Improving the Generalizability of Infantile Cataracts Detection via Deep Learning-Based Lens Partition Strategy and Multicenter Datasets

Frontiers in Medicine

Shutao Lei¹  Jiayun Yue²  Jiewei Jiang²  Jiamin Gong²  Mingmin Zhu³  Jingjing Chen⁴  Zhongwen Li⁴  Duoru Lin⁴  Zhuoling Lin⁴  Ruiyang Li⁴  Xiaohang Wu⁴  Haotian Lin⁴ 

[1] School of Communications and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, China;School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an, China;School of Mathematics and Statistics, Xidian University, Xi'an, China;State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China;

关键词: lens partition strategy;    infantile cataracts;    automatic diagnosis;    Faster R-CNN;    multicenter slit-lamp images;   

DOI  :  10.3389/fmed.2021.664023

来源: Frontiers

【 摘 要 】

Infantile cataract is the main cause of infant blindness worldwide. Although previous studies developed artificial intelligence (AI) diagnostic systems for detecting infantile cataracts in a single center, its generalizability is not ideal because of the complicated noises and heterogeneity of multicenter slit-lamp images, which impedes the application of these AI systems in real-world clinics. In this study, we developed two lens partition strategies (LPSs) based on deep learning Faster R-CNN and Hough transform for improving the generalizability of infantile cataracts detection. A total of 1,643 multicenter slit-lamp images collected from five ophthalmic clinics were used to evaluate the performance of LPSs. The generalizability of Faster R-CNN for screening and grading was explored by sequentially adding multicenter images to the training dataset. For the normal and abnormal lenses partition, the Faster R-CNN achieved the average intersection over union of 0.9419 and 0.9107, respectively, and their average precisions are both > 95%. Compared with the Hough transform, the accuracy, specificity, and sensitivity of Faster R-CNN for opacity area grading were improved by 5.31, 8.09, and 3.29%, respectively. Similar improvements were presented on the other grading of opacity density and location. The minimal training sample size required by Faster R-CNN is determined on multicenter slit-lamp images. Furthermore, the Faster R-CNN achieved real-time lens partition with only 0.25 s for a single image, whereas the Hough transform needs 34.46 s. Finally, using Grad-Cam and t-SNE techniques, the most relevant lesion regions were highlighted in heatmaps, and the high-level features were discriminated. This study provides an effective LPS for improving the generalizability of infantile cataracts detection. This system has the potential to be applied to multicenter slit-lamp images.

【 授权许可】

CC BY