Fully Convolutional Networks for Monocular Retinal Depth Estimation and Optic Disc-Cup Segmentation

视盘 人工智能 单眼 分割 计算机科学 视网膜 视杯(胚胎学) 计算机视觉 图像分割 卷积神经网络 模式识别(心理学) 眼科 医学 生物 基因 眼睛发育 表型 生物化学
作者
Sharath M Shankaranarayana,Keerthi Ram,Kaushik Mitra,Mohanasankar Sivaprakasam
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:23 (4): 1417-1426 被引量:67
标识
DOI:10.1109/jbhi.2019.2899403
摘要

Glaucoma is a serious ocular disorder for which the screening and diagnosis are carried out by the examination of the optic nerve head (ONH). The color fundus image (CFI) is the most common modality used for ocular screening. In CFI, the central region which is the optic disc and the optic cup region within the disc are examined to determine one of the important cues for glaucoma diagnosis called the optic cup-to-disc ratio (CDR). CDR calculation requires accurate segmentation of optic disc and cup. Another important cue for glaucoma progression is the variation of depth in ONH region. In this paper, we first propose a deep learning framework to estimate depth from a single fundus image. For the case of monocular retinal depth estimation, we are also plagued by the labeled data insufficiency. To overcome this problem we adopt the technique of pretraining the deep network where, instead of using a denoising autoencoder, we propose a new pretraining scheme called pseudo-depth reconstruction, which serves as a proxy task for retinal depth estimation. Empirically, we show pseudo-depth reconstruction to be a better proxy task than denoising. Our results outperform the existing techniques for depth estimation on the INSPIRE dataset. To extend the use of depth map for optic disc and cup segmentation, we propose a novel fully convolutional guided network, where, along with the color fundus image the network uses the depth map as a guide. We propose a convolutional block called multimodal feature extraction block to extract and fuse the features of the color image and the guide image. We extensively evaluate the proposed segmentation scheme on three datasets- ORIGA, RIMONEr3, and DRISHTI-GS. The performance of the method is comparable and in many cases, outperforms the most recent state of the art.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
andrew完成签到,获得积分10
1秒前
秋秋糖xte发布了新的文献求助10
3秒前
二娃完成签到,获得积分10
4秒前
5秒前
黑糖珍珠完成签到 ,获得积分10
6秒前
科研小白完成签到,获得积分10
7秒前
8秒前
梁采瑞完成签到,获得积分10
8秒前
CodeCraft应助Tonald Yang采纳,获得10
9秒前
Nollet完成签到 ,获得积分10
9秒前
Emily完成签到,获得积分10
10秒前
宁静完成签到,获得积分10
10秒前
NexusExplorer应助wenbin采纳,获得10
11秒前
lina完成签到 ,获得积分10
12秒前
追风筝的人完成签到,获得积分20
12秒前
淡然珍完成签到,获得积分10
12秒前
iwaking完成签到,获得积分10
12秒前
冷静剑成完成签到,获得积分10
13秒前
标致幻然完成签到 ,获得积分10
14秒前
来自三百发布了新的文献求助10
14秒前
fixing发布了新的文献求助10
14秒前
酪酪Alona完成签到,获得积分10
15秒前
小王完成签到,获得积分10
16秒前
今夜不设防完成签到,获得积分10
17秒前
QXS完成签到 ,获得积分10
17秒前
包容的雅青完成签到,获得积分10
17秒前
Muggle完成签到 ,获得积分20
19秒前
Darsine完成签到,获得积分10
19秒前
20秒前
ALLon完成签到 ,获得积分10
21秒前
怡然凌柏完成签到 ,获得积分10
22秒前
1111chen完成签到 ,获得积分10
22秒前
TCL完成签到 ,获得积分10
23秒前
不如看海完成签到 ,获得积分10
23秒前
孤独元容完成签到,获得积分10
23秒前
hugebear完成签到,获得积分10
24秒前
efengmo完成签到,获得积分10
24秒前
拼搏的明轩完成签到,获得积分10
25秒前
fmx完成签到,获得积分10
25秒前
cis2014完成签到,获得积分10
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968593
求助须知:如何正确求助?哪些是违规求助? 3513416
关于积分的说明 11167791
捐赠科研通 3248853
什么是DOI,文献DOI怎么找? 1794507
邀请新用户注册赠送积分活动 875170
科研通“疑难数据库(出版商)”最低求助积分说明 804671