Microaneurysm detection using fully convolutional neural networks

Chudzik, Piotr and Majumdar, Somshubra and Calivá, Francesco and Al-Diri, Bashir and Hunter, Andrew (2018) Microaneurysm detection using fully convolutional neural networks. Computer Methods and Programs in Biomedicine, 158 . pp. 185-192. ISSN 0169-2607

Documents
paper_lesions.pdf

Request a copy
31182 manuscript_chudzik.pdf
[img]
[Download]
[img] PDF
paper_lesions.pdf - Whole Document
Restricted to Repository staff only

1MB
[img]
Preview
PDF
31182 manuscript_chudzik.pdf - Whole Document

1MB
Item Type:Article
Item Status:Live Archive

Abstract

Backround and Objectives: Diabetic retinopathy is a microvascular complication of diabetes that can lead to sight loss if treated not early enough. Microaneurysms are the earliest clinical signs of diabetic retinopathy. This paper presents an automatic method for detecting microaneurysms in fundus photographies. Methods: A novel patch-based fully convolutional neural network with batch normalization layers and Dice loss function is proposed. Compared to other methods that require up to five processing stages, it requires only three. Furthermore, to the best of the authors’ knowledge, this is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain. Results: The proposed method was evaluated using three publicly available and widely used datasets: E-Ophtha, DIARETDB1, and ROC. It achieved better results than state-of-the-art methods using the FROC metric. The proposed algorithm accomplished highest sensitivities for low false positive rates, which is
particularly important for screening purposes. Conclusions: Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications.

Keywords:Medical image analysis, Microaneurysm detection, Convolutional neural networks, Retinal fundus images
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:31182
Deposited On:07 Mar 2018 14:16

Repository Staff Only: item control page