Published on Thu Jun 11 2020

W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network

Hongwei Zhao, Chengtao Peng, Lei Liu, Bin Li

We propose a method to simultaneously segment both the optic disc (OD) and the exudates in retinal images based on the multi-task learning (MTL) scheme. We demonstrated the effectiveness of our approach by applying five-fold cross-validation experiments on two public datasets.

0
0
0
Abstract

Segmentation of multiple anatomical structures is of great importance in medical image analysis. In this study, we proposed a -net to simultaneously segment both the optic disc (OD) and the exudates in retinal images based on the multi-task learning (MTL) scheme. We introduced a class-balanced loss and a multi-task weighted loss to alleviate the imbalanced problem and to improve the robustness and generalization property of the -net. We demonstrated the effectiveness of our approach by applying five-fold cross-validation experiments on two public datasets e\_ophtha\_EX and DiaRetDb1. We achieved F1-score of 94.76\% and 95.73\% for OD segmentation, and 92.80\% and 94.14\% for exudates segmentation. To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation. Our results demonstrated that by choosing the optimal weights of each task, the MTL based -net outperformed separate models trained individually on each task. Code and pre-trained models will be available at: \url{https://github.com/FundusResearch/MTL_for_OD_and_exudates.git}.

Fri Apr 07 2017
Computer Vision
ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network
Optical coherence tomography (OCT) is used for non-invasive diagnosis of diabetic macular edema assessing the retinal layers. ReLayNet uses a contracting path of convolutional blocks (encoders) to learn a hierarchy of contextual features.
0
0
0
Tue Jun 18 2019
Computer Vision
Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography
Automated drusen segmentation in retinal optical coherence tomography (OCT) is relevant for understanding age-related macular degeneration (AMD) risk and progression. This task is usually performed by segmenting the top/bottom interfaces. In this paper we propose a novel
0
0
0
Wed Jun 03 2020
Computer Vision
Automated segmentation of retinal fluid volumes from structural and angiographic optical coherence tomography using deep learning
0
0
0
Sun May 10 2020
Machine Learning
Segmentation of Macular Edema Datasets with Small Residual 3D U-Net Architectures
This paper investigates the application of deep convolutional neural networks to the problem of macular edema segmentation. It takes an experienced clinician two days to annotate a single 3D image, whereas our trained model achieves similar performance in less than a second.
0
0
0
Thu Dec 03 2020
Computer Vision
Dual-Branch Network with Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation from Colour Fundus Images
Automated segmentation of hard exudates in colour fundus images is a difficult task due to issues of extreme class imbalance and enormous size variation. This paper aims to tackle these issues and proposes a dual-branch network with dual-sampling modulated Dice loss.
0
0
0
Mon Jan 29 2018
Computer Vision
Deep Learning based Retinal OCT Segmentation
OCT images from 10 patients with mild non-proliferative diabetic retinopathy were used. The proposed automated approach segments images using fully convolutional networks (FCNs) together with Gaussian process (GP)-based post-processing. The results show that the proposed methods compare favorably with state of the art techniques.
0
0
0