You, Hong YuHong YuYouWei, Hsu TingHsu TingWeiLin, Cheng HungCheng HungLinJi, Jie YiJie YiJiLiu, Yu HengYu HengLiuLu, Cheng KaiCheng KaiLuJIA-KANG WANGHuang, Tzu LunTzu LunHuang2024-01-202024-01-202021-01-019781728193045https://scholars.lib.ntu.edu.tw/handle/123456789/638663This paper proposed a novel deep learning architecture, called the AMDOCT-NET architecture, to accurately detect age-related macular degeneration (AMD) on optical coherence tomography (OCT) images. Using the AMDOCT-NET architecture, the performance of various image processing, such as resizing, denoising, and cropping has been evaluated. The simulation results show that the AMDOCT-NET architecture with an input size of 224×224 pixels, no cropping, and no denoising achieves the accuracy of 99.09% to automatically detect the AMD. Compared with the well-known deep learning architecture, VGG16, the AMDOCT-NET improves accuracy by 2.09% and reduces the model size by 53.7%.Age-related macular degeneration | Deep learning technology | Optical coherence tomographyconference paper10.1109/ECBIOS51820.2021.95105702-s2.0-85124889225https://api.elsevier.com/content/abstract/scopus_id/85124889225