Search

The number of people suffering from ophthalmic diseases is increasing with the population aging. Many studies have been proposed to automatically identify diseases to reduce the risks of further retinal damage. However, most of existing methods mainly used a single type of dataset to solve the specific medical task, which is not clinically practical in the realworld scenarios. In this paper, we propose a multi-task deep learning network based on multi-types datasets to automatically recognise different ophthalmic diseases. Specifically, we first collect a multi-label dataset from the retinal fundus images and related diagnostic reports. Then, we propose a feature-fusion network to extract image and semantic retinal information from multi-types datasets. Finally, a multi-stream models is designed to integrate different specific features and realize the multiple disease detection. In this way, multi-types datasets based features are fully extracted in a multi-task learning manner. Experiments on our real-world dataset show that our proposed network significantly improve the classification performance of the model for ophthalmic diseases.

To investigate the error rate of automated choroidal segmentation and the effect of frame averaging on error rate.A horizontal B scan at the fovea was performed in patients having various retinochoroidal disorders using swept-source optical coherence tomography (OCT) with frame-averaging technique. Scanned images were classified into four morphological groups: normal from fellow eyes (NF ), normal from pathologic eyes (NP ), retinal abnormality (R) and retinochoroidal abnormality (RC) group. Choroidal segmentation was automatically performed using built-in software of a swept-source OCT device, and the error rate of choroidal segmentation was analysed.Qualified images for all four averaging types with different number of averaged frames were acquired in 89 eyes of 77 patients. Images of 12, 20, 24 and 33 eyes were classified as NF , NP , R and RC group, respectively. The choroidal segmentation error was detected in 1-2 images (8.3-16.7%) in the NF group, 3-6 images (15.0-30.0%) in the NP group, 4-8 images (16.7-33.3%) in the R group and 17-19 images (51.5-57.6%) in the RC group. The error rate was significantly higher in RC group than other groups (p 0.05). Increasing the number of frames for averaging showed no significant effect on the error rate in all groups (p 0.05).Automated choroidal segmentation showed a high error rate in images with choroidal abnormalities, and the averaging effect could not reduce the error rate significantly. Thus, further technological improvement is needed to increase the accuracy of the automated choroidal segmentation.

GACI (generalized arterial calcification of infancy) is a rare autosomal recessive disorder characterized by arterial and periarticular calcifications. Most children die in the first months of life of cardiovascular complications. Hypophosphatemic rickets (HR) resistant to medical treatment may complete the phenotype and is associated with a milder phenotype. This report discusses the case of a girl who presented neonatal ectopic periarticular calcifications with spontaneous regression, and then at the age of 3 years developed HR. There was no clinical improvement after treatment with calcitriol and phosphate, and correction of alkaline phosphatase induced the recurrence of periarticular and tissular calcifications : the treatment was reduced and the bone distortion treated by surgery. GACI diagnosis was confirmed by genetic analysis. At the age of 4.5 years, she developed a retinal abnormality and decreased radial pulse: these clinical signs are usually observed in pseudoxanthoma elasticum (PXE). It is now established that GACI and PXE belong to the same entity characterized by arterial and tissular calcifications of which this original case report is an illustration.

Purpose We investigated the outer retinal, RPE, and choroidal changes and the development of choroidal neovascularization (CNV) in fellow eyes of patients with unilateral polypoidal choroidal vasculopathy or aneurysmal type 1 neovascularization (PCV/AT1). Methods In this retrospective observational cohort study, 263 patients with unilateral PCV/AT1 were enrolled. Fundus photography, enhanced depth imaging optical coherence tomography, and indocyanine green angiography at baseline and follow-up were analyzed. Incidence and risk factors for the development of CNV were analyzed. Results In fellow eyes of unilateral PCV/AT1 cases, RPE and outer retinal abnormalities were observed in 222 (84%) eyes, and dilated Haller vessels (pachyvessel) were identified in the corresponding abnormality area in 157 (71%) eyes. Follow-up data were available for 233 patients. During a 27.6-month mean follow-up period, 20/233 (9%) eyes had CNV (12 PCV/AT1 and eight type 1 CNV). In 18 eyes (90%), CNV developed at the RPE or outer retinal abnormality areas accompanied by pachyvessel. A significantly higher risk for CNV was observed if RPE and outer retinal abnormalities were accompanied by pachyvessel (hazard ratio, 9.3; 95% confidence interval, 1.1-75.9, P = 0.037). Conclusions RPE and outer retinal abnormalities were common in fellow eyes of patients presenting with unilateral PCV/AT1. CNV developed in fellow eyes of 9% of patients, frequently in the areas with RPE and outer retinal abnormality accompanied by pachyvessel.

