Related Experiment Video
Updated: Nov 27, 2025
Noninvasive Assessment of Cardiac Abnormalities in Experimental Autoimmune Myocarditis by Magnetic Resonance Microscopy Imaging in the Mouse
Published on: June 20, 2014
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.
Abstract:
Rodent progressive cardiomyopathy (PCM) encompasses a constellation of microscopic findings commonly seen as a spontaneous background change in rat and mouse hearts. Primary histologic features of PCM include varying degrees of cardiomyocyte degeneration/necrosis, mononuclear cell infiltration, and fibrosis. Mineralization can also occur. Cardiotoxicity may increase the incidence and severity of PCM, and toxicity-related morphologic changes can overlap with those of PCM. Consequently, sensitive and consistent detection and quantification of PCM features are needed to help differentiate spontaneous from test article-related findings. To address this, we developed a computer-assisted image analysis algorithm, facilitated by a fully convolutional network deep learning technique, to detect and quantify the microscopic features of PCM (degeneration/necrosis, fibrosis, mononuclear cell infiltration, mineralization) in rat heart histologic sections. The trained algorithm achieved high values for accuracy, intersection over union, and dice coefficient for each feature. Further, there was a strong positive correlation between the percentage area of the heart predicted to have PCM lesions by the algorithm and the median severity grade assigned by a panel of veterinary toxicologic pathologists following light microscopic evaluation. By providing objective and sensitive quantification of the microscopic features of PCM, deep learning algorithms could assist pathologists in discerning cardiotoxicity-associated changes.
Insights
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.
