July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
CATARACT DETECTION AND GRADING BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK
Author Affiliations & Notes
  • Hongyan Zhang
    Beijing Tongren Eye center, Beijing, China
    Beijing Tongren Hospital, China
  • Kai Niu
    Key Laboratory of Universal Wireless Communations, China
    Beijing University of Posts and Telecommunications, Beijing, China
  • Yanmin Xiong
    Key Laboratory of Universal Wireless Communations, China
    Beijing University of Posts and Telecommunications, Beijing, China
  • Weihua Yang
    The First People’s Hospital of Huzhou, Huzhou, Zhejiang, China
  • Zhiqiang He
    Key Laboratory of Universal Wireless Communations, China
    Beijing University of Posts and Telecommunications, Beijing, China
  • Hongxin Song
    Beijing Tongren Eye center, Beijing, China
    Beijing Tongren Hospital, China
  • Footnotes
    Commercial Relationships   Hongyan Zhang, None; Kai Niu, None; Yanmin Xiong, None; Weihua Yang, None; Zhiqiang He, None; Hongxin Song, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1129. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Hongyan Zhang, Kai Niu, Yanmin Xiong, Weihua Yang, Zhiqiang He, Hongxin Song; CATARACT DETECTION AND GRADING BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1129.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : The shortage of ophthmologist in rural area in China casued a lot of cataract patients can’t get diagnosis and effective treatment. We developed an algorithm and platform to automatically diagnose and grade cataract based on fundus images of patients. This method can be used to help government assisting the poor population more accurately.

Methods : The novel six-level cataract grading method proposed in this paper focuses on the multi-feature fusion based on stacking. We extract two kinds of features which can effectively distinguish different levels of cataract. One is high-level feaetures extracted from residual network (ResNet18). The other is texture features extarcted by gray level co-occurrence matrix (GLCM). Then we propose a frame to automatically grade cataract by the extracted features. In the frame, two support vector machine (SVM) classifiers are used as base-learners to obtain the probability outputs of each fundus image, and fully connected neural network (FCNN) are used as meta-learner to output the final classification result, which consists of two layers of fully connected layers (FC).

Results : The accuracy of six-level grading achieved by the proposed method is up to 92.66% on average, the highest of which reaches 93.33%. The proposed method achieves 94.75% accuracy on four-level grading for cataract, which is at least 1.75% higher than those of the exiting methods.

Conclusions : Six-category comparison experiments show that Multi-feature & Stacking helps achieve higher grading performance and lower volatility than grading using high-level features and texture features respectively. We also applied our algorithum into four-level cataract grading system and our resutls also show highest accuracy compared with previous reports.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×