ABSTRACT
Optical-resolution photoacoustic microcopy (OR-PAM) is a non-invasive imaging technology that can achieve high-resolution vascular imaging and has been widely used in the field of vessel segmentation. Due to the low contrast of photoacoustic microvessel images and the discontinuity of vessels, existing vessel segmentation methods have some shortcomings: the accuracy of capillary extraction is insufficient, it is difficult to extract thick and thin vessels at the same time, and the vessels have deformed in some segmentation results. Therefore, we propose a deep learning network (RA-MP-Net) that integrates the residual attention(RA) module and the multi-scale perception (MP) module. Among them, RA module can focus on the vascular region in the image, and MP module can aggregate multi-scale vessel features. We conduct experiments on the normal vessel dataset from OR-PAM. Compared with existing work, the proposed microvascular segmentation algorithm can extract thick and thin vessels more accurately and continuously. In quantitative analysis, compared with the previously proposed 2D deep learning method, our evaluation indicators improved by 2.4%∽10.6%. The improvement in the accuracy of extracting vessels using our method is helpful for the diagnosis and evaluation of microvascular diseases.
- Chuncheng Zhang, Guodong Liu, Zhihua Xie, Zhenghua Shu, Zhong Ren, and Qingkai Yao. 2021. Vascular recognition system based on photoacoustic detection. Journal of Laser Applications 33,1 (Febuary 2021), 012051. https://doi.org/10.2351/7.0000261Google ScholarCross Ref
- Leli Zeng, Gongcheng Ma, Jing Lin, and Peng Huang. 2018. Photoacoustic Probes for Molecular Detection: Recent Advances and Perspectives. Small 14, 30 (June 2018), 1800782. https://doi.org/10.1002/smll.201800782Google ScholarCross Ref
- Yinhao Pan, Ningbo Chen, Liangjian Liu, Chengbo Liu, Zhiqiang Xu, and Jianhui Zhang. 2021. Recovery of photoacoustic images based on accurate ultrasound positioning. Visual Computing for Industry, Biomedicine, and Art 4,1 (March 2021), 1-7. https://doi.org/10.1186/s42492-021-00072-2Google ScholarCross Ref
- Myeongsu Seong, and Sung-Liang Chen. 2020. Recent advances toward clinical applications of photoacoustic microscopy: a review. Science China Life Sciences 63 (May 2020), 1798-1812. https://doi.org/10.1007/s11427-019-1628-7Google ScholarCross Ref
- Yiwen Zheng, Mengyao Liu, and Lixin Jiang. 2022. Progress of photoacoustic imaging combined with targeted photoacoustic contrast agents in tumor molecular imaging. Frontiers in Chemistry 10 (November 2022), 1077937. https://doi.org/10.3389/fchem.2022.1077937Google ScholarCross Ref
- Rui Cao, Chenchu Zhang, Vladimir V. Mitkin, Miles F. Lankford, Jun Li, Zhiyi Zuo, Craig H. Meyer, Christopher P. Goyne, Stephen T. Ahlers, James R. Stone, and Song Hu. 2019. Comprehensive Characterization of Cerebrovascular Dysfunction in Blast Traumatic Brain Injury Using Photoacoustic Microscopy. Journal of Neurotrauma 36, 10 (May 2019), 1526-1534. https://doi.org/10.1089/neu.2018.6062Google ScholarCross Ref
- M. Toi, Y. Asao, Y. Matsumoto, H. Sekiguchi, A. Yoshikawa, M. Takada, M. Kataoka, T. Endo, N. Kawaguchi-Sakita, M. Kawashima, E. Fakhrejahani, S. Kanao, I. Yamaga, Y. Nakayama, M. Tokiwa, M. Torii, T. Yagi, T. Sakurai, K. Togashi, and T. Shiina. 2017. Visualization of tumor-related blood vessels in human breast by photoacoustic imaging system with a hemispherical detector array. Scientific Reports 7, 1 (February 2017), 41970. https://doi.org/10.1038/srep41970Google ScholarCross Ref
