Artificial intelligence techniques are now being applied in different medical solutions ranging from disease screening to activity recognition and computer-aided diagnosis. The combination of computer science methods and medical knowledge facilitates and improves the accuracy of the different processes and tools. Inspired by these advances, this paper performs a literature review focused on state-of-the-art glaucoma screening, segmentation, and classification based on images of the papilla and excavation using deep learning techniques. These techniques have been shown to have high sensitivity and specificity in glaucoma screening based on papilla and excavation images. The automatic segmentation of the contours of the optic disc and the excavation then allows the identification and assessment of the glaucomatous disease’s progression. As a result, we verified whether deep learning techniques may be helpful in performing accurate and low-cost measurements related to glaucoma, which may promote patient empowerment and help medical doctors better monitor patients.

Glaucoma is a silent disease that leads to vision loss or irreversible blindness. Current deep learning methods can help glaucoma screening by extending it to larger populations using retinal images. Low-cost lenses attached to mobile devices can increase the frequency of screening and alert patients earlier for a more thorough evaluation. This work explored and compared the performance of classification and segmentation methods for glaucoma screening with retinal images acquired by both retinography and mobile devices. The goal was to verify the results of these methods and see if similar results could be achieved using images captured by mobile devices. The used classification methods were the Xception, ResNet152 V2 and the Inception ResNet V2 models. The models’ activation maps were produced and analysed to support glaucoma classifier predictions. In clinical practice, glaucoma assessment is commonly based on the cup-to-disc ratio (CDR) criterion, a frequent indicator used by specialists. For this reason, additionally, the U-Net architecture was used with the Inception ResNet V2 and Inception V3 models as the backbone to segment and estimate CDR. For both tasks, the performance of the models reached close to that of state-of-the-art methods, and the classification method applied to a low-quality private dataset illustrates the advantage of using cheaper lenses.

Public databases for glaucoma studies contain color images of the retina, emphasizing the optic papilla. These databases are intended for research and standardized automated methodologies such as those using deep learning techniques. These techniques are used to solve complex problems in medical imaging, particularly in the automated screening of glaucomatous disease. The development of deep learning techniques has demonstrated potential for implementing protocols for large-scale glaucoma screening in the population, eliminating possible diagnostic doubts among specialists, and benefiting early treatment to delay the onset of blindness. However, the images are obtained by different cameras, in distinct locations, and from various population groups and are centered on multiple parts of the retina. We can also cite the small number of data, the lack of segmentation of the optic papillae, and the excavation. This work is intended to offer contributions to the structure and presentation of public databases used in the automated screening of glaucomatous papillae, adding relevant information from a medical point of view. The gold standard public databases present images with segmentations of the disc and cupping made by experts and division between training and test groups, serving as a reference for use in deep learning architectures. However, the data offered are not interchangeable. The quality and presentation of images are heterogeneous. Moreover, the databases use different criteria for binary classification with and without glaucoma, do not offer simultaneous pictures of the two eyes, and do not contain elements for early diagnosis.

Glaucoma is a chronic optic neuropathy characterized by irreversible damage to the retinal nerve fiber layer (RNFL), resulting in changes in the visual field (VC). Glaucoma screening is performed through a complete ophthalmological examination, using images of the optic papilla obtained in vivo for the evaluation of glaucomatous characteristics, eye pressure, and visual field. Identifying the glaucomatous papilla is quite important, as optical papillary images are considered the gold standard for tracking. Therefore, this article presents a review of the diagnostic methods used to identify the glaucomatous papilla through technology over the last five years. Based on the analyzed works, the current state-of-the-art methods are identified, the current challenges are analyzed, and the shortcomings of these methods are investigated, especially from the point of view of automation and independence in performing these measurements. Finally, the topics for future work and the challenges that need to be solved are proposed.

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.

Great advances in stitching high-quality retinal images have been made in recent years. On the other hand, very few studies have been carried out on low-resolution retinal imaging. This work investigates the challenges of low-resolution retinal images obtained by the D-EYE smartphone-based fundus camera. The proposed method uses homography estimation to register and stitch low-quality retinal images into a cohesive mosaic. First, a Siamese neural network extracts features from a pair of images, after which the correlation of their feature maps is computed. This correlation map is fed through four independent CNNs to estimate the homography parameters, each specializing in different corner coordinates. Our model was trained on a synthetic dataset generated from the Microsoft Common Objects in Context (MSCOCO) dataset; this work added an important data augmentation phase to improve the quality of the model. Then, the same is evaluated on the FIRE retina and D-EYE datasets for performance measurement using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The obtained results are promising: the average PSNR was 26.14 dB, with an SSIM of 0.96 on the D-EYE dataset. Compared to the method that uses a single neural network for homography calculations, our approach improves the PSNR by 7.96 dB and achieves a 7.86% higher SSIM score.