In-vivo full-field measurement of microcirculatory blood flow velocity based on intelligent object identification

Abstract. Microcirculation plays a crucial role in delivering oxygen and nutrients to living tissues and in removing metabolic wastes from the human body. Monitoring the velocity of blood flow in microcirculation is essential for assessing various diseases, such as diabetes, cancer, and critical illnesses. Because of the complex morphological pattern of the capillaries, both in-vivo capillary identification and blood flow velocity measurement by conventional optical capillaroscopy are challenging. Thus, we focused on developing an in-vivo optical microscope for capillary imaging, and we propose an in-vivo full-field flow velocity measurement method based on intelligent object identification. The proposed method realizes full-field blood flow velocity measurements in microcirculation by employing a deep neural network to automatically identify and distinguish capillaries from images. In addition, a spatiotemporal diagram analysis is used for flow velocity calculation. In-vivo experiments were conducted, and the images and videos of capillaries were collected for analysis. We demonstrated that the proposed method is highly accurate in performing full-field blood flow velocity measurements in microcirculation. Further, because this method is simple and inexpensive, it can be effectively employed in clinics.

[1]  Ruikang K. Wang,et al.  Capillary blood flow imaging within human finger cuticle using optical microangiography , 2015, Journal of biophotonics.

[2]  Samuel J. Yang,et al.  In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images , 2018, Cell.

[3]  Yibo Zhang,et al.  Deep Learning Microscopy , 2017, ArXiv.

[4]  M. Furue,et al.  High Speed Digital Video Capillaroscopy: Nailfold Capillary Shape Analysis and Red Blood Cell Velocity Measurement , 2007 .

[5]  Wiendelt Steenbergen,et al.  Laser speckle contrast imaging: theoretical and practical limitations , 2013, Journal of biomedical optics.

[6]  R.A. Zoroofi,et al.  Automatic extraction and measurement of leukocyte motion in microvessels using spatiotemporal image analysis , 1997, IEEE Transactions on Biomedical Engineering.

[7]  Ivanov Kp,et al.  Microcirculation velocity changes under hypoxia in brain, muscles, liver, and their physiological significance , 1985 .

[8]  G M Collins,et al.  Blood flow in the microcirculation. , 1966, Pacific medicine and surgery.

[9]  Ata Mahjoubfar,et al.  Deep Learning in Label-free Cell Classification , 2016, Scientific Reports.

[10]  Álvaro Sánchez-Ferro,et al.  Non-invasive detection of severe neutropenia in chemotherapy patients by optical imaging of nailfold microcirculation , 2018, Scientific Reports.

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  M Watanabe,et al.  The time-space correlation method for measurement of erythrocyte velocity in microvessels using a CCD linear image sensor. , 1991, Microvascular research.

[13]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[14]  Xiaobo Zhou,et al.  Red Blood Cell Tracking Using Optical Flow Methods , 2014, IEEE Journal of Biomedical and Health Informatics.

[15]  Christopher J. Taylor,et al.  Improved Diagnosis of Systemic Sclerosis Using Nailfold Capillary Flow , 2016, MICCAI.

[16]  Christopher J. Taylor,et al.  An Automated System for Detecting and Measuring Nailfold Capillaries , 2014, MICCAI.

[17]  Gabriel Popescu,et al.  Imaging red blood cell dynamics by quantitative phase microscopy. , 2008, Blood cells, molecules & diseases.

[18]  Graham Dunn,et al.  Comparison of thermography and laser Doppler imaging in the assessment of Raynaud's phenomenon. , 2003, Microvascular research.

[19]  I M Braverman,et al.  Ultrastructure and organization of the cutaneous microvasculature in normal and pathologic states. , 1989, The Journal of investigative dermatology.

[20]  Perikumar Javia,et al.  Machine Learning Algorithms for Classification of Microcirculation Images from Septic and Non-septic Patients , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[21]  Christopher G Ellis,et al.  Automated Method for Tracking Individual Red Blood Cells Within Capillaries to Compute Velocity and Oxygen Saturation , 2005, Microcirculation.

[22]  Christopher J. Taylor,et al.  Automated structure and flow measurement — a promising tool in nailfold capillaroscopy , 2018, Microvascular research.

[23]  Krzysztof Krawiec,et al.  Segmenting Retinal Blood Vessels With Deep Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[24]  Levkovich YuI,et al.  Microcirculation velocity changes under hypoxia in brain, muscles, liver, and their physiological significance. , 1985, Microvascular research.

[25]  Dan Zhu,et al.  Visualization of skin microvascular dysfunction of type 1 diabetic mice using in vivo skin optical clearing method , 2018, Journal of biomedical optics.

[26]  Vyacheslav Kalchenko,et al.  Label free in vivo laser speckle imaging of blood and lymph vessels. , 2012, Journal of biomedical optics.

[27]  Nicu Sebe,et al.  Computer Vision – ECCV 2016 , 2016, Lecture Notes in Computer Science.

[28]  Yan Song,et al.  Inception Single Shot MultiBox Detector for object detection , 2017, 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[29]  Gerhard Gompper,et al.  Modeling microcirculatory blood flow: current state and future perspectives , 2016, Wiley interdisciplinary reviews. Systems biology and medicine.

[30]  Philippe Bonnin,et al.  Noninvasive assessment of endothelial function in the skin microcirculation. , 2010, American journal of hypertension.

[31]  J D Briers,et al.  Laser speckle contrast analysis (LASCA): a nonscanning, full-field technique for monitoring capillary blood flow. , 1996, Journal of biomedical optics.

[32]  D. Goldman,et al.  Comparison of Generated Parallel Capillary Arrays to Three‐Dimensional Reconstructed Capillary Networks in Modeling Oxygen Transport in Discrete Microvascular Volumes , 2013, Microcirculation.

[33]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[34]  Tianfu Wang,et al.  A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images , 2016, IEEE Transactions on Medical Imaging.

[35]  Khalid Saeed,et al.  K3M: A universal algorithm for image skeletonization and a review of thinning techniques , 2010, Int. J. Appl. Math. Comput. Sci..

[36]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[37]  Nobuhiko Hata,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 , 2014, Lecture Notes in Computer Science.

[38]  Geoffrey Zhang,et al.  Red blood cell velocity measurements of complete capillary in finger nail-fold using optical flow estimation. , 2009, Microvascular research.