Hostname: page-component-78c5997874-s2hrs Total loading time: 0 Render date: 2024-11-18T10:31:31.556Z Has data issue: false hasContentIssue false
  • English
  • Français

A Machine Learning Method for Automated In Vivo Transparent Vessel Segmentation and Identification Based on Blood Flow Characteristics

Published online by Cambridge University Press:  07 April 2022

Mingzhu Sun ,
Yiwen Wang Open the ORCID record for Yiwen Wang [Opens in a new window] ,
Zhenhua Fu ,
Lu Li ,
Yaowei Liu  and
Xin Zhao
Mingzhu Sun
Affiliation:
Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR), Nankai University, Tianjin 300350, China
Yiwen Wang
Affiliation:
Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR), Nankai University, Tianjin 300350, China
Zhenhua Fu
Affiliation:
Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR), Nankai University, Tianjin 300350, China
Lu Li
Affiliation:
Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR), Nankai University, Tianjin 300350, China
Yaowei Liu
Affiliation:
Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR), Nankai University, Tianjin 300350, China
Xin Zhao*
Affiliation:
Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR), Nankai University, Tianjin 300350, China
*
*Corresponding author: Xin Zhao, E-mail: zhaoxin@nankai.edu.cn
Get access

Abstract

In vivo transparent vessel segmentation is important to life science research. However, this task remains very challenging because of the fuzzy edges and the barely noticeable tubular characteristics of vessels under a light microscope. In this paper, we present a new machine learning method based on blood flow characteristics to segment the global vascular structure in vivo. Specifically, the videos of blood flow in transparent vessels are used as input. We use the machine learning classifier to classify the vessel pixels through the motion features extracted from moving red blood cells and achieve vessel segmentation based on a region-growing algorithm. Moreover, we utilize the moving characteristics of blood flow to distinguish between the types of vessels, including arteries, veins, and capillaries. In the experiments, we evaluate the performance of our method on videos of zebrafish embryos. The experimental results indicate the high accuracy of vessel segmentation, with an average accuracy of 97.98%, which is much more superior than other segmentation or motion-detection algorithms. Our method has good robustness when applied to input videos with various time resolutions, with a minimum of 3.125 fps.

Keywords

blood flowmachine learningmicroscopy imagesregion growingvessel segmentation
Type
Biological Applications
Information
Microscopy and Microanalysis , Volume 28 , Issue 3 , June 2022 , pp. 801 - 814
Copyright
Copyright © The Author(s), 2022. Published by Cambridge University Press on behalf of the Microscopy Society of America

