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.