Automated diabetic retinopathy grading and lesion detection based on the modified R‐FCN object‐detection algorithm. Issue 1 (16th January 2020)

• Record Type: Journal Article
• Authors: Wang, Jialiang; Luo, Jianxu; Liu, Bin; Feng, Rui; Lu, Lina; Zou, Haidong
• Is Part Of: IET computer vision. Volume 14:Issue 1(2020)
• Page Start: 1
• Page End: 8
• Publication Date: 2020-01-16
• Subjects: feature extraction -- biomedical optical imaging -- image segmentation -- medical image processing -- object detection -- eye -- diseases -- image classification -- blood vessels; feature pyramid network -- modified region proposal network -- DR-grading model -- Messidor data -- Shanghai Eye Hospital -- hospital data -- modified R-FCN lesion-detection model -- lesion detection -- modified R-FCN object-detection algorithm -- computer-aided retinal image screening system -- retinal fundus images -- modified object-detection method -- region-based fully convolutional network; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5508
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : In this work, we develop a computer‐aided retinal image screening system that can perform automated diabetic retinopathy (DR) grading and DR lesion detection in retinal fundus images. We propose a modified object‐detection method for this task via a region‐based fully convolutional network (R‐FCN). A feature pyramid network and a modified region proposal network are applied to enhance the detection of small objects. The DR‐grading model based on the modified R‐FCN is evaluated on the Messidor data set and images provided by the Shanghai Eye Hospital. High sensitivity of 99.39% and specificity of 99.93% are obtained on the hospital data. Moreover, high sensitivity of 92.59% and specificity of 96.20% are obtained on the Messidor data set. The modified R‐FCN lesion‐detection model is validated on the hospital data set and achieves a 92.15% mean average precision. The proposed R‐FCN can efficiently accomplish DR grading and lesion detection with high accuracy.