Learning and modeling biosignatures from tissue images
| Autor: | Julie A. Hutt, Robert Veroff, Frank L. Gilfeather, Vikas Hamine, Paul Helman, Terry A. Loring, C. Rick Lyons |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
Lung Diseases
Population Feature extraction Health Informatics Biology Infections Machine learning computer.software_genre Mice Artificial Intelligence Image Interpretation Computer-Assisted Animals Humans Computer Simulation Diagnosis Computer-Assisted education Lung education.field_of_study business.industry Bayesian network Bayes Theorem Computer Science Applications Chemical agents Risk stratification Identification (biology) Artificial intelligence Lung tissue business computer Algorithms |
| Zdroj: | Computers in Biology and Medicine. 37:1539-1552 |
| ISSN: | 0010-4825 |
| DOI: | 10.1016/j.compbiomed.2007.02.005 |
| Popis: | Ideally biosignatures can be detected at the early infection phase and used both for developing diagnostic patterns and for prognostic triage. Such biosignatures are important for vaccine validation and to provide risk stratification to a population such as for the identification of individuals who are exposed to biological or chemical agents and who are at high risk for developing an infection. The research goal is to detect broad based biosignature models and is initially focused on developing effective computer-augmented pathology tied to animal models developed at the University of New Mexico (UNM). Using lung tissue from infected and nai ve mice, feature extraction from images of the tissue under a specialized microscope, and Bayesian networks to analyze the data sets of features, we were able to differentiate normal from diseased samples and viral from bacterial samples in mid to late stages of infection. This effort has shown the potential effectiveness of computer-augmented pathology in this application. The extended research intends to couple analysis of serum, microarray analysis of organs, proteomic data and the pathology. The rational for the current invasive procedure on animal models is to facilitate the development of data analysis and machine learning techniques that can eventually be generalized to the task of discovering non-invasive and early stage biosignatures for human models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect