CNN with Multiple Inputs for Automatic Glaucoma Assessment Using Fundus Images

In the area of ophthalmology, glaucoma affects an increasing number of people. It is a major cause of blindness. Early detection avoids severe ocular complications such as glaucoma, cystoid macular edema, or diabetic proliferative retinopathy. Intelligent artificial intelligence has been confirmed beneficial for glaucoma assessment. In this paper, we describe an approach to automate glaucoma diagnosis using funds images. The setup of the proposed framework is in order: The Bi-dimensional Empirical Mode Decomposition (BEMD) algorithm is applied to decompose the Regions of Interest (ROI) to components (BIMFs+residue). CNN architecture VGG19 is implemented to extract features from decomposed BEMD components. Then, we fuse the features of the same ROI in a bag of features. These last very long; therefore, Principal Component Analysis (PCA) are used to reduce features dimensions. The bags of features obtained are the input parameters of the implemented classifier based on the Support Vector Machine (SVM). To train the built models, we have used two public datasets, which are ACRIMA and REFUGE. For testing our models, we have used a part of ACRIMA and REFUGE plus four other public datasets, which are RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF. The overall precision of 98.31%, 98.61%, 96.43%, 96.67%, 95.24%, and 98.60% is obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, by using the model trained on REFUGE. Again an accuracy of 98.92%, 99.06%, 98.27%, 97.10%, 96.97%, and 96.36% is obtained in the ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, using the model training on ACRIMA. The experimental results obtained from different datasets demonstrate the efficiency and robustness of the proposed approach. A comparison with some recent previous work in the literature has shown a significant advancement in our proposal.

Factors Associated with Changes in Peripapillary Retinal Nerve Fibre Layer Thickness in Healthy Myopic Eyes

Myopic people face an elevated risk of primary open angle glaucoma. Changes in the fundus in people with high myopia often lead to misdiagnosis of glaucoma, as this condition has many clinical signs in common with myopia, making the diagnosis of glaucoma more challenging. Compared to reduction of the visual field, a decrease in retinal nerve fibre layer (RNFL) thickness occurs earlier in glaucoma, which is widely considered useful for distinguishing between these conditions. With the development of optical coherence tomography (OCT), RNFL thickness can be measured with good reproducibility. According to previous studies, this variable is not only affected by axial length but also related to the patient’s age, gender, ethnicity, optic disc area, and retinal blood flow in myopia. Herein, we intend to summarize the factors relevant to the RNFL in myopia to reduce the false-positive rate of glaucoma diagnosis and facilitate early prevention of myopia.

MulTiNet: Multimodal Neural Networks for Glaucoma Based on Transfer Learning

Background: Being one of the most serious causes of irreversible blindness, glaucoma has many subtypes and complex symptoms. In clinic, doctors usually need to use a variety of medical images for diagnosis. Optical Coherence Tomography (OCT), Visual Field (VF) , Fundus Photosexams (FP) and Ultrasonic BioMicroscope (UBM) are widely-used and complementary techniques for diagnosing glaucoma.Methods: At present, the field of intelligent diagnosis of glaucoma is limited by two major problems. One is the small number of data sets, and the other is the low diagnostic accuracy of Single-Modal Modal. In order to solve the above two problems, we have done the following work. First, we construct DualSY glaucoma multimodal data set. The four most important subtypes of glaucoma are discussed in this article which are Primary Open Angle Glaucoma (POAG), Primary Angle Closure Glaucoma (PACG), Primary Angle Closure Suspect (PACS) and Primary Angle Closure (PAC). Each patient in the DualSY data set contains more than five medical images, as shown in the figure 4.And DualSY are labeled with image-level multi-labels. Second, We propose a new Multi-Modal classification network for glaucoma, which is a multiclass classification model with various medical images of glaucoma patients and text information as input. The network structure consists of three main branches to deal with patient metadata, domain-based glaucoma features and medical images. Transfer learning method is introduced into this paper due to the small number of medical image data sets. The flowchart is shown in Figure 5.Result: Our method on glaucoma diagnosis outperforms state-of-the-art methods. A promising average result of overall accuracy (ACC) of 94.7% is obtained. Our data set outperformed most data sets in glaucoma diagnosis with an accuracy of 87.8%.Conclusions: The results suggest that medical images such as Heidelberg OCT and three-dimensional fundus photos used in this paper can better express the high-level information of glaucoma and our modal greatly improve the accuracy of glaucoma diagnosis. At the same time, this data set has great potential, and we continue to study this data.

