Computational Intelligent Techniques and Analysis on Automated Retinal Layer Segmentation and Detection of Retinal Diseases

The number of critically sick patients is increasing, placing pressure on the healthcare system, which is witnessing twice as many new cases as a year ago. Artificial intelligence (AI) technologies are advantageous to the health business because they offer better and more accurate autonomous sickness detection. Artificial intelligence applications are revolutionizing image classification and pattern recognition, two fields of commerce. Optical coherence tomography, or OCT, is a noninvasive imaging method that provides high resolution without causing pain to the patient. It is used to study the retina’s anatomy. Non-invasive images of a cross-sectional volume of tissues may be obtained using OCT. Picture segmentation techniques and structure classification strategies that have been found to be the most successful among the presently available research are discussed in this review study. This study presents a short overview of all of the most recent ways for applying machine learning algorithms to the problem of predicting retinal abnormalities based on OCT images. Readers will be able to find the algorithm that delivers the best degree of accuracy for retinal classification of infected and healthy eyes while also taking the least amount of processing time for layer segmentation using the techniques mentioned in this research study. As a consequence, accuracy improves while the amount of time needed decreases.