Diabetic retinopathy (DR) is a common chronic fundus disease, which has four different kinds of microvessel structure and microvascular lesions: microaneurysms (MAs), hemorrhages (HEs), hard exudates, and soft exudates. Accurate detection and counting of them are a basic but important work. The manual annotation of these lesions is a labor-intensive task in clinical analysis. To solve the problem, we proposed a novel segmentation method for different lesions in DR. Our method is based on a convolutional neural network and can be divided into encoder module, attention module, and decoder module, so we refer it as EAD-Net. After normalization and augmentation, the fundus images were sent to the EAD-Net for automated feature extraction and pixel-wise label prediction. Given the evaluation metrics based on the matching degree between detected candidates and ground truth lesions, our method achieved sensitivity of 92.77%, specificity of 99.98%, and accuracy of 99.97% on the e_ophtha_EX dataset and comparable AUPR (Area under Precision-Recall curve) scores on IDRiD dataset. Moreover, the results on the local dataset also show that our EAD-Net has better performance than original U-net in most metrics, especially in the sensitivity and F1-score, with nearly ten percent improvement. The proposed EAD-Net is a novel method based on clinical DR diagnosis. It has satisfactory results on the segmentation of four different kinds of lesions. These effective segmentations have important clinical significance in the monitoring and diagnosis of DR.

Research on an Intelligent Lightweight-Assisted Pterygium Diagnosis Model Based on Anterior Segment Images: Aims. The lack of primary ophthalmologists in China results in the inability of basic-level hospitals to diagnose pterygium patients. To solve this problem, an intelligent-assisted lightweight pterygium diagnosis model based on anterior segment images is proposed in this study. Methods. Pterygium is a common and frequently occurring disease in ophthalmology, and fibrous tissue hyperplasia is both a diagnostic biomarker and a surgical biomarker. The model diagnosed pterygium based on biomarkers of pterygium. First, a total of 436 anterior segment images were collected; then, two intelligent-assisted lightweight pterygium diagnosis models (MobileNet 1 and MobileNet 2) based on raw data and augmented data were trained via transfer learning. The results of the lightweight models were compared with the clinical results. The classic models (AlexNet, VGG16 and ResNet18) were also used for training and testing, and their results were compared with the lightweight models. A total of 188 anterior segment images were used for testing. Sensitivity, specificity, F1-score, accuracy, kappa, area under the concentration-time curve (AUC), 95 CI, size, and parameters are the evaluation indicators in this study. Results. There are 188 anterior segment images that were used for testing the five intelligent-assisted pterygium diagnosis models. The overall evaluation index for the MobileNet2 model was the best. The sensitivity, specificity, F1-score, and AUC of the MobileNet2 model for the normal anterior segment image diagnosis were 96.72, 98.43, 96.72, and 0976, respectively; for the pterygium observation period anterior segment image diagnosis, the sensitivity, specificity, F1-score, and AUC were 83.7, 90.48, 82.54, and 0.872, respectively; for the surgery period anterior segment image diagnosis, the sensitivity, specificity, F1-score, and AUC were 84.62, 93.50, 85.94, and 0.891, respectively. The kappa value of the MobileNet2 model was 77.64, the accuracy was 85.11, the model size was 13.5M, and the parameter size was 4.2M. Conclusion. This study used deep learning methods to propose a three-category intelligent lightweight-assisted pterygium diagnosis model. The developed model can be used to screen patients for pterygium problems initially, provide reasonable suggestions, and provide timely referrals. It can help primary doctors improve pterygium diagnoses, confer social benefits, and lay the foundation for future models to be embedded in mobile devices.

Pterygium is a common ocular surface disease. When pterygium significantly invades the cornea, it limits eye movement and impairs vision, which requires surgery to remove. It is medically recognized that when the width of the pterygium that invades the cornea is >3 mm, the patient can be treated with surgical resection. Owing to this, this study proposes a system for diagnosing and measuring the pathological progress of pterygium using deep learning methods, which aims to assist doctors in designing pterygium surgical treatment strategies. The proposed system only needs to input the anterior segment images of patients to automatically and efficiently measure the width of the pterygium that invades the cornea, and the patient's pterygium symptom status can be obtained. The system consists of three modules, including cornea segmentation module, pterygium segmentation module, and measurement module. Both segmentation modules use convolutional neural networks. In the pterygium segmentation module, to adapt the diversity of the pterygium's shape and size, an improved U-Net++ model by adding an Attention gate before each up-sampling layer is proposed. The Attention gates extract information related to the target, so that the model can pay more attention to the shape and size of the pterygium. The measurement module realizes the measurement of the width and area of the pterygium that invades the cornea and the classification of pterygium symptom status. In this study, the effectiveness of the proposed system is verified using datasets collected from the ocular surface diseases center at the Affiliated Eye Hospital of Nanjing Medical University. The results obtained show that the Dice coefficient of the cornea segmentation module and the pterygium segmentation module are 0.9620 and 0.9020, respectively. The Kappa consistency coefficient between the final measurement results of the system and the doctor's visual inspection results is 0.918, which proves that the system has practical application significance.

