ABSTRACT
Assessment of the perfusion state for capillaries provides important guidances in diagnosis and treatment of critically ill patients. A high-quality capture of video and image, convenient and effective analysis of vessels are the foundation of microcirculation assessment in clinical application. Here, we experimentally develop a sublingual microcirculation monitoring and imaging system that uses a front-end probe parallel to the bottom of tongue to control the force on sublingual tissues, and propose a U-Net based segmentation approach for extracting the vascular structures. Human sublingual microcirculation videos are acquired from both sidestream dark field and self-built imaging system to train and test the algorithm. The model locates most of blood vessels accurately and the area under receiver operating characteristic curve measure of the model achieves 0.95, which demonstrates an excellent performance and robustness of our algorithm.
- Piagnerelli, M., Ince, C., and Dubin, A. (2012). Microcirculation. Critical Care Research and Practice, 2012: 867176.Google ScholarCross Ref
- Sakr, Y., Dubois, M. J., De Backer, D., Creteur, J., and Vincent, J. L. (2004). Persistent microcirculatory alterations are associated with organ failure and death in patients with septic shock. Critical Care Medicine, 32(9), 1825-1831.Google ScholarCross Ref
- Edul, V. S. K., Enrico, C., Laviolle, B., Vazquez, A. R., Ince, C., and Dubin, A. (2012). Quantitative assessment of the microcirculation in healthy volunteers and in patients with septic shock. Critical Care Medicine, 40(5), 1443-1448..Google ScholarCross Ref
- Trzeciak, S., Dellinger, R. P., Parrillo, J. E., Guglielmi, M., Bajaj, J., Abate, N. L., Arnold, R.C., Colilla, S., Zanotti, S., Hollenberg, S.M., and in Resuscitation, M. A. (2007). Early microcirculatory perfusion derangements in patients with severe sepsis and septic shock: relationship to hemodynamics, oxygen transport, and survival. Annals of Emergency Medicine, 49(1), 88-98.Google ScholarCross Ref
- De Backer, D., Hollenberg, S., Boerma, C., Goedhart, P., Büchele, G., Ospina-Tascon, G., Dobbe, I., and Ince, C. (2007). How to evaluate the microcirculation: report of a round table conference. Critical Care, 11(5), 1-9.Google ScholarCross Ref
- Hilty, M. P., Guerci, P., Ince, Y., Toraman, F., and Ince, C. (2019). MicroTools enables automated quantification of capillary density and red blood cell velocity in handheld vital microscopy. Communications Biology, 2(1), 1-15.Google ScholarCross Ref
- Groner, W., Winkelman, J. W., Harris, A. G., Ince, C., Bouma, G. J., Messmer, K., and Nadeau, R. G. (1999). Orthogonal polarization spectral imaging: a new method for study of the microcirculation. Nature Medicine, 5(10), 1209-1212.Google ScholarCross Ref
- Goedhart, P. T., Khalilzada, M., Bezemer, R., Merza, J., and Ince, C. (2007). Sidestream Dark Field (SDF) imaging: a novel stroboscopic LED ring-based imaging modality for clinical assessment of the microcirculation. Optics Express, 15(23), 15101-15114.Google ScholarCross Ref
- Sherman, H., Klausner, S., and Cook, W. A. (1971). Incident dark-field illumination: a new method for microcirculatory study. Angiology, 22(5), 295-303.Google ScholarCross Ref
- Massey, M. J., and Shapiro, N. I. (2015). A guide to human in vivo microcirculatory flow image analysis. Critical Care, 20(1), 1-10.Google ScholarCross Ref
- Lindert, J., Werner, J., Redlin, M., Kuppe, H., Habazettl, H., and Pries, A. R. (2002). OPS imaging of human microcirculation: a short technical report. Journal of Vascular Research, 39(4), 368-372.Google ScholarCross Ref
- Balestra, G. M., Bezemer, R., Boerma, E. C., Yong, Z. Y., Sjauw, K. D., Engstrom, A. E., Koopmans, M., and Ince, C. (2010). Improvement of sidestream dark field imaging with an image acquisition stabilizer. BMC Medical Imaging, 10(1), 1-7.Google ScholarCross Ref
- Liu, C., Gomez, H., Narasimhan, S., Dubrawski, A., Pinsky, M. R., and Zuckerbraun, B. (2015). Real-time visual analysis of microvascular blood flow for critical care. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2217-2225.Google Scholar
