Automatic classification of heterogeneous slit-illumination images using an ensemble of cost-sensitive convolutional neural networks

Jiewei Jiang; Liming Wang; Haoran Fu; Erping Long; Yibin Sun; Ruiyang Li; Zhongwen Li; Mingmin Zhu; Zhenzhen Liu; Jingjing Chen; Zhuoling Lin; Xiaohang Wu; Dongni Wang; Xiyang Liu; Haotian Lin

doi:10.21037/atm-20-6635

Automatic classification of heterogeneous slit-illumination images using an ensemble of cost-sensitive convolutional neural networks

Ann Transl Med. 2021 Apr;9(7):550. doi: 10.21037/atm-20-6635.

Authors

Affiliations

¹ School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an, China.
² School of Computer Science and Technology, Xidian University, Xi'an, China.
³ State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China.
⁴ School of Mathematics and Statistics, Xidian University, Xi'an, China.

Abstract

Background: Lens opacity seriously affects the visual development of infants. Slit-illumination images play an irreplaceable role in lens opacity detection; however, these images exhibited varied phenotypes with severe heterogeneity and complexity, particularly among pediatric cataracts. Therefore, it is urgently needed to explore an effective computer-aided method to automatically diagnose heterogeneous lens opacity and to provide appropriate treatment recommendations in a timely manner.

Methods: We integrated three different deep learning networks and a cost-sensitive method into an ensemble learning architecture, and then proposed an effective model called CCNN-Ensemble [ensemble of cost-sensitive convolutional neural networks (CNNs)] for automatic lens opacity detection. A total of 470 slit-illumination images of pediatric cataracts were used for training and comparison between the CCNN-Ensemble model and conventional methods. Finally, we used two external datasets (132 independent test images and 79 Internet-based images) to further evaluate the model's generalizability and effectiveness.

Results: Experimental results and comparative analyses demonstrated that the proposed method was superior to conventional approaches and provided clinically meaningful performance in terms of three grading indices of lens opacity: area (specificity and sensitivity; 92.00% and 92.31%), density (93.85% and 91.43%) and opacity location (95.25% and 89.29%). Furthermore, the comparable performance on the independent testing dataset and the internet-based images verified the effectiveness and generalizability of the model. Finally, we developed and implemented a website-based automatic diagnosis software for pediatric cataract grading diagnosis in ophthalmology clinics.

Conclusions: The CCNN-Ensemble method demonstrates higher specificity and sensitivity than conventional methods on multi-source datasets. This study provides a practical strategy for heterogeneous lens opacity diagnosis and has the potential to be applied to the analysis of other medical images.

Keywords: Cost-sensitive; deep convolutional neural networks (CNNs); ensemble learning; heterogeneous slit-illumination images; pediatric cataract.