Purpose: To assess the value of automatic disc-fovea angle (DFA) measurement using the DeepLabv3+ segmentation model.Methods: A total of 682 normal fundus image datasets were collected from the Eye Hospital of Nanjing Medical University. The following parts of the images were labeled and subsequently reviewed by ophthalmologists: optic disc center, macular center, optic disc area, and virtual macular area. A total of 477 normal fundus images were used to train DeepLabv3+, U-Net, and PSPNet model, which were used to obtain the optic disc area and virtual macular area. Then, the coordinates of the optic disc center and macular center were obstained by using the minimum outer circle technique. Finally the DFA was calculated.Results: In this study, 205 normal fundus images were used to test the model. The experimental results showed that the errors in automatic DFA measurement using DeepLabv3+, U-Net, and PSPNet segmentation models were 0.76°, 1.4°, and 2.12°, respectively. The mean intersection over union (MIoU), mean pixel accuracy (MPA), average error in the center of the optic disc, and average error in the center of the virtual macula obstained by using DeepLabv3+ model was 94.77%, 97.32%, 10.94 pixels, and 13.44 pixels, respectively. The automatic DFA measurement using DeepLabv3+ got the less error than the errors that using the other segmentation models. Therefore, the DeepLabv3+ segmentation model was finally chosen to measure DFA automatically.Conclusions: The DeepLabv3+ segmentation model -based automatic segmentation techniques can produce accurate and rapid DFA measurements.

Congenital aniridia is a rare autosomal dominant congenital ocular disorder. Genetic studies suggest that heterozygous mutations in the developmental regulator PAX6 gene or the related regulatory regions leading to haploinsufficiency are the main cause of congenital aniridia. In this study, the clinical characteristics and pathogenic mutation of a four-generation Chinese family with congenital aniridia were investigated. All members recruited in this study underwent comprehensive ophthalmic examinations. Targeted gene capture sequencing and Sanger sequencing were performed to screen and confirm the candidate pathogenicity gene and its mutation. A multiple alignment of homologous sequences covering the identified mutation from different species was investigated, and the mutant protein structure was predicted using Swiss-Model. Additionally, the prediction of pathogenicity was analyzed using the ACMG Guidelines. Thirteen patients in this pedigree were diagnosed with congenital aniridia. A novel heterozygous frameshift mutation (c.391_398dupATACCAAG, p.Ser133Argfs*8) in exon 7 of the PAX6 gene was identified in all affected individuals in the family. This study demonstrates that this frameshift mutation of the PAX6 gene might be the causative genetic defect of congenital aniridia in this family. This mutation is predicted to cause the premature truncation of the PAX6 protein, leading to the functional haploinsufficiency of PAX6, which may be the major molecular mechanism underlying the aniridia phenotype. To the best of our knowledge, this is the first report of a novel pathogenic PAX6 gene variant c.391_398dupATACCAAG(p.Ser133Argfs*8) identified in a Chinese family with congenital aniridia.

Introduction: Congenital cataract (CC), defined as lens opacity present at birth or in early infancy, is a major cause of reversible childhood blindness and shows marked genetic heterogeneity. This study aimed to investigate the genetic basis of CC in a multigenerational Chinese family. Methods: A four-generation family with CC was clinically characterized. Whole-exome sequencing was performed in the proband, followed by stepwise variant filtering based on minor allele frequency, predicted functional impact, known CC-associated genes, and an autosomal dominant inheritance model. Candidate variants were annotated and classified according to ACMG guidelines. Sanger sequencing was used to validate variants in two additional affected relatives. Results: Two heterozygous missense variants were identified in known CC-associated genes: GJA3 c.776C > A (p.Ser259Tyr) and CRYBA1 c.346A > T (p.Ile116Phe). Both were extremely rare or absent in population databases and predicted to be damaging by multiple in silico tools. Sanger sequencing confirmed that the two variants co-occurred in all three affected family members tested, and no other rare, protein-altering variants meeting the filtering criteria were found in established cataract genes. Discussion: According to ACMG guidelines, both variants remain classified as variants of uncertain significance, but their rarity, predicted functional impact and consistent co-occurrence in affected individuals support them as strong candidate variants that may jointly contribute to CC in this family and expand the spectrum of GJA3- and CRYBA1-associated changes.