- Dongfang Li, Manli Zhao, Chao Tao, Xiaoqin Qian, and Xiaojun Liu. 2023. High-resolution in vivo imaging of human nailbed microvasculature by using photoacoustic microscopy. Journal of Biophotonics 16, 8 (May 2023), e202300058. https://doi.org/10.1002/jbio.202300058Google ScholarCross Ref
- Riqiang Lin, Jianhua Chen, Huina Wang, Meng Yan, Wei Zheng, and Liang Song. 2015. Longitudinal label-free optical-resolution photoacoustic microscopy of tumor angiogenesis in vivo. Quantitative Imaging in Medicine and Surgery 5, 1 (February 2015), 23. https://doi.org/10.3978/j.issn.2223-4292.2014.11.08Google ScholarCross Ref
- Brian Soetikno, Song Hu, Ernie Gonzales, Qiaonan Zhong, Konstantin Maslov, Jin-Moo Lee, and Lihong V. Wang. 2012. Vessel segmentation analysis of ischemic stroke images acquired with photoacoustic microscopy. In Proceedings of the Photons Plus Ultrasound: Imaging and Sensing 2012 Vol. 8223, pp. 765-769. SPIE. https://doi.org/10.1117/12.911089Google ScholarCross Ref
- Zhenyuan Yang, Jianhua Chen, Junjie Yao, Riqiang Lin, Jing Meng, Chengbo Liu, Jinhua Yang, Xiang Li, Lihong Wang, and Liang Song. 2014. Multi-parametric quantitative microvascular imaging with optical-resolution photoacoustic microscopy in vivo. Optics Express 22, 2 (January 2014), 1500-1511. https://doi.org/10.1364/OE.22.001500Google ScholarCross Ref
- Huangxuan Zhao, Guangsong Wang, Riqiang Lin, Xiaojing Gong, Liang Song, Tan Li, Wenjia Wang, Kunya Zhang, Xiuqing Qian, Haixia Zhang, Lin Li, Zhicheng Liu, and Chengbo Liu. 2018. Three-dimensional Hessian matrix-based quantitative vascular imaging of rat iris with optical-resolution photoacoustic microscopy in vivo. Journal of Biomedical Optics 23, 4 (April 2018), 046006. https://doi.org/10.1117/1.JBO.23.4.046006Google ScholarCross Ref
- Qian Zhao, Riqiang Lin, Chengbo Liu, Jingxiu Zhao, Guangtao Si, Liang Song, and Jing Meng. 2019. Quantitative analysis on in vivo tumor-microvascular images from optical-resolution photoacoustic microscopy. Journal of Biophotonics 12, 6 (February 2019), e201800421. https://doi.org/10.1002/jbio.201800421Google ScholarCross Ref
- Mingjian Sun, Chao Li, Ningbo Chen, Huangxuan Zhao, Liyong Ma, Chengbo Liu, Yi Shen, Riqiang Lin, and Xiaojing Gong. 2020. Full three-dimensional segmentation and quantification of tumor vessels for photoacoustic images. Photoacoustics 20 (December 2020), 100212. https://doi.org/10.1016/j.pacs.2020.100212Google ScholarCross Ref
- Thi Thao Mai 1, Su Woong Yoo, Suhyun Park, Jin Young Kim, Kang-Ho Choi, Chulhong Kim, Seong Young Kwon, Jung-Joon Min and Changho Lee. 2021. In Vivo Quantitative Vasculature Segmentation and Assessment for Photodynamic Therapy Process Monitoring Using Photoacoustic Microscopy. Sensors 21, 5 (March 2021), 1776. https://doi.org/10.3390/s21051776Google ScholarCross Ref
- Ting Liu, Mingjian Sun, Naizhang Feng, Zhenghua Wu, and Yi Shen. 2015. Multiscale Hessian filter-based segmentation and quantification method for photoacoustic microangiography. Chinese Optics Letters 13, 9 (August 2015), 091701. http://dx.doi.org/10.3788/COL201513.091701Google ScholarCross Ref
- Alan Yilun Yuan, Yang Gao, Liangliang Peng, Lingxiao Zhou, Jun Liu, Siwei Zhu, and Wei Song. 2020. Hybrid deep learning network for vascular segmentation in photoacoustic imaging. Biomedical Optics Express 11, 11 (November 2020), 6445-6457. https://doi.org/10.1364/BOE.409246Google ScholarCross Ref
