Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network

• Published in: PloS one Vol. 12; no. 3; p. e0168606
• Main Authors: Liu, Xiyang, Jiang, Jiewei, Zhang, Kai, Long, Erping, Cui, Jiangtao, Zhu, Mingmin, An, Yingying, Zhang, Jia, Liu, Zhenzhen, Lin, Zhuoling, Li, Xiaoyan, Chen, Jingjing, Cao, Qianzhong, Li, Jing, Wu, Xiaohang, Wang, Dongni, Lin, Haotian
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 17-03-2017; Public Library of Science (PLoS)
• Subjects: Accuracy; Artificial intelligence; Artificial neural networks; Automation; Biology and Life Sciences; Cataract - diagnosis; Cataracts; Child; Classification; Computer and Information Sciences; Computer science; Computer vision; Confectionery; Datasets; Diagnosis; Diagnostic software; Diagnostic systems; Disease; Evaluation; Feature extraction; Hough transformation; Humans; Image detection; International conferences; Laboratories; Localization; Machine learning; Medical diagnosis; Medical personnel; Medicine and Health Sciences; Methods; Nerve Net; Neural networks; Noise; Pattern recognition; Pediatrics; Research and Analysis Methods; Studies; Support vector machines; Therapeutic applications; Visual impairment
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0168606

Slit-lamp images play an essential role for diagnosis of pediatric cataracts. We present a computer vision-based framework for the automatic localization and diagnosis of slit-lamp images by identifying the lens region of interest (ROI) and employing a deep learning convolutional neural network (CNN). First, three grading degrees for slit-lamp images are proposed in conjunction with three leading ophthalmologists. The lens ROI is located in an automated manner in the original image using two successive applications of Candy detection and the Hough transform, which are cropped, resized to a fixed size and used to form pediatric cataract datasets. These datasets are fed into the CNN to extract high-level features and implement automatic classification and grading. To demonstrate the performance and effectiveness of the deep features extracted in the CNN, we investigate the features combined with support vector machine (SVM) and softmax classifier and compare these with the traditional representative methods. The qualitative and quantitative experimental results demonstrate that our proposed method offers exceptional mean accuracy, sensitivity and specificity: classification (97.07%, 97.28%, and 96.83%) and a three-degree grading area (89.02%, 86.63%, and 90.75%), density (92.68%, 91.05%, and 93.94%) and location (89.28%, 82.70%, and 93.08%). Finally, we developed and deployed a potential automatic diagnostic software for ophthalmologists and patients in clinical applications to implement the validated model.