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Alhussein, M, Aurangzeb, K & Haider, SI (2020). An unsupervised retinal vessel segmentation using Hessian and intensity based approach. IEEE Access 8, 165056–165070.CrossRefGoogle Scholar
Arcese, L, Fruchard, M & Ferreira, A (2013). Adaptive controller and observer for a magnetic microrobot. IEEE Trans Rob 29(4), 1060–1067.CrossRefGoogle Scholar
Barnich, O & Droogenbroeck, MV (2011). ViBe: A universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6), 1709–1724.CrossRefGoogle ScholarPubMed
Bartyzel, K (2016). Adaptive Kuwahara filter. Signal Image Video Process 10(4), 663–670.CrossRefGoogle Scholar
Cai, S, Tian, Y, Lui, H, Zeng, H, Wu, Y & Chen, G (2020). Dense-UNet: A novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network. Quantit Imaging Med Surg 10(6), 1275–1285.CrossRefGoogle ScholarPubMed
Chan, KG & Liebling, M (2015). Estimation of divergencefree 3D cardiac blood flow in a zebrafish larva using multi-view microscopy. In IEEE International Symposium on Biomedical Imaging. IEEE Press.Google Scholar
Cho, TS, Freeman, WT & Tsao, H (2007). A reliable skin mole localization scheme. In IEEE 11th International Conference on Computer Vision, pp. 1–8.CrossRefGoogle Scholar
Daien, V, Carriere, I, Kawasaki, R, Cristol, JP, Villain, M, Fesler, P, Ritchie, K & Delcourt, C (2013). Retinal vascular caliber is associated with cardiovascular biomarkers of oxidative stress and inflammation: The POLA study. PLoS One 8(7), e71089.CrossRefGoogle ScholarPubMed
Dong, HY, Kwon, D, Yun, ID & Sang, UL (2008). Fast multiscale vessel enhancement filtering. Proc SPIE Int Soc Opt Eng 6914, 691423.Google Scholar
Farnebck, G (2003). Two-frame motion estimation based on polynomial expansion. In 13th Scandinavian Conference on Image Analysis (SCIA 2003), Vol. 2749, pp. 363–370. Springer-Verlag.CrossRefGoogle Scholar
Feng, J, Cheng, SH, Chan, PK & Ip, HHS (2005). Reconstruction and representation of caudal vasculature of zebrafish embryo from confocal scanning laser fluorescence microscopic images. Comput Biol Med 35(10), 915–931.CrossRefGoogle ScholarPubMed
Flusser, J, Farokhi, S, Hoschl, C, Suk, T, Zitová, B & Pedone, M (2016). Recognition of images degraded by Gaussian blur. IEEE Trans Image Process 25(2), 790–806.CrossRefGoogle ScholarPubMed
Francia, GA, Pedraza, C, Aceves, M & Tovar-Arriaga, S (2020). Optics: Ordering points to identify the clustering structure. IEEE Access 8, 38493–38500.Google Scholar
Frangi, RF, Niessen, WJ, Vincken, KL & Viergever, MA (1998). Multiscale vessel enhancement filtering. In International Conference on Medical Image Computing & Computer-assisted Intervention, Vol. 1496.CrossRefGoogle Scholar
Guan, S, Khan, A, Sikdar, S & Chitnis, PV (2020). Fully dense UNet for 2D sparse photoacoustic tomography artifact removal. IEEE J Bio Health Inform 24(2), 568–576.CrossRefGoogle Scholar
Ip, H, Feng, JJ & Cheng, SH (2002). Automatic segmentation and tracking of vasculature from confocal scanning laser fluorescence microscope using multi-orientation dissections. In IEEE International Symposium on Biomedical Imaging, pp. 249–252. IEEE Press.CrossRefGoogle Scholar
İlk, HG, Jane, O & İlk, Ö (2011). The effect of Laplacian filter in adaptive unsharp masking for infrared image enhancement. Infrared Phys Technol 54(5), 427–438.CrossRefGoogle Scholar
Jodoin, PM & Mignotte, M (2005). Motion segmentation using a k-nearest-neighbor-based fusion procedure of spatial and temporal label cues. In Image Analysis and Recognition, Second International Conference, ICIAR, Vol. 3656, pp. 778–788. Springer.CrossRefGoogle Scholar
Kim, J, Um, S & Min, D (2018). Fast 2D complex Gabor filter with kernel decomposition. IEEE Trans Image Process 27(4), 1713–1722.CrossRefGoogle ScholarPubMed
Kugler, E, Plant, K, Chico, T & Armitage, PA (2019). Enhancement and segmentation workflow for the developing zebrafish vasculature. J Imaging 5, 14.CrossRefGoogle ScholarPubMed
Li, D, Zhang, G, Wu, Z & Yi, L (2010). An edge embedded marker-based watershed algorithm for high spatial resolution remote sensing image segmentation. IEEE Trans Image Process 19(10), 2781–2787.Google ScholarPubMed
Li, M, Liu, X & Feng, X (2019). Cardiovascular toxicity and anxiety-like behavior induced by deltamethrin in zebrafish (Danio rerio) larvae. Chemosphere 219(Mar), 155–164.CrossRefGoogle ScholarPubMed
Li, R, Zeng, T, Peng, H & Ji, S (2017). Deep learning segmentation of optical microscopy images improves 3-D neuron reconstruction. IEEE Trans Med Imaging 36(7), 1533–1541.CrossRefGoogle ScholarPubMed
Li, X, Chen, H, Qi, X, Dou, Q, Fu, CW & Heng, PA (2018). H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans Med Imaging 37(12), 2663–2674.CrossRefGoogle ScholarPubMed
Lorenz, C, Carlsen, IC, Buzug, TM, Fassnacht, C & Weese, J (1997). A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation. In Scale-Space Theory in Computer Vision. Lect Notes Comput Sci, Vol. 1252(1), pp. 152–163.CrossRefGoogle Scholar
Ma, Y, Hao, H, Xie, J, Fu, H, Zhang, J, Yang, J, Wang, Z, Liu, J, Zheng, Y & Zhao, Y (2021). ROSE: A retinal OCT-angiography vessel segmentation dataset and new model. IEEE Trans Med Imaging 40(3), 928–939.CrossRefGoogle ScholarPubMed
