Related Experiment Video
Updated: Nov 27, 2025
12:24
Noninvasive Assessment of Cardiac Abnormalities in Experimental Autoimmune Myocarditis by Magnetic Resonance Microscopy Imaging in the Mouse
Published on: June 20, 2014
10.2K
Using Artificial Intelligence to Detect, Classify, and Objectively Score Severity of Rodent Cardiomyopathy.
Debra A Tokarz1, Thomas J Steinbach1, Avinash Lokhande2
1Experimental Pathology Laboratories, Inc, Research Triangle Park, NC, USA.
Toxicologic Pathology
|December 8, 2020
Summary
A new deep learning algorithm accurately quantifies rodent progressive cardiomyopathy (PCM) features in heart tissue. This tool helps distinguish spontaneous changes from drug-induced cardiotoxicity, improving toxicologic pathology assessments.
Area of Science:
- Veterinary pathology
- Computational pathology
- Toxicologic pathology
Background:
- Rodent progressive cardiomyopathy (PCM) presents as spontaneous heart changes in rats and mice.
- Key features include cardiomyocyte degeneration, inflammation, fibrosis, and mineralization.
- Distinguishing PCM from drug-induced cardiotoxicity is challenging due to overlapping features.
Purpose of the Study:
- To develop a computer-assisted image analysis algorithm for detecting and quantifying PCM features.
- To utilize deep learning (fully convolutional network) for objective assessment.
- To aid in differentiating spontaneous PCM from test article-related cardiotoxicity.
Main Methods:
- A deep learning algorithm based on a fully convolutional network was developed.
- The algorithm was trained to detect and quantify four key PCM features: degeneration/necrosis, fibrosis, mononuclear cell infiltration, and mineralization.
- Performance was evaluated using accuracy, intersection over union, and dice coefficient metrics.
Main Results:
- The algorithm demonstrated high accuracy in detecting and quantifying PCM features.
- A strong positive correlation was found between the algorithm's predicted lesion area and pathologist-assigned severity grades.
- The algorithm effectively quantified microscopic features of PCM in rat heart histology.
Conclusions:
- Deep learning algorithms can provide objective and sensitive quantification of PCM microscopic features.
- This approach can assist veterinary toxicologic pathologists in distinguishing spontaneous PCM from cardiotoxicity.
- Computer-assisted analysis enhances the reliability of assessing cardiac changes in preclinical studies.