- Mahmoud, O., Janssen, G. H., and El-Sakka, M. R. (2020). Machine-Learning-Based Functional Microcirculation Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, No. 08, pp. 13326-13331.Google ScholarCross Ref
- Ellis, C. G., Ellsworth, M. L., Pittman, R. N., and Burgess, W. L. (1992). Application of image analysis for evaluation of red blood cell dynamics in capillaries. Microvascular Research, 44(2), 214-225.Google ScholarCross Ref
- Steger, C. (1998). An unbiased detector of curvilinear structures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(2), 113-125.Google ScholarDigital Library
- Hashemzadeh, M., and Azar, B. A. (2019). Retinal blood vessel extraction employing effective image features and combination of supervised and unsupervised machine learning methods. Artificial Intelligence in Medicine, 95, 1-15.Google ScholarDigital Library
- Mo, J., and Zhang, L. (2017). Multi-level deep supervised networks for retinal vessel segmentation. International Journal of Computer Assisted Radiology and Surgery,12(12), 2181-2193.Google ScholarCross Ref
- Zhu, C., Zou, B., Zhao, R., Cui, J., Duan, X., Chen, Z., and Liang, Y. (2017). Retinal vessel segmentation in colour fundus images using extreme learning machine. Computerized Medical Imaging and Graphics, 55, 68-77.Google ScholarCross Ref
- Hu, K., Zhang, Z., Niu, X., Zhang, Y., Cao, C., Xiao, F., and Gao, X. (2018). Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function. Neurocomputing, 309, 179-191.Google ScholarDigital Library
- Demir, S., Mirshahi, N., Tiba, M. H., Draucker, G., Ward, K., Hobson, R., and Najarian, K. (2009). Image processing and machine learning for diagnostic analysis of microcirculation. ICME International Conference on Complex Medical Engineering, pp. 1-5.Google ScholarCross Ref
- Zuiderveld, K. (1994). Contrast limited adaptive histogram equalization. Graphics Gems, 474-485.Google ScholarCross Ref
- Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241.Google ScholarCross Ref
- Kingma, D. P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.Google Scholar
- Frangi, A. F., Niessen, W. J., Vincken, K. L., and Viergever, M. A. (1998). Multiscale vessel enhancement filtering. International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 130-137.Google ScholarDigital Library
- Lorenz, C., Carlsen, I. C., Buzug, T. M., Fassnacht, C., and Weese, J. (1997). Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images. International Conference on Computer Vision, Virtual Reality, and Robotics in Medicine, pp. 233-242.Google ScholarCross Ref
- Sato, Y., Nakajima, S., Atsumi, H., Koller, T., Gerig, G., Yoshida, S., and Kikinis, R. (1997). 3D multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. International Conference on Computer Vision, Virtual Reality, and Robotics in Medicine, pp. 213-222.Google ScholarCross Ref
Recommendations
A Fusion Based Approach for Blood Vessel Segmentation from Fundus Images by Separating Brighter Optic Disc
Abstract—In ophthalmology, blood vessel segmentation from fundus images plays a significant role in automated retinal disease screening systems. Several research papers on blood vessel segmentation suggest enhancing fundus images before segmentation ...
Assessment of Pain-Induced Changes in Cerebral Microcirculation by Imaging Photoplethysmography
Bioinformatics and Biomedical EngineeringAbstractEvaluation of the dynamics of cerebral blood flow during surgical treatment and during experiments with laboratory animals is an important component of assessment of physiological reactions of a body. None of the modern methods of hemodynamic ...
Blood vessel segmentation methodologies in retinal images - A survey
Retinal vessel segmentation algorithms are a fundamental component of automatic retinal disease screening systems. This work examines the blood vessel segmentation methodologies in two dimensional retinal images acquired from a fundus camera and a ...
Comments