Abstract
High-throughput imaging techniques, such as Knife-Edge Scanning Microscopy (KESM),are capable of acquiring three-dimensional whole-organ images at sub-micrometer resolution. These images are challenging to segment since they can exceed several terabytes (TB) in size, requiring extremely fast and fully automated algorithms. Staining techniques are limited to contrast agents that can be applied to large samples and imaged in a single pass. This requires maximizing the number of structures labeled in a single channel, resulting in images that are densely packed with spatial features. In this paper, we propose a three-dimensional approach for locating cells based on iterative voting. Due to the computational complexity of this algorithm, a highly efficient GPU implementation is required to make it practical on large data sets. The proposed algorithm has a limited number of input parameters and is highly parallel.
Highlights
Finding positions of cell nuclei is important for several biomedical applications, including cancer research (Dow et al, 1996), disease diagnosis (Zink et al, 2004), neurodegenerative disease research (Li et al, 2007a), and in vitro tracking (Merouane et al, 2015)
We demonstrate the effectiveness of the proposed algorithm on two groups of data: (1) nissl stained images collected using Knife-Edge Scanning Microscopy (KESM), and (2) 3D fluorescent images, including publicly available data sets
Since the pixel size of all of the sample images is known, we provide this value in micrometers, which makes our algorithm independent of sampling resolution and anisotropy
Summary
Finding positions of cell nuclei is important for several biomedical applications, including cancer research (Dow et al, 1996), disease diagnosis (Zink et al, 2004), neurodegenerative disease research (Li et al, 2007a), and in vitro tracking (Merouane et al, 2015). Several cell localization methods have been explored in the past few decades. They are mostly limited to two dimensional datasets, and the available three-dimensional (3D) algorithms are inaccurate, slow, or difficult to automate due to common variations in cell size, shape, and proximity. Recent advances in high-throughput imaging allow researchers to acquire images of whole brains (Yuan et al, 2015; Xiong et al, 2017) containing cellular data that is difficult to segment. Processing these data sets using traditional methods is time consuming and impractical
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
