Parallel deep neural networks for endoscopic OCT image segmentation

被引：31

作者：

Li, Dawei ^{[1
]}

Wu, Jimin ^{[2
]}

He, Yufan ^{[2
]}

Yao, Xinwen ^{[1
]}

Yuan, Wu ^{[1
]}

Chen, Defu ^{[1
]}

Park, Hyeon-Cheol ^{[1
]}

Yu, Shaoyong ^{[3
]}

Prince, Jerry L. ^{[2
]}

Li, Xingde ^{[1
]}

机构：

[1] Johns Hopkins Univ, Dept Biomed Engn, Baltimore, MD 21205 USA

[2] Johns Hopkins Univ, Dept Elect & Comp Engn, Baltimore, MD 21218 USA

[3] Johns Hopkins Univ, Sch Med, Dept Med, Baltimore, MD 21205 USA

来源：

BIOMEDICAL OPTICS EXPRESS | 2019年 / 10卷 / 03期

基金：

美国国家卫生研究院;

关键词：

OPTICAL COHERENCE TOMOGRAPHY; RETINAL LAYER SEGMENTATION; AUTOMATIC SEGMENTATION; FLUID SEGMENTATION; BOUNDARIES;

D O I：

10.1364/BOE.10.001126

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

We report parallel-trained deep neural networks for automated endoscopic OCT image segmentation feasible even with a limited training data set. These U-Net-based deep neural networks were trained using a modified dice loss function and manual segmentations of ultrahigh-resolution cross-sectional images collected by an 800 nm OCT endoscopic system. The method was tested on in vivo guinea pig esophagus images. Results showed its robust layer segmentation capability with a boundary error of 1.4 mu m insensitive to lay topology disorders. To further illustrate its clinical potential, the method was applied to differentiating in vivo OCT esophagus images from an eosinophilic esophagitis (EOE) model and its control group, and the results clearly demonstrated quantitative changes in the top esophageal layers' thickness in the EOE model. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

引用

页码：1126 / 1135

页数：10

共 50 条

[1] Deep OCT image compression with convolutional neural networks
Guo, Pengfei
Li, Dawei
Li, Xingde
[J]. BIOMEDICAL OPTICS EXPRESS, 2020, 11 (07): : 3543 - 3554
[2] Automated segmentation of macular edema in OCT using deep neural networks
Hu, Junjie
Chen, Yuanyuan
Yi, Zhang
[J]. MEDICAL IMAGE ANALYSIS, 2019, 55 : 216 - 227
[3] Medical Image Segmentation Using Deep Neural Networks
Aydin, Musa
[J]. 29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021), 2021,
[4] Ordinal Image Segmentation using Deep Neural Networks
Fernandes, Kelwin
Cardoso, Jaime S.
[J]. 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
[5] Lung CT Image Segmentation Using Deep Neural Networks
Ait Skourt, Brahim
El Hassani, Abdelhamid
Majda, Aicha
[J]. PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING IN DATA SCIENCES (ICDS2017), 2018, 127 : 109 - 113
[6] Deep Memristive Cellular Neural Networks for Image Classification and Segmentation
Horvath, Andras
Rajki, Franciska
Ascoli, Alon
Tetzlaff, Ronald
[J]. IEEE Transactions on Nanotechnology, 2024, 23 : 718 - 726
[7] Evolutionary Compression of Deep Neural Networks for Biomedical Image Segmentation
Zhou, Yao
Yen, Gary G.
Yi, Zhang
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (08) : 2916 - 2929
[8] Ovarian Tumor Ultrasound Image Segmentation with Deep Neural Networks
Siahpoosh, Mahnaz
Imani, Maryam
Ghassemian, Hassan
[J]. PROCEEDINGS OF THE 13TH IRANIAN/3RD INTERNATIONAL MACHINE VISION AND IMAGE PROCESSING CONFERENCE, MVIP, 2024, : 112 - 116
[9] Sea Ice Image Semantic Segmentation Using Deep Neural Networks
Dowden, Benjamin
De Silva, Oscar
Huang, Weimin
[J]. GLOBAL OCEANS 2020: SINGAPORE - U.S. GULF COAST, 2020,
[10] Automatic Design of Deep Neural Networks Applied to Image Segmentation Problems
Lima, Ricardo
Pozo, Aurora
Mendiburu, Alexander
Santana, Roberto
[J]. GENETIC PROGRAMMING, EUROGP 2021, 2021, 12691 : 98 - 113

← 1 2 3 4 5 →