Targeted computational analysis of the C3HEB/FEJ mouse model for drug efficacy testing

Asay, Bryce Clifford, author
Lenaerts, Anne J., advisor
Belisle, John, committee member
Munsky, Brian, committee member
Lyons, Michael, committee member
Journal Title
Journal ISSN
Volume Title
Efforts to develop effective and safe drugs for the treatment of tuberculosis (TB) require preclinical evaluation in animal models. Alongside efficacy testing of novel therapies, effects on pulmonary pathology and disease progression are monitored by using histopathology images from these infected animals. To compare the severity of disease across treatment cohorts, pathologists have historically assigned a semi-quantitative histopathology score that may be subjective in terms of their training, experience, and personal bias. Manual histopathology, therefore, has limitations regarding reproducibility between studies and pathologists, potentially masking successful treatments. This report describes a pathologist-assistive software tool that reduces these user limitations while providing a rapid, quantitative scoring system for digital histopathology image analysis. The software, called 'Lesion Image Recognition and Analysis' (LIRA), employs convolutional neural networks to classify seven different pathology features, including three different lesion types from pulmonary tissues of the C3HeB/FeJ tuberculosis mouse model. LIRA was developed to improve the efficiency of histopathology analysis for mouse tuberculosis infection models. The model approach also has broader applications to other diseases and tissues. This also includes animals that are undergoing anti-mycobacterial treatment and host immune system modulation. A complimentary software package called 'Mycobacterial Image Analysis' (MIA) had also been developed that characterizes the varying bacilli characteristics such as density, aggregate/planktonic bacilli size, fluorescent intensity, and total counts. This further groups the bacilli characteristic data depending on the seven different classifications that are selected by the user. Using this approach allows for an even more targeted analysis approach that can determine how therapy and microenvironments influence the Mtb response.
2020 Spring.
Includes bibliographical references.
Rights Access
artificial intelligence
computer vision
animal modeling
Associated Publications