Menon, PG, Rochon, ER & Roman, BL (2016). In-vivo cell tracking to quantify endothelial cell migration during zebrafish angiogenesis. SPIE Medical Imaging. International Society for Optics and Photonics.Google Scholar
Oszust, M (2018). No-reference image quality assessment with local features and high-order derivatives. J Vis Commun Image Represent 56(Oct), 15–26.CrossRefGoogle Scholar
Otsu, N (2007). A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1), 62–66.CrossRefGoogle Scholar
Perona, P & Malik, J (1990). Scale space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7), 629–639.CrossRefGoogle Scholar
Phellan, R, Lindner, T, Helle, M, Falcao, AX & Forkert, ND (2018). Automatic temporal segmentation of vessels of the brain using 4D ASL MRA images. IEEE Trans Biomed Eng 65(7), 1486–1494.CrossRefGoogle ScholarPubMed
Rajalaxmi, S & Nirmala, S (2014). Entropy-based straight kernel filter for echocardiography image denoising. J Digit Imaging 27(5), 610–624.CrossRefGoogle ScholarPubMed
Rodrigues, EO, Conci, A & Liatsis, P (2020). Element: Multi-modal retinal vessel segmentation based on a coupled region growing and machine learning approach. IEEE J Bio Health Inform 24(12), 3507–3519.CrossRefGoogle ScholarPubMed
Schindelin, J, Arganda-Carreras, I, Frise, E, Kaynig, V, Longair, M, Pietzsch, T, Preibisch, S, Rueden, C, Saalfeld, S, Schmid, B, Tinevez, JY, White, DJ, Hartenstein, V, Eliceiri, K, Tomancak, P & Cardona, A (2012). Fiji: An open-source platform for biological-image analysis. Nat Methods 9(7), 676–682.CrossRefGoogle ScholarPubMed
Seidelmann, SB, Claggett, B, Bravo, P, Gupta, A, Farhad, H, Di Carli, M & Solomon, S (2016). Retina vessel caliber in atherosclerotic cardiovascular event prediction: The atherosclerosis in communities study. J Am Coll Cardiol 67(13), 1893.CrossRefGoogle Scholar
Staal, J, Abramoff, MD, Niemeijer, M, Viergever, MA & Ginneken, BV (2004). Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23(4), 501–509.CrossRefGoogle ScholarPubMed
Sun, M, Li, L, Yao, Y, Wang, Y, Gong, H, Gao, Q, Chen, D & Zhao, X (2021). Robotic cardinal vein microinjection of zebrafish larvae based on 3D positioning. In International Conference on Robotics and Automation, pp. 1256–1262.CrossRefGoogle Scholar
Vincent, L (1994).Morphological area openings and closings for grey-scale images. Shape in Picture 126, 197–208.CrossRefGoogle Scholar
Wang, C, Oda, M, Hayashi, Y, Yoshino, Y & Mori, K (2019). Tensor-cut: A tensor-based graph-cut blood vessel segmentation method and its application to renal artery segmentation. Med Image Anal 60, 101623.CrossRefGoogle ScholarPubMed
Wang, L & Pan, C (2014). Robust level set image segmentation via a local correntropy-based k-means clustering. Pattern Recognit 47(5), 1917–1925.CrossRefGoogle Scholar
Witten, IH, Frank, E & Hall, MA (2011). Data Mining: Practical Machine Learning Tools and Techniques. Amsterdam: Morgan Kaufmann, Elsevier.Google Scholar
Xu, R, Liu, T, Ye, X & Chen, YW (2020). Boosting connectivity in retinal vessel segmentation via a recursive semantics-guided network. In Medical Image Computing and Computer Assisted Intervention - MICCAI 2020 - 23rd International Conference, Vol. 12265, pp. 786–795.CrossRefGoogle Scholar
Xu, Y, Mao, Z, Liu, C & Wang, B (2018). Pulmonary vessel segmentation via stage-wise convolutional networks with orientation-based region growing optimization. IEEE Access 6, 71296–71305.CrossRefGoogle Scholar
Yaacoub, C & Daou, RAZ (2019). Fractional order sobel edge detector. In Ninth International Conference on Image Processing Theory, Tools and Applications, IPTA 2019, pp. 1–5. IEEE Press.CrossRefGoogle Scholar
Yan, Q, Wang, B, Zhang, W, Luo, C & You, Z (2020). An attention-guided deep neural network with multi-scale feature fusion for liver vessel segmentation. IEEE J Bio Health Inform 25(7), 2629–2642.CrossRefGoogle Scholar
Yang, WJ & Xu, JY (2017). Recognition of blood vessels in image of zebrafish embryo based on improved AdaBoost network. Transducer and Microsystem Technologies 36(8), 141–144.Google Scholar
Yip, RKH, Rimes, JS, Capaldo, BD, Vaillant, F, Mouchemore, KA, Pal, B, Chen, Y, Surgenor, E, Murphy, AJ, Anderson, RL, Smyth, GK, Lindeman, GJ, Hawkins, ED & Visvader, JE (2021). Mammary tumour cells remodel the bone marrow vascular microenvironment to support metastasis. Nat Commun 12, 6920.CrossRefGoogle ScholarPubMed
Zhang, K, Zhang, H, Zhou, H, Crookes, D, Li, L, Shao, Y & Liu, D (2019). Zebrafish embryo vessel segmentation using a novel dual ResUNet model. Comput Intell Neurosci 2019, 1–14.Google ScholarPubMed
Zhao, H, Li, H & Cheng, L (2019). Improving retinal vessel segmentation with joint local loss by matting. Pattern Recognit 98, 107068.CrossRefGoogle Scholar
Zivkovic, Z & Heijden, F (2006). Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognit Lett 27(7), 773–780.CrossRefGoogle Scholar
Supplementary material: File

Sun et al. supplementary material

Sun et al. supplementary material

Download Sun et al. supplementary material(File)
File 4.3 KB