Xiao Haodong, Ju Lie, Lu Zupeng, Zhang Shiguang, Jiang Yan, Yang Yuan, Zhang Xuerui, Zhang Wenting, Liu Huanyu, Liang Tingyi, Ren Jianing, Yin Jiawei, Liu Xiaoyu, Ma Tong, Wang Lin, Feng Wei, Song Kaimin, Chen Yuzhong, Ge Zongyuan, Shao Qian, Peng Jie, Chen Jili, Zhao Peiquan
Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Beijing Airdoc Technology Co., Ltd., Beijing, China.
Front Med (Lausanne). 2025 Jun 3;12:1584378. doi: 10.3389/fmed.2025.1584378. eCollection 2025.
To develop and evaluate a deep learning system for screening multiple abnormal findings including hemorrhages, drusen, hard exudates, cotton wool spots and retinal breaks using ultra-widefield fundus images.
The system consisted of three modules: (I) quality assessment module, (II) artifact removal module and (III) lesion recognition module. In Module III, a heatmap was generated to highlight the lesion area. A total of 4,521 UWF images were used for the training and internal validation of the DL system. The system was evaluated in two external validation datasets consisting of 344 images and 894 images from two other hospitals. The performance of the system in these two datasets was compared with or without Module II.
In both external validation datasets, the deep learning system made better performance when recognizing lesions on processed images after Module II than on original images without Module II. Module II-enhanced preprocessing improved Module III's five-lesion recognition performance by an average of 6.73% and 14.4% areas under the curves, 14.47% and 19.62% accuracy in the two external validations.
Our system showed reliable performance for detecting MAF in real-world UWF images. For deep learning systems to recognize real-world images, the artifact removal module was indeed helpful.
开发并评估一种深度学习系统，用于使用超广角眼底图像筛查包括出血、玻璃膜疣、硬性渗出、棉絮斑和视网膜裂孔在内的多种异常表现。
该系统由三个模块组成：（I）质量评估模块，（II）伪影去除模块和（III）病变识别模块。在模块III中，生成热图以突出病变区域。总共4521张超广角图像用于深度学习系统的训练和内部验证。该系统在由另外两家医院的344张图像和894张图像组成的两个外部验证数据集中进行评估。将该系统在这两个数据集中的性能与有无模块II的情况进行比较。
在两个外部验证数据集中，深度学习系统在识别模块II处理后的图像上的病变时，比在没有模块II的原始图像上表现更好。模块II增强的预处理使模块III在两个外部验证中的五种病变识别性能的曲线下面积平均提高了6.73%和14.4%，准确率提高了14.47%和19.62%。
我们的系统在检测真实世界超广角图像中的多种异常表现方面显示出可靠的性能。对于深度学习系统识别真实世界图像而言，伪影去除模块确实很有帮助。