A few systemic diseases, for example, hypertension, diabetes, and vascular disorders will first affect the retinal vessels. When affected with these diseases, the retinal vessels show some sort of vascular changes according to the severity of the conditions. So, in order to diagnose this kind of diseases an efficient system that can detect the retinal abnormalities is required. This paper presents a hybrid approach for the automatic retinal vessel classification, vascular caliber estimation, and exudate detection in retinal images. The retinal vessel classification and caliber estimation is done by exploiting both visual and geometric features that enable discrimination between vein and arteries. Exudates are identified by extracting the yellow pixel level in the retinal image. Based on these three parameters, the retinal abnormality risk prediction model predicts whether the input retinal image is normal or abnormal.

INTRODUCTION: Macular edema is not a disease itself, but, a very common condition in most of the retinal diseases, such as diabetic retinopathy, retinal vein occlusion, hypertensive retinopathy, age-related macular edema, etc. and post-ocular surgery. OBJECTIVES: We have discussed how macular edema plays an important role in blindness in case of various retinal blood vascular diseases and post-ophthalmic surgery. We have analyzed vast state-of-the-art methods for retinal abnormality detection.METHODS: The proposed method uses a semi-automated macula segmentation approach and Local Binary Pattern features to train k-Nearest Neighbor classifier and performs binary classification. RESULTS: We have achieved 80% accuracy and 90% sensitivity in classifying normal and abnormal retina.CONCLUSION: We justified the notion that it will be beneficial to have a method that can analyse the macula region and alert if there is any abnormality near that region to prevent vision loss.

Diabetic retinopathy (DR), one of the most common causes of blindness, is a retinal abnormality caused by high glucose in diabetic patients that leads to micro vascular complications. DR has five levels of severity, i.e. no DR, mild non-proliferative diabetic retinopathy (NPDR), moderate NPDR, severe NPDR and proliferative diabetic retinopathy (PDR). Microaneurysms (MAs), the first sign of NPDR, can be used as a pre-indicator of DR. However, a manual assessment on digital colour fundus images conducted by ophthalmologists is time consuming. This paper introduces a new algorithm for the automated microaneurysms (MAs) detection in digital colour fundus images using matched filter. Generally, the algorithm consists of four phases, namely green band extraction, MAs and blood vessels isolation, MAs and blood vessels detection, and blood vessels removal. To validate the developed algorithm, the results are compared with their ground truths and annotations using ROI based validation. This algorithm obtains an average sensitivity, specificity, accuracy, and false positive number of 91.0603%, 99.9752%, 99.9752% and 256.44 pixels, respectively. This indicates that the proposed algorithm successfully detects microaneurysms and is able to be implemented in a system for DR mass screening purposes.

Systemic diseases like hypertension, diabetes and vascular disorders will affect the retinal vessels. Whenever affected with these kinds of diseases the retinal vessels show some sort of vascular variations according to the severity of the conditions. So in order to diagnose these diseases an efficient system that can detect the retinal abnormalities is required. For identifying the variations in retinal vessel caliber, AVR ratio is calculated. This paper presents a performance evaluation of various automatic retinal vessel classification systems and exudate identification system. The retinal vessel classification and caliber estimation can be done by exploiting either visual or geometric features that enable discrimination between vein and arteries.

Retinal abnormality associated with high blood pressure is known as hypertensive retinopathy (HR). This disease leads to permanent blindness so timely diagnosis and treatment of the disease is very important. Fundus image analysis is used to diagnose HR. An automated system for the early detection of HR proves to be useful for ophthalmologists and patients. In this paper, we propose an automated system for the detection of HR using arteriovenous (AV) ratio. The proposed system consists of novel method for classification of vessels as arteries and veins using new feature vector and hybrid classifier. This paper also presents a new method to calculate vessel width which is useful to measure AV ratio. The system detects whether fundus image contains HR or not using already calculated AV ratio. Two publicly available digital fundus image databases i.e. VICAVR and DRIVE are used for the testing of our proposed algorithm. Experimental results show the validity of our proposed algorithm.

The oral-facial-digital syndromes (OFDS) are a heterogeneous group. Recently, Gurrieri et al. [1992: Am J Med Genet 42:789-792] described a new OFDS characterised by typical oral, facial and digital abnormalities but distinguishable from previously reported OFDS by the presence of retinochoroidal lacunae of an apparently colobomatous origin. Toriello [1993: Clin Dysmorph 2:95-105] designated this possible new OFDS as Type IX. We describe a young woman presenting with oral, facial and digital anomalies and with the specific retinal abnormality reported by Gurrieri et al. [1992], thus confirming the existence of OFDS Type IX. As the patients of Gurrieri et al. [1992] were two affected brothers, they were unable to distinguish between autosomal and X-linked recessive inheritance. As our patient is an affected female, an autosomal recessive mode of inheritance is more likely.

