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

12Citations
Citations of this article
34Readers
Mendeley users who have this article in their library.

Abstract

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.

References Powered by Scopus

Deep residual learning for image recognition

173772Citations
N/AReaders
Get full text

Going deeper with convolutions

39542Citations
N/AReaders
Get full text

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

25868Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Machine Learning for Cataract Classification/Grading on Ophthalmic Imaging Modalities: A Survey

48Citations
N/AReaders
Get full text

Automatic Classification of Colour Fundus Images for Prediction Eye Disease Types Based on Hybrid Features

33Citations
N/AReaders
Get full text

Artificial Intelligence-Assisted Renal Pathology: Advances and Prospects

9Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Jiang, J., Lei, S., Zhu, M., Li, R., Yue, J., Chen, J., … Lin, H. (2021). Improving the Generalizability of Infantile Cataracts Detection via Deep Learning-Based Lens Partition Strategy and Multicenter Datasets. Frontiers in Medicine, 8. https://doi.org/10.3389/fmed.2021.664023

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 5

50%

Professor / Associate Prof. 4

40%

Researcher 1

10%

Readers' Discipline

Tooltip

Computer Science 3

33%

Medicine and Dentistry 3

33%

Engineering 2

22%

Nursing and Health Professions 1

11%

Save time finding and organizing research with Mendeley

Sign up for free