Exudates Segmentation using Fully Convolutional Neural Network and Auxiliary Codebook

Lukasz, Piotr and Al-Diri, Bashir and Caliva, Francesco and Hunter, Andrew (2018) Exudates Segmentation using Fully Convolutional Neural Network and Auxiliary Codebook. 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . pp. 770-773. ISSN 1557-170X

Full content URL: https://doi.org/10.1109/EMBC.2018.8512354

Documents
Exudates Segmentation using Fully Convolutional Neural Network and Auxiliary Codebook
Publishers PDF

Request a copy
[img] PDF
exudates.pdf - Whole Document
Restricted to Repository staff only

4MB
Item Type:Article
Item Status:Live Archive

Abstract

Diabetic retinopathy (DR) is an asymptotic complication of diabetes and the leading cause of preventable blindness in the working-age population. Early detection and treatment of DR is critical to avoid vision loss. Exudates are one of the earliest and most prevalent signs of DR. In this work, we propose a novel two-stage method for the detection and segmentation of exudates in fundus photographs. In the first stage, a fully convolutional neural network architecture is
trained to segment exudates using small image patches. Next, an auxilary codebook is built from network’s intermediate layer output using incremental principal component analysis. Finally, outputs of both systems are combined to produce final result. Compared to other methods, the proposed algorithm does not require computation of candidate regions or removal of other anatomical structures. Furthermore, a transfer learning approach was applied to improve the performance of the system. The proposed method was evaluated using publicly available E-Ophtha datasets. It achieved better results than the state-of-the-art methods in terms of sensitivity and specificity metrics. The proposed method accomplished better results using a diseased/not diseased evaluation scenario which indicates its applicability for screening purposes. Simplicity, performance, efficiency and robustness of the proposed method demonstrate its suitability for diabetic retinopathy screening applications.

Keywords:Deep Learning, Retinal Imaging, Diabetic Retinopathy, Exudate Detection, Convolutional Neural Networks
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:33287
Deposited On:07 Jan 2019 09:37

Repository Staff Only: item control page