Two-step hierarchical neural network for classification of dry age-related macular degeneration using optical coherence tomography images

Min Hu; Bin Wu; Di Lu; Jing Xie; Yiqiang Chen; Zhikuan Yang; Weiwei Dai

doi:10.3389/fmed.2023.1221453

Two-step hierarchical neural network for classification of dry age-related macular degeneration using optical coherence tomography images

Front Med (Lausanne). 2023 Jul 19:10:1221453. doi: 10.3389/fmed.2023.1221453. eCollection 2023.

Authors

Min Hu^#¹, Bin Wu^#², Di Lu³, Jing Xie¹, Yiqiang Chen⁴, Zhikuan Yang⁵, Weiwei Dai^{1

6}

Affiliations

¹ Changsha Aier Eye Hospital, Changsha, China.
² Department of Retina, Shenyang Aier Excellence Eye Hospital, Shenyang, China.
³ Department of Retina, Shenyang Aier Optometry Hospital, Shenyang, China.
⁴ Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.
⁵ Aier Institute of Optometry and Vision Science, Changsha, China.
⁶ Anhui Aier Eye Hospital, Anhui Medical University, Hefei, China.

^# Contributed equally.

Abstract

Purpose: The aim of this study is to apply deep learning techniques for the development and validation of a system that categorizes various phases of dry age-related macular degeneration (AMD), including nascent geographic atrophy (nGA), through the analysis of optical coherence tomography (OCT) images.

Methods: A total of 3,401 OCT macular images obtained from 338 patients admitted to Shenyang Aier Eye Hospital in 2019-2021 were collected for the development of the classification model. We adopted a convolutional neural network (CNN) model and introduced hierarchical structure along with image enhancement techniques to train a two-step CNN model to detect and classify normal and three phases of dry AMD: atrophy-associated drusen regression, nGA, and geographic atrophy (GA). Five-fold cross-validation was used to evaluate the performance of the multi-label classification model.

Results: Experimental results obtained from five-fold cross-validation with different dry AMD classification models show that the proposed two-step hierarchical model with image enhancement achieves the best classification performance, with a f1-score of 91.32% and a kappa coefficients of 96.09% compared to the state-of-the-art models. The results obtained from the ablation study demonstrate that the proposed method not only improves accuracy across all categories in comparison to a traditional flat CNN model, but also substantially enhances the classification performance of nGA, with an improvement from 66.79 to 81.65%.

Conclusion: This study introduces a novel two-step hierarchical deep learning approach in categorizing dry AMD progression phases, and demonstrates its efficacy. The high classification performance suggests its potential for guiding individualized treatment plans for patients with macular degeneration.

Keywords: age-related macular degeneration (AMD); convolutional neural network (CNN); deep learning; nascent geographic atrophy (nGA); optical coherence tomography (OCT).