Wavelet-based selection-and-recalibration network for Parkinson's disease screening in OCT images

Jingqi Huang, Xiaoqing Zhang, Richu Jin, Tao Xu, Zi Jin, Meixiao Shen, Fan Lv, Jiangfan Chen, Jiang Liu

Abstract: Highlights•We propose a frequency domain learning network to accurately screen PD.•We construct a module to target specific retinal structures.•This paper uses visual methods to explore SRM’s focus and interpret the PD screening.•Results suggest the retina could be a valuable tool for assessing PD.•Experiments validate our model’s effectiveness on two public datasets.