Using Artificial Intelligence to Detect, Classify, and Objectively Score Severity of Rodent Cardiomyopathy
| Autor: | Mark F. Cesta, Vivian S. Chen, Gargi Srivastava, Rajesh Ugalmugle, Kristen Hobbie, Heath C. Thomas, Thomas J Steinbach, Caroll A. Co, Emily Singletary, Keith R. Shockley, Debra A Tokarz, Avinash Lokhande, Torrie A. Crabbs |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Pathology
medicine.medical_specialty animal structures Cardiomyopathy Rodentia Toxicology Score severity Positive correlation Article Pathology and Forensic Medicine Mice 03 medical and health sciences 0302 clinical medicine Sørensen–Dice coefficient Artificial Intelligence Fibrosis medicine Animals skin and connective tissue diseases Molecular Biology 030304 developmental biology 0303 health sciences Cardiotoxicity business.industry Cell Biology Rat heart medicine.disease Rats Mononuclear cell infiltration 030220 oncology & carcinogenesis Neural Networks Computer Cardiomyopathies business Algorithms |
| Zdroj: | Toxicol Pathol |
| ISSN: | 1533-1601 0192-6233 |
| DOI: | 10.1177/0192623320972614 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|