51
|
Lapierre-Landry M, Liu Z, Ling S, Bayat M, Wilson DL, Jenkins MW. Nuclei Detection for 3D Microscopy With a Fully Convolutional Regression Network. IEEE ACCESS : PRACTICAL INNOVATIONS, OPEN SOLUTIONS 2021; 9:60396-60408. [PMID: 35024261 PMCID: PMC8751907 DOI: 10.1109/access.2021.3073894] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Advances in three-dimensional microscopy and tissue clearing are enabling whole-organ imaging with single-cell resolution. Fast and reliable image processing tools are needed to analyze the resulting image volumes, including automated cell detection, cell counting and cell analytics. Deep learning approaches have shown promising results in two- and three-dimensional nuclei detection tasks, however detecting overlapping or non-spherical nuclei of different sizes and shapes in the presence of a blurring point spread function remains challenging and often leads to incorrect nuclei merging and splitting. Here we present a new regression-based fully convolutional network that located a thousand nuclei centroids with high accuracy in under a minute when combined with V-net, a popular three-dimensional semantic-segmentation architecture. High nuclei detection F1-scores of 95.3% and 92.5% were obtained in two different whole quail embryonic hearts, a tissue type difficult to segment because of its high cell density, and heterogeneous and elliptical nuclei. Similar high scores were obtained in the mouse brain stem, demonstrating that this approach is highly transferable to nuclei of different shapes and intensities. Finally, spatial statistics were performed on the resulting centroids. The spatial distribution of nuclei obtained by our approach most resembles the spatial distribution of manually identified nuclei, indicating that this approach could serve in future spatial analyses of cell organization.
Collapse
Affiliation(s)
- Maryse Lapierre-Landry
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
| | - Zexuan Liu
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
| | - Shan Ling
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
| | - Mahdi Bayat
- Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH 44106, USA
| | - David L Wilson
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
- Department of Radiology, Case Western Reserve University, Cleveland, OH 44106, USA
| | - Michael W Jenkins
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
- Department of Pediatrics, Case Western Reserve University, Cleveland, OH 44106, USA
| |
Collapse
|
52
|
Kalita-de Croft P, Sadeghi Rad H, Gasper H, O'Byrne K, Lakhani SR, Kulasinghe A. Spatial profiling technologies and applications for brain cancers. Expert Rev Mol Diagn 2021; 21:323-332. [PMID: 33685321 DOI: 10.1080/14737159.2021.1900735] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
INTRODUCTION Malignant primary and secondary brain tumors pose a major health challenge, and the incidence of these tumors is rising. The brain tumor microenvironment (TME) is highly complex and thought to impact treatment resistance and failure. To enable a greater understanding of the milieu of cells in the brain TME, advances in imaging and sequential profiling of proteins/mRNA have given rise to the field of spatial transcriptomics. These technologies provide a greater depth of understanding of the tissue architecture, cellular and spatial profiles, including cellular activation status, which may provide insights into effective therapies for brain cancers. AREAS COVERED In this review, we provide an overview of spatial profiling technologies at the forefront in the field and describe the applications for brain cancer. EXPERT OPINION Brain tumors are often resistant to treatment, and display both an immunosuppressive and heterogeneous tumor microenvironment. Next-generation imaging and multi-omics technologies are providing a tool for intricately characterizing their tissue biology. This information will aid in the design of effective therapies and begin to provide an understanding of therapy resistance.
Collapse
Affiliation(s)
- Priyakshi Kalita-de Croft
- UQ Centre for Clinical Research, Faculty of Medicine, The University of Queensland, Brisbane, Australia
| | - Habib Sadeghi Rad
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Harry Gasper
- Department of Medical Oncology, Royal Brisbane and Women's Hospital, Herston, Australia.,School of Medicine, University of Queensland, Herston, Queensland, Australia
| | - Ken O'Byrne
- The School of Biomedical Sciences, Institute of Health and Biomedical Innovation, Queensland University ofTechnology, Woolloongabba, Queensland, Australia.,Translational Research Institute, Brisbane, Queensland, Australia.,Princess Alexandra Hospital, Brisbane, Queensland, Australia
| | - Sunil R Lakhani
- UQ Centre for Clinical Research, Faculty of Medicine, The University of Queensland, Brisbane, Australia.,Pathology Queensland, The Royal Brisbane and Women's Hospital Herston, Queensland, Australia
| | - Arutha Kulasinghe
- The School of Biomedical Sciences, Institute of Health and Biomedical Innovation, Queensland University ofTechnology, Woolloongabba, Queensland, Australia.,Translational Research Institute, Brisbane, Queensland, Australia
| |
Collapse
|