- Huangxuan Zhao, Jia Huang, Qiang Zhou, Ningbo Chen, Liangjian Liu, Xinggang Wang, Tao Wang, Leqing Chen, Chengbo Liu, Chuansheng Zheng, and Fan Yang. 2022. Deep Learning-Based Optical-Resolution Photoacoustic Microscopy for In Vivo 3D Microvasculature Imaging and Segmentation. Advanced Intelligent Systems 4, 9 (June 2022), 2200004. https://doi.org/10.1002/aisy.202200004Google ScholarCross Ref
- Chunwei Tian, Yong Xu, Zuoyong Li, Wangmeng Zuo, Lunke Fei, and Hong Liu. 2020. Attention-guided CNN for image denoising. Neural Networks, 124 (April 2020), 117-129. https://doi.org/10.1016/j.neunet.2019.12.024Google ScholarDigital Library
- Renlong Hang, Zhu Li, Qingshan Liu, Pedram Ghamisi, and Shuvra S. Bhattacharyya. 2020. Hyperspectral Image Classification With Attention-Aided CNNs. IEEE Transactions on Geoscience and Remote Sensing 59, 3 (March 2021), 2281-2293. https://doi.org/10.1109/TGRS.2020.3007921Google ScholarCross Ref
- Shoudong Han, and Xinyu Wang. 2015. Texture Segmentation Using Graph Cuts in Spectral Decomposition Based Riemannian Multi-scale Nonlinear Structure Tensor Space. International Journal of Computer Theory and Engineering 7, 4 (August 2015), 259. https://doi.org/10.7763/IJCTE.2015.V7.967Google ScholarCross Ref
- Tran Duy Linh, and Masayuki Arai. 2018. Multi-scale Subnetwork for Roi Pooling for Instance Segmentation. International Journal of Computer Theory and Engineering 10, 6 (December 2018), 207-211. https://doi.org/10.7763/IJCTE.2018.V10.1227Google ScholarCross Ref
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (pp. 234-241). Springer International Publishing. https://doi.org/10.1007/978-3-319-24574-4_28Google ScholarCross Ref
- Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, and Hannaneh Hajishirzi. 2018. ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 552-568). https://doi.org/10.48550/arXiv.1803.06815Google ScholarCross Ref
- Jianhua Chen, Riqiang Lin, Huina Wang, Jing Meng, Hairong Zheng, and Liang Song. 2013. Blind-deconvolution optical-resolution photoacoustic microscopy in vivo. Optics Express 21, 6 (March 2013), 7316-7327. https://doi.org/10.1364/OE.21.007316Google ScholarCross Ref
Index Terms
- RA-MP-Net: Residual attention and multi-scale perception network for microvasculature extraction in optical-resolution photoacoustic microscopy
Recommendations
U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina
Ophthalmic Medical Image AnalysisAbstractFundus photography has routinely been used to document the presence and severity of retinal degenerative diseases such as age-related macular degeneration (AMD), glaucoma, and diabetic retinopathy (DR) in clinical practice, for which the fovea and ...
ECG Arrhythmia Detection Based on Hidden Attention Residual Neural Network
Bioinformatics Research and ApplicationsAbstractArrhythmias such as atrial fibrillation (AFIB), atrial flutter (AFL), and ventricular fibrillation (VFIB) are early indicators of stroke and sudden cardiac death, and the electrocardiogram (ECG) provides vital information for arrhythmia detection. ...
Cell segmentation from telecentric bright-field transmitted light microscopy images using a Residual Attention U-Net: A case study on HeLa line
AbstractLiving cell segmentation from bright-field light microscopy images is challenging due to the image complexity and temporal changes in the living cells. Recently developed deep learning (DL)-based methods became popular in medical and microscopy ...
Graphical abstractDisplay Omitted
Highlights- U-Net-based segmentation of live cells in images acquired by high-resolution bright-field light transmission microscopy.
- The network contains the attention and residual modules in the U-Net.
- High segmentation accuracy compared with ...
Comments