A Comprehensive Review of Methods and Equipment for Aiding Automatic Glaucoma Tracking

Abstract

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.

Advancing glaucoma detection with convolutional neural networks: a paradigm shift in ophthalmology

“…This may include medical therapy, laser treatment, or surgical interventions, tailored to the specific needs of the individual. Early diagnosis allows for the monitoring of treatment efficacy and disease progression, facilitating timely adjustments in the treatment plans as required [ 31 , 32 ].…”

“…Through their automated feature extraction capabilities, CNNs excel at capturing both low-level and high-level features from medical images. This comprehensive understanding of visual information enables CNN to differentiate between healthy and glaucomatous conditions with unprecedented accuracy [ 32 ].…”

“…The use of CNNs in glaucoma diagnosis has shown promising results in achieving accurate and reliable classification of glaucomatous and healthy images. By leveraging deep learning algorithms and large datasets of labeled fundus images, CNNs have demonstrated their ability to automatically extract relevant features and detect subtle patterns associated with glaucoma [ 32 ]. The performance evaluation of CNN in glaucoma diagnosis involves assessing metrics such as accuracy, sensitivity, specificity, F1 score, and AUC-ROC.…”

“…By maintaining consistency in the architecture, training process, and evaluation metrics, researchers can communicate the limitations, strengths, and biases of their models. This transparency fosters trust among healthcare professionals, patients, and regulatory authorities, encouraging responsible and ethical use of CNN models for glaucoma management [ 32 - 34 ].…”

Advancements in Glaucoma Diagnosis: The Role of AI in Medical Imaging

“…Over the years, more sensitive tests have been developed to more reliably identify early loss of visual function in patients with glaucoma, and more sophisticated imaging devices have been created to identify the first signs of disease-induced structural damage to aid in precocious diagnosis. Among these devices, optical coherence tomography (OCT), laser scanning polarimetry, and confocal laser scanning ophthalmoscopy stand out [ 19 , 20 ]. Although devices have demonstrated a good ability to assist ophthalmologists in the diagnosis of glaucoma, few studies have specifically examined the use of such technologies early in the disease, making the early diagnosis of glaucoma a difficult task for specialists, even with the aid of sophisticated equipment [ 19 ].…”