Muhammad Jamal Afridi1, Arun Ross1, Xiaoming Liu1, Margaret F Bennewitz2, Dorela D Shuboni3, Erik M Shapiro3. 1. Department of Computer Science and Engineering, Michigan State University, East Lansing, Michigan, USA. 2. Vascular Medicine Institute, University of Pittsburgh, Pittsburgh, Pennsylvania, USA. 3. Department of Radiology, Michigan State University, East Lansing, Michigan, USA.
Abstract
PURPOSE: Magnetic resonance imaging (MRI)-based cell tracking has emerged as a useful tool for identifying the location of transplanted cells, and even their migration. Magnetically labeled cells appear as dark contrast in T2*-weighted MRI, with sensitivities of individual cells. One key hurdle to the widespread use of MRI-based cell tracking is the inability to determine the number of transplanted cells based on this contrast feature. In the case of single cell detection, manual enumeration of spots in three-dimensional (3D) MRI in principle is possible; however, it is a tedious and time-consuming task that is prone to subjectivity and inaccuracy on a large scale. This research presents the first comprehensive study on how a computer-based intelligent, automatic, and accurate cell quantification approach can be designed for spot detection in MRI scans. METHODS: Magnetically labeled mesenchymal stem cells (MSCs) were transplanted into rats using an intracardiac injection, accomplishing single cell seeding in the brain. T2*-weighted MRI of these rat brains were performed where labeled MSCs appeared as spots. Using machine learning and computer vision paradigms, approaches were designed to systematically explore the possibility of automatic detection of these spots in MRI. Experiments were validated against known in vitro scenarios. RESULTS: Using the proposed deep convolutional neural network (CNN) architecture, an in vivo accuracy up to 97.3% and in vitro accuracy of up to 99.8% was achieved for automated spot detection in MRI data. CONCLUSION: The proposed approach for automatic quantification of MRI-based cell tracking will facilitate the use of MRI in large-scale cell therapy studies. Magn Reson Med 78:1991-2002, 2017.
PURPOSE: Magnetic resonance imaging (MRI)-based cell tracking has emerged as a useful tool for identifying the location of transplanted cells, and even their migration. Magnetically labeled cells appear as dark contrast in T2*-weighted MRI, with sensitivities of individual cells. One key hurdle to the widespread use of MRI-based cell tracking is the inability to determine the number of transplanted cells based on this contrast feature. In the case of single cell detection, manual enumeration of spots in three-dimensional (3D) MRI in principle is possible; however, it is a tedious and time-consuming task that is prone to subjectivity and inaccuracy on a large scale. This research presents the first comprehensive study on how a computer-based intelligent, automatic, and accurate cell quantification approach can be designed for spot detection in MRI scans. METHODS: Magnetically labeled mesenchymal stem cells (MSCs) were transplanted into rats using an intracardiac injection, accomplishing single cell seeding in the brain. T2*-weighted MRI of these rat brains were performed where labeled MSCs appeared as spots. Using machine learning and computer vision paradigms, approaches were designed to systematically explore the possibility of automatic detection of these spots in MRI. Experiments were validated against known in vitro scenarios. RESULTS: Using the proposed deep convolutional neural network (CNN) architecture, an in vivo accuracy up to 97.3% and in vitro accuracy of up to 99.8% was achieved for automated spot detection in MRI data. CONCLUSION: The proposed approach for automatic quantification of MRI-based cell tracking will facilitate the use of MRI in large-scale cell therapy studies. Magn Reson Med 78:1991-2002, 2017.
Authors: Piotr Walczak; Jian Zhang; Assaf A Gilad; Dorota A Kedziorek; Jesus Ruiz-Cabello; Randell G Young; Mark F Pittenger; Peter C M van Zijl; Judy Huang; Jeff W M Bulte Journal: Stroke Date: 2008-03-06 Impact factor: 7.914
Authors: Ping Wang; Christian Schuetz; Prashanth Vallabhajosyula; Zdravka Medarova; Aseda Tena; Lingling Wei; Kazuhiko Yamada; Shaoping Deng; James F Markmann; David H Sachs; Anna Moore Journal: Transplantation Date: 2015-08 Impact factor: 4.939
Authors: Yijen L Wu; Qing Ye; Danielle F Eytan; Li Liu; Bedda L Rosario; T Kevin Hitchens; Fang-Cheng Yeh; Nico Rooijen van; Chien Ho Journal: Circ Cardiovasc Imaging Date: 2013-10-04 Impact factor: 7.792
Authors: Edwin J Baldelomar; Jennifer R Charlton; Scott C Beeman; Bradley D Hann; Luise Cullen-McEwen; Valeria M Pearl; John F Bertram; Teresa Wu; Min Zhang; Kevin M Bennett Journal: Kidney Int Date: 2016-02 Impact factor: 10.612