Exudate segmentation using fully convolutional neural networks and inception modules

Chudzik, Piotr and Somshubra, Majumdar and Caliva, Francesco and Al-Diri, Bashir and Hunter, Andrew (2018) Exudate segmentation using fully convolutional neural networks and inception modules. Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 1057430 (2 March 2018) . ISSN 0277-786X

Full content URL: https://doi.org/10.1117/12.2293549

Documents
Exudate segmentation using fully convolutional neural networks and inception modules
[img]
[Download]
[img]
Preview
PDF
exudates.pdf - Whole Document

2MB
Item Type:Article
Item Status:Live Archive

Abstract

Diabetic retinopathy is an eye disease associated with diabetes mellitus and also it is the leading cause of
preventable blindness in working-age population. Early detection and treatment of DR is essential to prevent
vision loss. Exudates are one of the earliest signs of diabetic retinopathy. This paper proposes an automatic
method for the detection and segmentation of exudates in fundus photographies. A novel fully convolutional
neural network architecture with Inception modules is proposed. Compared to other methods it does not require
the removal of other anatomical structures. Furthermore, a transfer learning approach is applied between small
datasets of different modalities from the same domain. To the best of authors’ knowledge, it is the first time
that such approach has been used in the exudate segmentation domain. 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 algorithm 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.

Additional Information:Proceedings Volume 10574, Medical Imaging 2018: Image Processing; 1057430 (2018) https://doi.org/10.1117/12.2293549 Event: SPIE Medical Imaging, 2018, Houston, Texas, United States
Keywords:Deep Learning, Fundus Photography, Convolutional Neural Networks
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:31549
Deposited On:06 Apr 2018 13:54

Repository Staff Only: item control page