Glaucoma, a disease that damages the optic nerve, is the leading cause of irreversible blindness worldwide. The early detection of glaucoma is a challenge, which in recent years has driven the study and application of Deep Learning (DL) techniques in the automatic classification of eye fundus images. Among these intelligent systems, Convolutional Neural Networks (CNNs) stand out, although alternatives have recently appeared, such as Vision Transformers (ViTs) or hybrid systems, which are also highly efficient in image processing. The question that arises in the face of so many emerging methods is whether all these new techniques are really more efficient for the problem of glaucoma diagnosis than the CNNs that have been used so far. In this article, we present a comprehensive comparative study of all these DL models in glaucoma detection, with the aim of elucidating which strategies are significantly better. Our main conclusion is that there are no significant differences between the efficiency of both DL strategies for the medical diagnostic problem addressed.

Glaucoma, a leading cause of blindness, damages the optic nerve, making early diagnosis challenging due to no initial symptoms. Fundus eye images taken with a non-mydriatic retinograph help diagnose glaucoma by revealing structural changes, including the optic disc and cup. This research aims to thoroughly analyze saliency maps in interpreting convolutional neural network decisions for diagnosing glaucoma from fundus images. These maps highlight the most influential image regions guiding the network’s decisions. Various network architectures were trained and tested on 739 optic nerve head images, with nine saliency methods used. Some other popular datasets were also used for further validation. The results reveal disparities among saliency maps, with some consensus between the folds corresponding to the same architecture. Concerning the significance of optic disc sectors, there is generally a lack of agreement with standard medical criteria. The background, nasal, and temporal sectors emerge as particularly influential for neural network decisions, showing a likelihood of being the most relevant ranging from 14.55% to 28.16% on average across all evaluated datasets. We can conclude that saliency maps are usually difficult to interpret and even the areas indicated as the most relevant can be very unintuitive. Therefore, its usefulness as an explanatory tool may be compromised, at least in problems such as the one addressed in this study, where the features defining the model prediction are generally not consistently reflected in relevant regions of the saliency maps, and they even cannot always be related to those used as medical standards.

Purpose: To analyze the progression of visual field loss using sector analysis of the cumulative defect curve and other procedures. Methods: Visual fields of 260 glaucomatous eyes were analyzed over 2.8 years (SD = 1.2) with at least five examinations (mean 6.9; SD = 2.0) using Octopus 311 perimeter and TOP strategy. The authors applied Threshold Noiseless Trend (TNT) program, which performs local filtering of threshold to reduce fluctuation, and analyzed five criteria: 1) a score based on significant progression of eight sectors of the cumulative defect curve (CD); 2) a score based on the presence of points (PO) with significant progression; 3) global progression (GL) of all local deviations; 4) progression of mean defect (MD); 5) progression of the square root of loss variance (sLV). The authors estimated false diagnoses (FD), randomly reordering examinations of each patient. An index of focality of progression (FI) was obtained. Results: sLV presented low sensitivity and GL low specificity. CD and PO presented twice the sensitivity of MD, often proving earlier indicators. The authors observed significant progression of some of the three criteria in 17.5% of the cases when MD 6 dB (FD=5.7%). Agreement between two criteria occurred in 6.8% of cases with MD 6 dB (FD=1.9%). Result reproducibility in successive examinations was observed in 9.9% of cases (FD=1.3%). Focality of progression increased with MD. Conclusions: PO and CD indicate suspected progression earlier than MD. Reproduction of results in successive examinations or agreement between criteria allows confirmation of progression.

The automatic location of the fovea is very useful for diagnosing retinal diseases. It is a complex problem for which different solutions have been proposed based on classical image processing and Deep Learning techniques. The method presented in this paper is based on histograms that combine spatial and color information in such a way that the spatial coordinates are incorporated into conventional color histograms as an additional dimension. The binarization of these histograms retains a considerable amount of relevant information from the original image, allowing them to be processed as if they were ordinary images. This approach to the problem results in a simple, fast and effective method for locating the fovea. Different experiments have been carried out with three popular sets of images: Messidor, REFUGE1 and DIARETDB1, and a comparison was made with other state-of-the-art techniques. Our results show that the proposed method, despite its simplicity, is capable of surpassing many of these techniques.

Glaucoma is one of the world leading causes of irreversible blindness. Early detection is essential to delay its progression and prevent vision loss. An accurate segmentation of the cup region in retinal fundus images is necessary to obtain relevant measurements for the detection of glaucoma. In recent years, multiple methods have been developed to automatically detect this region. All these methods are adjusted or trained using images that had been previously segmented by experts. In order to aid clinicians in performing this task, an interactive tool for the segmentation of the optic cup in stereo retinal fundus images using virtual reality has been developed. By using stereo images, the implemented virtual reality environment allows users to naturally perceive the three–dimensional structure of the optic cup region, which eases its segmentation compared to monocular images. The usage of the presented application was observed to increase accuracy of the delimitation, compared to using only two–dimensional fundus images, especially on areas with blood vessels.