Clinical Features of the Fellow Eyes of Children with Unilateral Facial Port-Wine Stains and Ipsilateral Glaucoma

Purpose: To investigate the clinical features of non-affected fellow eyes in patients with unilateral facial port-wine stain (PWS) and ipsilateral secondary glaucoma.Methods: We performed a retrospective analysis of the medical records of 35 patients with unilateral facial PWS glaucoma and those of controls (35 subjects without both facial PWS and glaucoma) between September 1996 and May 2020. We noted patients’ age at the glaucoma diagnosis (for unilateral facial PWS glaucoma patients) or at the initial examination (for controls), cup-to-disc ratio (CDR), and intraocular pressure (IOP). We compared the clinical features between the glaucoma-free eyes in patients with unilateral facial PWS glaucoma and the controls.Results: The mean age at the glaucoma diagnosis for unilateral facial PWS glaucoma patients was 0.56 ± 0.99 years (range, 0.08-4). The mean IOP of the glaucoma-free eyes was 16.68 ± 5.73 mmHg (range, 9-22.9), and the mean CDR was 0.37 ± 0.14 (range, 0.15-0.80) at glaucoma diagnosis. The mean IOP of the glaucoma-free eyes was 14.14 ± 6.29 mmHg (range, 8.1-26.7), and the mean CDR was 0.37 ± 0.12 (range, 0.26-0.82) at final examination. When comparing glaucoma-free eyes of the unilateral facial PWS glaucoma patients with the control group (mean age, 11.2 ± 7.4 years), the mean CDR was significantly greater (0.37 ± 0.12 vs. 0.30 ± 0.08; p = 0.014) but there was no significant difference in the mean IOP (14.14 ± 6.29 mmHg vs. 14.57 ± 2.49 mmHg; p = 0.712).Conclusions: The glaucoma-free eyes of unilateral facial PWS glaucoma patients showed greater CDR compared to the non-facial PWS and non-glaucoma controls. Additional longitudinal studies are needed to investigate the clinical course of those eyes, whether the risk of developing glaucoma is increased.

Efficient Feature Descriptor using Gabor Filter and Principal Component Analysis for Glaucoma Diagnosis

An automated Computer Aided Diagnosis (CAD) system for glaucoma diagnosis using fundus images is developed. The various glaucoma image classification schemes using the supervised and unsupervised learning approaches are reviewed. The research paper involves three stages of glaucoma disease diagnosis. First, the pre-processing stage the texture features of the fundus image is recorded with a two-dimensional Gabor filter at various sizes and orientations. The image features are generated using higher order statistical characteristics, and then Principal Component Analysis (PCA) is used to select and reduce the dimension of the image features. For the performance study, the Gabor filter based features are extracted from the RIM-ONE and HRF database images, and then Support Vector Machine (SVM) classifier is used for classification. Final stage utilizes the SVM classifier with the Radial Basis Function (RBF) kernel learning technique for the efficient classification of glaucoma disease with accuracy 90%.

Do Hispanic Patients Who Require a Medical Interpreter Understand the Severity of Their Glaucoma Diagnosis?

Background and Hypothesis: Glaucoma is a group of progressive optic neuropathies characterized by a degeneration of retinal ganglion cells with characteristic changes in the visual field. The Los Angeles Latino Eye Study (LALES) is the largest and most recent study to determine the prevalence of open-angle glaucoma in Hispanics; reported at nearly 5%. Between 2010 – 2019, Hispanic patients accounted for more than half of the United States population growth, reaching a record of 60.6 million Hispanics living in the United States. With an influx of Hispanic’s migrating to the United States, there is an increased need for medical interpreters to assist medical professionals in encounters with Hispanic patients. The success of a medical encounter relies on a multitude of factors, but when a medical interpreter is involved, the stakes are even higher. We hypothesize that Hispanic speaking patients will have lower rates of understanding their glaucoma diagnosis and severity, in comparison to English speaking patients due to gaps in translation provided by medical interpreters. Project Methods: Native Spanish and native English-speaking patients from the Eskenazi Health Eye Clinic were recruited via phone, reminding them of their upcoming eye appointment and their eligibility to participate in the study. Interested patients were provided with information regarding the study and consent materials at the start of the medical encounter. Participants who consented were administered the survey at the end of their medical encounter, in their preferred language, in person, at the clinic. Results: This is an ongoing prospective study. Potential Impact: This study will determine if medical interpreters successfully relay all the necessary information regarding a Hispanic patient’s glaucoma diagnosis. This study could also provide a partial explanation as to why there is a high no show rate and high medication noncompliance rate within the Eskenazi Health Eye Clinic Hispanic population.