Automatic boundary segmentation of vascular Doppler optical coherence tomography images based on cascaded U-net architecture

Wu, Chuanchao; Xie, Yingxiong; Shao, Lisheng; Yang, Jian; Ai, Danni; Song, Hong; Wang, Yongtian; Huang, Yong

doi:10.1364/osac.2.000677

Cited by 16 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, strain information along the rock bolts should be collected to reveal long‐term movements of the rock mass and to allow an operator to take necessary precautions . With the development of optical fiber technology and its use in sensing and measurement, this technology is increasingly used in monitoring stress, overburden deformation, temperature, humidity, and moisture . Lately, optical fibers have been used in monitoring the stress of bolts .…”

Section: Introductionmentioning

confidence: 99%

Monitoring and correction of the stress in an anchor bolt based on Pulse Pre‐Pumped Brillouin Optical Time Domain Analysis

Liu

Chai

Chen

et al. 2020

Energy Science & Engineering

View full text Add to dashboard Cite

Bolt is an important connection in underground construction and monitoring its stress characteristics is essential to evaluate the effectiveness of bolt. The strain information collected along a rock bolt reveals the long-term movement characteristics of rock mass, which greatly helps toward disaster prevention and risk warning.Grooving on the surface of a bolt and embedding an optical fiber is one of the main methods for monitoring the anchorage performance and stress distribution around the bolt in underground engineering. In this study, Pulse Pre-Pumped Brillouin Optical Time Domain Analysis (PPP-BOTDA) technology is used to evaluate the stress, axial force, and shear stress distribution of the bolt under tensile load for different types (grooved and nongrooved) of bolts embedded in concrete with resin as anchoring agent. The results show that the PPP-BOTDA sensor can be used to monitor the stress state of the bolt embedded in concrete with resin as anchoring agent when the bolt is subjected to a tensile force. However, the apparent stress value measured in this way is not the actual stress value of the bolt, but is an increased value caused due to the groove. The closer to the exposed end of the bolt, the greater is the deviation between the apparent stress value and the actual stress value of the bolt. Based on the monitoring results from this experimental study, a stress reduction calculation method is proposed, which can change the measured value into the actual stress of the bolt. K E Y W O R D Saxial force, bolt, PPP-BOTDA technology, pullout test, shear stress 2012 |

show abstract

Section: Introductionmentioning

confidence: 99%

Monitoring and correction of the stress in an anchor bolt based on Pulse Pre‐Pumped Brillouin Optical Time Domain Analysis

Liu

Chai

Chen

et al. 2020

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…In [103], a Densely Connected Stacked U-Network (DCSU) is used to segment confocal microscopy images of filament. Unlike [95,98,102], DCSU is a cascaded U-Net (combination of multiple U-Nets, the output of previous level U-Net is related to the input of the next U-Net [104]) and dense connections occur between convolutional blocks of different U-Nets. A microtubule dataset containing 5032407 training patches is proposed to evaluate DCSU.…”

Section: Dense U-netmentioning

confidence: 99%

A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification

Wu¹,

Liu²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image analysis technology is used to solve the inadvertences of artificial traditional methods in disease, wastewater treatment, environmental change monitoring analysis and convolutional neural networks (CNN) play an important role in microscopic image analysis. An important step in detection, tracking, monitoring, feature extraction, modeling and analysis is image segmentation, in which U-Net has increasingly applied in microscopic image segmentation. This paper comprehensively reviews the development history of U-Net, and analyzes various research results of various segmentation methods since the emergence of U-Net and conducts a comprehensive review of related papers. First, This paper has summarizes the improved methods of U-Net and then listed the existing significances of image segmentation techniques and their improvements that has introduced over the years. Finally, focusing on the different improvement strategies of U-Net in different papers, the related work of each application target is reviewed according to detailed technical categories to facilitate future research. Researchers can clearly see the dynamics of transmission of technological development and keep up with future trends in this interdisciplinary field.

show abstract

“…Chiu et al reported a kernel regression-based segmentation method for retinal OCT images with diabetic macular edema [7]. Recently, convolutional neural networks (CNN) have been widely applied to segment images obtained from various modalities and thus enable exciting applications [18][19][20][21][22][23][24][25][26]. Fully convolutional networks (FCN) [27] and U-Net [28] are two popular candidates for medical image segmentation.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and disc in peripapillary OCT images

Li¹,

Jin²,

Zhu³

et al. 2021

Preprint

View full text Add to dashboard Cite

An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma. However, due to the presence of the optic disc, the anatomical structure of the peripapillary region of the retina is complicated and is challenging for segmentation. To address this issue, we developed a novel graph convolutional network (GCN)-assisted two-stage framework to simultaneously label the nine retinal layers and the optic disc. Specifically, a multi-scale global reasoning module is inserted between the encoder and decoder of a U-shape neural network to exploit anatomical prior knowledge and perform spatial reasoning. We conducted experiments on human peripapillary retinal OCT images. The Dice score of the proposed segmentation network is 0.820 ± 0.001 and the pixel accuracy is 0.830 ± 0.002, both of which outperform those from other state-of-the-art techniques.

show abstract

Automatic boundary segmentation of vascular Doppler optical coherence tomography images based on cascaded U-net architecture

Cited by 16 publications

References 29 publications

Monitoring and correction of the stress in an anchor bolt based on Pulse Pre‐Pumped Brillouin Optical Time Domain Analysis

Monitoring and correction of the stress in an anchor bolt based on Pulse Pre‐Pumped Brillouin Optical Time Domain Analysis

A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification

Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and disc in peripapillary OCT images

Contact Info

Product

Resources

About