Cargando…

Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation

Laser speckle contrast imaging (LSCI) is a full-field, high spatiotemporal resolution and low-cost optical technique for measuring blood flow, which has been successfully used for neurovascular imaging. However, due to the low signal–noise ratio and the relatively small sizes, segmenting the cerebra...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Heping, Shi, Yan, Bo, Bin, Zhao, Denghui, Miao, Peng, Tong, Shanbao, Wang, Chunliang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8669333/
https://www.ncbi.nlm.nih.gov/pubmed/34916898
http://dx.doi.org/10.3389/fnins.2021.755198
_version_ 1784614757089673216
author Chen, Heping
Shi, Yan
Bo, Bin
Zhao, Denghui
Miao, Peng
Tong, Shanbao
Wang, Chunliang
author_facet Chen, Heping
Shi, Yan
Bo, Bin
Zhao, Denghui
Miao, Peng
Tong, Shanbao
Wang, Chunliang
author_sort Chen, Heping
collection PubMed
description Laser speckle contrast imaging (LSCI) is a full-field, high spatiotemporal resolution and low-cost optical technique for measuring blood flow, which has been successfully used for neurovascular imaging. However, due to the low signal–noise ratio and the relatively small sizes, segmenting the cerebral vessels in LSCI has always been a technical challenge. Recently, deep learning has shown its advantages in vascular segmentation. Nonetheless, ground truth by manual labeling is usually required for training the network, which makes it difficult to implement in practice. In this manuscript, we proposed a deep learning-based method for real-time cerebral vessel segmentation of LSCI without ground truth labels, which could be further integrated into intraoperative blood vessel imaging system. Synthetic LSCI images were obtained with a synthesis network from LSCI images and public labeled dataset of Digital Retinal Images for Vessel Extraction, which were then used to train the segmentation network. Using matching strategies to reduce the size discrepancy between retinal images and laser speckle contrast images, we could further significantly improve image synthesis and segmentation performance. In the testing LSCI images of rodent cerebral vessels, the proposed method resulted in a dice similarity coefficient of over 75%.
format Online
Article
Text
id pubmed-8669333
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-86693332021-12-15 Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation Chen, Heping Shi, Yan Bo, Bin Zhao, Denghui Miao, Peng Tong, Shanbao Wang, Chunliang Front Neurosci Neuroscience Laser speckle contrast imaging (LSCI) is a full-field, high spatiotemporal resolution and low-cost optical technique for measuring blood flow, which has been successfully used for neurovascular imaging. However, due to the low signal–noise ratio and the relatively small sizes, segmenting the cerebral vessels in LSCI has always been a technical challenge. Recently, deep learning has shown its advantages in vascular segmentation. Nonetheless, ground truth by manual labeling is usually required for training the network, which makes it difficult to implement in practice. In this manuscript, we proposed a deep learning-based method for real-time cerebral vessel segmentation of LSCI without ground truth labels, which could be further integrated into intraoperative blood vessel imaging system. Synthetic LSCI images were obtained with a synthesis network from LSCI images and public labeled dataset of Digital Retinal Images for Vessel Extraction, which were then used to train the segmentation network. Using matching strategies to reduce the size discrepancy between retinal images and laser speckle contrast images, we could further significantly improve image synthesis and segmentation performance. In the testing LSCI images of rodent cerebral vessels, the proposed method resulted in a dice similarity coefficient of over 75%. Frontiers Media S.A. 2021-11-30 /pmc/articles/PMC8669333/ /pubmed/34916898 http://dx.doi.org/10.3389/fnins.2021.755198 Text en Copyright © 2021 Chen, Shi, Bo, Zhao, Miao, Tong and Wang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Chen, Heping
Shi, Yan
Bo, Bin
Zhao, Denghui
Miao, Peng
Tong, Shanbao
Wang, Chunliang
Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
title Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
title_full Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
title_fullStr Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
title_full_unstemmed Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
title_short Real-Time Cerebral Vessel Segmentation in Laser Speckle Contrast Image Based on Unsupervised Domain Adaptation
title_sort real-time cerebral vessel segmentation in laser speckle contrast image based on unsupervised domain adaptation
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8669333/
https://www.ncbi.nlm.nih.gov/pubmed/34916898
http://dx.doi.org/10.3389/fnins.2021.755198
work_keys_str_mv AT chenheping realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation
AT shiyan realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation
AT bobin realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation
AT zhaodenghui realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation
AT miaopeng realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation
AT tongshanbao realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation
AT wangchunliang realtimecerebralvesselsegmentationinlaserspecklecontrastimagebasedonunsuperviseddomainadaptation