Low electrooculographic (EOG) ratios have been reported in patients with seasonal affective disorder (SAD). This study was undertaken to replicate these results and to consider the effects of light therapy on the EOG in SAD patients. Sixteen outpatients with SAD and 16 age-, sex-, and medication-matched control subjects had EOG testing before and after 1 week of light therapy during the winter. The EOG ratios in the SAD patients were only marginally lower than those in the normal control subjects. These differences persisted after light therapy. Although the slightly decreased EOG ratios in SAD patients might have resulted from an artifact of test variability, drowsiness, or other confounding factors, the difference between patients and control subjects raises the possibility of retinal abnormality in SAD.

Objective Increased permeability of the cerebral microvasculature occurs during the treatment of diabetic ketoacidosis (DKA). Microvascular changes consistent with diabetic retinopathy have been reported prior to and after the treatment of DKA. This study evaluated the structural and functional aspects of the retina immediately following the correction of DKA. Methods Seven young patients had comprehensive ophthalmologic examinations, including fluorescein angiography, within 24 h after the correction of severe DKA (pH Results None of the patients had clinical, photographic, or angiographic evidence of a retinal abnormality. Conclusion The blood–retinal barrier (BRB) does not experience the same degree of perturbation as the blood–brain barrier (BBB) does and may be a protected site during the insult of DKA and its treatment. The greater stability of the retinal microvasculature may be due to the increased number of pericytes in the BRB in comparison with the BBB.

We report the findings of a new osteo-chondrodysplasia which does not fulfil the diagnostic criteria of any previously reported dysplasia. Severe short stature, resulting from spine and rhizomelic limb shortening, and cataracts are associated with radiological abnormalities of the spine, epiphyses and metaphyses. M.S. was born in 1973 in a village in Bangladesh. No measurements were made at birth but his mother says he was a little smaller than her three later born children. As a child he was always smaller than the other children but his short staturebecame more obvious with age and by the time he was 10 years old it was clear that he was severely short. When he went to the village school at the age of 5, poor vision was noted and subsequently he went to an ophthalmic service in Sylhet where bilateral cataracts were operated on with some visual improvement. No retinal abnormality was commented upon. He came with his mother and younger brothers to the UK in 1989 to join his father, who had been here inter...

To determine whether intraocular cooling using room-temperature irrigating solution can cause abnormal electroretinograph readings, we operated on six patients with premacular fibrosis and minimal retinal detachment, measuring the temperature in the vitreous cavity and using an electroretinographic monitor. The temperature in the vitreous cavity dropped to 27 degrees C to 28 degrees C after vitrectomies during which room-temperature solutions were used. This resulted in abnormal electroretinograph readings (markedly delayed peak times and reduced amplitudes). These results suggest that the routinely used room-temperature solution affects retinal function during vitrectomy; however, this functional change was reversible in patients having only minimal retinal abnormality.

Inherited retinal disorders are a fascinating group of diseases that are infrequently encountered in a routine ophthalmic practice. However, accurate diagnoses of these conditions are necessary to provide the genetic and prognostic counseling that may be very helpful to patients and their families. This book is a unique atlas that identifies the characteristic features of 72 inherited retinal disorders. The text is intended for the general ophthalmologist who may have the opportunity to examine a patient with an unusual case of inherited retinal abnormality. In addition, residents and fellows of ophthalmology will find this book a convenient reference source for an overview of the salient features of this collection of rare retinal diseases. "... a unique atlas that identifies the characteristic features of 72 inherited retinal disorders." The book is organized into three sections. Part 1 provides a brief review of the important principles of inheritance of human disease and genetic

Recordings were made from single retinal ganglion cell somas in cats whose visual cortical areas 17 and 18 were damaged on the day of birth or in adulthood. Neonatal lesions produced a 78 percent loss of X-cells in the retina, while lesions made in adulthood produced a 22 percent loss. Y-cells and W-cells were unaffected. This retinal abnormality needs to be considered when interpreting studies of behavioral deficits and neural mechanisms of recovery after damage to the visual cortex.

An electroretinographic (ERG) technique is described in which the relationship between scotopic b wave amplitude and stimulus light intensity is determined. The relative amplitude of scotopic to photopic responses is assessed by means of red light and flicker. The method is applied to the detection of ERG abnormalities in heterozygotes for X-linked retinitis pigmentosa. These have been found in only a proportion of cases. The ERG results can be used to suggest the nature of the retinal abnormality.

The retinal abnormality of fundus flavimaculatus can easily be diagnosed erroneously as tapetoretinal degeneration when one depends merely on oph-thalmoscopic findings, not performing psychophysical and electrophysiolo-gical testings (CARR, 1965). KLIEN & KRILL (1967) emphasized the usefulness of fluorescein fundus angiography for the differential diagnosis of fundus flavimaculatus. Several reports of this disease have been made in foreign countries, but very few in Japan (YURI, et al., 1969, OGINO, et al, 1970, WATANABE, et al., 1971).