Li Meixuan, Shen Yadan, Wu Renxiong, Huang Shaoyan, Zheng Fei, Chen Sizhu, Wang Rong, Dong Wentao, Zhong Jie, Ni Guangming, Liu Yong
School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.
Eye School, Chengdu University of Traditional Chinese Medicine, Chengdu 610075, China.
Biomed Opt Express. 2024 Jan 26;15(2):1115-1131. doi: 10.1364/BOE.513619. eCollection 2024 Feb 1.
Wet age-related macular degeneration (AMD) is the leading cause of visual impairment and vision loss in the elderly, and optical coherence tomography (OCT) enables revolving biotissue three-dimensional micro-structure widely used to diagnose and monitor wet AMD lesions. Many wet AMD segmentation methods based on deep learning have achieved good results, but these segmentation results are two-dimensional, and cannot take full advantage of OCT's three-dimensional (3D) imaging characteristics. Here we propose a novel deep-learning network characterizing multi-scale and cross-channel feature extraction and channel attention to obtain high-accuracy 3D segmentation results of wet AMD lesions and show the 3D specific morphology, a task unattainable with traditional two-dimensional segmentation. This probably helps to understand the ophthalmologic disease and provides great convenience for the clinical diagnosis and treatment of wet AMD.
湿性年龄相关性黄斑变性（AMD）是老年人视力损害和视力丧失的主要原因，光学相干断层扫描（OCT）能够对生物组织进行三维微观结构成像，被广泛用于诊断和监测湿性AMD病变。许多基于深度学习的湿性AMD分割方法都取得了良好的效果，但这些分割结果是二维的，无法充分利用OCT的三维（3D）成像特性。在此，我们提出了一种新颖的深度学习网络，该网络具有多尺度和跨通道特征提取以及通道注意力机制，以获得湿性AMD病变的高精度3D分割结果，并展示其3D特定形态，这是传统二维分割无法实现的任务。这可能有助于理解眼科疾病，并为湿性AMD的临床诊断和治疗提供极大便利。
