Retinal Nerve Fiber Layer Analysis Using Deep Learning to Improve Glaucoma Detection in Eye Disease Assessment

Recently, the development of a rapid detection approach for glaucoma has been widely proposed to assist medical personnel in detecting glaucoma disease thanks to the outstanding performance of artificial intelligence. In several glaucoma detectors, cup-to-disc ratio (CDR) and disc damage likelihood scale (DDLS) play roles as the major objects that are used to analyze glaucoma. However, using CDR and DDLS is quite difficult since every person has different characteristics (shape, size, etc.) of the optic disc and optic cup. To overcome this issue, we proposed an alternative way to detect glaucoma disease by analyzing the damage to the retinal nerve fiber layer (RNFL). Our proposed method is divided into two processes: (1) the pre-treatment process and (2) the glaucoma classification process. We started the pre-treatment process by removing unnecessary parts, such as the optic disc and blood vessels. Both parts are considered for removal since they might be obstacles during the analysis process. For the classification stages, we used nine deep-learning architectures. We evaluated our proposed method in the ORIGA dataset and achieved the highest accuracy of 92.88% with an AUC of 89.34%. This result is improved by more than 15% from the previous research work. Finally, it is expected that our model could help improve eye disease diagnosis and assessment.

Automated summary

Recently, the development of a rapid detection approach using artificial intelligence for detecting glaucoma disease has been proposed. Cup-to-disc ratio (CDR) and disc damage likelihood scale (DDLS) are commonly used for glaucoma analysis, but their variability in individuals makes it difficult. To solve this problem, a new method of glaucoma detection based on analyzing the damage to the retinal nerve fiber layer (RNFL) is proposed, with a pre-treatment process and a glaucoma classification process. With the use of nine deep-learning architectures, the proposed method achieves a highest accuracy of 92.88% and an AUC of 89.34% in the evaluation using the ORIGA dataset, showing improved results compared to previous research works. The model is expected to contribute to the improvement of eye disease diagnosis and assessment.