating professionals involved in eye care have interactive discussions about common eye conditions by sharing digital images of cases and investigations on a global online platform. This has received worldwide attention and inspired the creation of other university courses, e-learning platforms in eye-health education, and shared-care schemes in the screening of eye disease. We show that digital ophthalmology plays a vital role in the integration of community and HES partnership in delivery of patient care and in facilitating eye-health education to a global audience.
ObjectiveTo develop and test a deep learning (DL) model for semantic segmentation of anatomical layers of the anterior chamber angle (ACA) in digital gonio-photographs.Methods and analysisWe used a pilot dataset of 274 ACA sector images, annotated by expert ophthalmologists to delineate five anatomical layers: iris root, ciliary body band, scleral spur, trabecular meshwork and cornea. Narrow depth-of-field and peripheral vignetting prevented clinicians from annotating part of each image with sufficient confidence, introducing a degree of subjectivity and features correlation in the ground truth. To overcome these limitations, we present a DL model, designed and trained to perform two tasks simultaneously: (1) maximise the segmentation accuracy within the annotated region of each frame and (2) identify a region of interest (ROI) based on local image informativeness. Moreover, our calibrated model provides results interpretability returning pixel-wise classification uncertainty through Monte Carlo dropout.ResultsThe model was trained and validated in a 5-fold cross-validation experiment on ~90% of available data, achieving ~91% average segmentation accuracy within the annotated part of each ground truth image of the hold-out test set. An appropriate ROI was successfully identified in all test frames. The uncertainty estimation module located correctly inaccuracies and errors of segmentation outputs.ConclusionThe proposed model improves the only previously published work on gonio-photographs segmentation and may be a valid support for the automatic processing of these images to evaluate local tissue morphology. Uncertainty estimation is expected to facilitate acceptance of this system in clinical settings.
Background: Plasma fibroblast skin tightening treatment is a relatively novel and growing minimally invasive aesthetic skin procedure. The treatment claims to rejuvenate skin by improving facial lines, wrinkles and skin pigmentation associated with photo-ageing. The skin is often anaesthetised prior to the procedure with topical creams such as EMLA (Eutectic mixture of local anaesthetics). We present the first case of bilateral chemical eye injury following plasma fibroblast skin tightening treatment secondary to EMLA cream. EMLA cream was inadvertently administered to both eyes in preparation for the treatment. Case presentation: A patient was referred from the emergency department to a tertiary ophthalmology centre with bilateral exquisite eye pain, inability to open the eyes, photosensitivity and reduced vision. She underwent cosmetic plasma fibroblast skin tightening treatment at her local salon four hours earlier. She was found to have bilateral alkali chemical eye injuries with significant diffuse corneal epithelial loss. The injury was thought to be caused by inadvertent ocular exposure to EMLA cream, which was used in preparation for the plasma fibroblast skin tightening treatment. She was treated with topical antibiotics and achieved satisfactory recovery. Conclusion: This case report highlights a possible complication following plasma fibroblast skin tightening treatment. We lay emphasis on the importance identifying chemical injury and recommend that medication attention should be sought if there is any concern.
Introduction: Pre-school orthoptic vision screening (POVS) was implemented by the Scottish government and is a standardised assessment to promote early detection of visual problems in children. The target conditions are amblyopia, refractive errors and strabismus. We present the preliminary findings for the first three years of the screening program. Methods: The data from POVS was collected retrospectively. The data includes screening years 2013 to 2016 inclusive. Data was collected from each health board in Scotland. We report the coverage, referral rate, true positives and positive predictive values. Results: A total of 167,962 children were due to have vision screening over the 3 screening years included in this paper. This figure does not include the children that opted out of the eye test (mean opt-out rate 1.8%) and children that already attend the hospital eye service (mean already attend rate 3.1%). The POVS program had a mean coverage of 85.5%, ranging from 63.7% to 94.8% between health boards. Over the 3 year screening period, the mean referral rate was found to be 17.9%. The mean true positive rate was 88.9%, and the mean positive predictive value was 86.9%. Conclusion: The Scottish data set on pre-school orthoptic vision screening has shown excellent mean coverage. A consistently high true positive rate over the three screening years demonstrates it is a sensitive screening program, which is essential for the detection of visual problems in children.
A patient presented with left upper eyelid swelling and ptosis. The MRI reported a cyst with proteinaceous content. On surgical excision of the cyst, a rigid gas permeable (RGP) contact lens was found. The RGP lens was encapsulated within the upper eyelid soft tissue. It was later revealed that the patient experienced childhood trauma while wearing RGP contact lenses 28 years previously. The patient assumed that the RGP lens fell out and was lost; however, it can be inferred that the lens migrated into the eyelid and resided there asymptomatically for 28 years.
True isolated sixth nerve palsy as the initial presentation of multiple sclerosis (MS) is rare. MS is a chronic inflammatory, immune-mediated disease of the central nervous system. This is the most common cause of neurological disability in young adults. Common symptoms include acute episodes of muscle weakness, altered sensation, balance and gait disturbances, visual loss and bladder dysfunction.Diagnosis of MS is supported with the incidence of symptomatic clinical episodes with subsequent cross-sectional imaging to confirm radiological lesions that are disseminated in space and time.In the following report, we discuss the case of a woman in her 30s who presented to ophthalmology with a sixth nerve palsy in the absence of ocular or systemic disease. This is the first presentation of MS, a rare clinical event.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.