Anna Maria Masci1, Scott White2, Ben Neely3, Maryanne Ardini-Polaske4, Carol B Hill5, Ravi S Misra6, Bruce Aronow7, Nathan Gaddis4, Lina Yang2, Susan E Wert8, Scott M Palmer9, Cliburn Chan2. 1. Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA. annamaria.masci@duke.edu. 2. Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, USA. 3. Duke Crucible, Duke University, Durham, NC, USA. 4. RTI International, Research Triangle Park, NC, USA. 5. Duke Clinical Research Institute, Duke School of Medicine, Durham, NC, USA. 6. Department of Pediatrics, University of Rochester Medical Center, Rochester, NY, USA. 7. Departments of Biomedical Informatics, Developmental Biology, and Pediatrics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 8. Department of Pediatrics Perinatal Institute Divisions of Neonatology, Perinatal and Pulmonary Biology Cincinnati Children's Hospital Medical Center/Research Foundation, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 9. Vice Chair for Research, Department of Medicine, Director, Respiratory Research, Duke Clinical Research Institute, Duke University Medical Center, Durham, NC, USA.
Abstract
BACKGROUND: Immunofluorescent confocal microscopy uses labeled antibodies as probes against specific macromolecules to discriminate between multiple cell types. For images of the developmental mouse lung, these cells are themselves organized into densely packed higher-level anatomical structures. These types of images can be challenging to segment automatically for several reasons, including the relevance of biomedical context, dependence on the specific set of probes used, prohibitive cost of generating labeled training data, as well as the complexity and dense packing of anatomical structures in the image. The use of an application ontology helps surmount these challenges by combining image data with its metadata to provide a meaningful biological context, modeled after how a human expert would make use of contextual information to identify histological structures, that constrains and simplifies the process of segmentation and object identification. RESULTS: We propose an innovative approach for the semi-supervised analysis of complex and densely packed anatomical structures from immunofluorescent images that utilizes an application ontology to provide a simplified context for image segmentation and object identification. We describe how the logical organization of biological facts in the form of an ontology can provide useful constraints that facilitate automatic processing of complex images. We demonstrate the results of ontology-guided segmentation and object identification in mouse developmental lung images from the Bioinformatics REsource ATlas for the Healthy lung database of the Molecular Atlas of Lung Development (LungMAP1) program CONCLUSION: We describe a novel ontology-guided approach to segmentation and classification of complex immunofluorescence images of the developing mouse lung. The ontology is used to automatically generate constraints for each image based on its biomedical context, which facilitates image segmentation and classification.
BACKGROUND: Immunofluorescent confocal microscopy uses labeled antibodies as probes against specific macromolecules to discriminate between multiple cell types. For images of the developmental mouse lung, these cells are themselves organized into densely packed higher-level anatomical structures. These types of images can be challenging to segment automatically for several reasons, including the relevance of biomedical context, dependence on the specific set of probes used, prohibitive cost of generating labeled training data, as well as the complexity and dense packing of anatomical structures in the image. The use of an application ontology helps surmount these challenges by combining image data with its metadata to provide a meaningful biological context, modeled after how a human expert would make use of contextual information to identify histological structures, that constrains and simplifies the process of segmentation and object identification. RESULTS: We propose an innovative approach for the semi-supervised analysis of complex and densely packed anatomical structures from immunofluorescent images that utilizes an application ontology to provide a simplified context for image segmentation and object identification. We describe how the logical organization of biological facts in the form of an ontology can provide useful constraints that facilitate automatic processing of complex images. We demonstrate the results of ontology-guided segmentation and object identification in mouse developmental lung images from the Bioinformatics REsource ATlas for the Healthy lung database of the Molecular Atlas of Lung Development (LungMAP1) program CONCLUSION: We describe a novel ontology-guided approach to segmentation and classification of complex immunofluorescence images of the developing mouse lung. The ontology is used to automatically generate constraints for each image based on its biomedical context, which facilitates image segmentation and classification.
Authors: Alexander D Diehl; Alison Deckhut Augustine; Judith A Blake; Lindsay G Cowell; Elizabeth S Gold; Timothy A Gondré-Lewis; Anna Maria Masci; Terrence F Meehan; Penelope A Morel; Anastasia Nijnik; Bjoern Peters; Bali Pulendran; Richard H Scheuermann; Q Alison Yao; Martin S Zand; Christopher J Mungall Journal: J Biomed Inform Date: 2010-02-01 Impact factor: 6.317
Authors: Terrence F Meehan; Anna Maria Masci; Amina Abdulla; Lindsay G Cowell; Judith A Blake; Christopher J Mungall; Alexander D Diehl Journal: BMC Bioinformatics Date: 2011-01-05 Impact factor: 3.169
Authors: Christopher J Mungall; Carlo Torniai; Georgios V Gkoutos; Suzanna E Lewis; Melissa A Haendel Journal: Genome Biol Date: 2012-01-31 Impact factor: 13.583
Authors: Barry Smith; Werner Ceusters; Bert Klagges; Jacob Köhler; Anand Kumar; Jane Lomax; Chris Mungall; Fabian Neuhaus; Alan L Rector; Cornelius Rosse Journal: Genome Biol Date: 2005-04-28 Impact factor: 13.583
Authors: Maryanne E Ardini-Poleske; Robert F Clark; Charles Ansong; James P Carson; Richard A Corley; Gail H Deutsch; James S Hagood; Naftali Kaminski; Thomas J Mariani; Steven S Potter; Gloria S Pryhuber; David Warburton; Jeffrey A Whitsett; Scott M Palmer; Namasivayam Ambalavanan Journal: Am J Physiol Lung Cell Mol Physiol Date: 2017-08-10 Impact factor: 5.464
Authors: Anna Maria Masci; Cecilia N Arighi; Alexander D Diehl; Anne E Lieberman; Chris Mungall; Richard H Scheuermann; Barry Smith; Lindsay G Cowell Journal: BMC Bioinformatics Date: 2009-02-25 Impact factor: 3.169
Authors: Darren A Natale; Cecilia N Arighi; Judith A Blake; Carol J Bult; Karen R Christie; Julie Cowart; Peter D'Eustachio; Alexander D Diehl; Harold J Drabkin; Olivia Helfer; Hongzhan Huang; Anna Maria Masci; Jia Ren; Natalia V Roberts; Karen Ross; Alan Ruttenberg; Veronica Shamovsky; Barry Smith; Meher Shruti Yerramalla; Jian Zhang; Aisha AlJanahi; Irem Çelen; Cynthia Gan; Mengxi Lv; Emily Schuster-Lezell; Cathy H Wu Journal: Nucleic Acids Res Date: 2013-11-21 Impact factor: 16.971