Using Artificial Intelligence to Detect, Classify, and Objectively Score Severity of Rodent Cardiomyopathy
-
- Debra A. Tokarz
- Experimental Pathology Laboratories, Inc, Research Triangle Park, NC, USA
-
- Thomas J. Steinbach
- Experimental Pathology Laboratories, Inc, Research Triangle Park, NC, USA
-
- Avinash Lokhande
- AIRA Matrix Private Limited, Mumbai, India
-
- Gargi Srivastava
- AIRA Matrix Private Limited, Mumbai, India
-
- Rajesh Ugalmugle
- AIRA Matrix Private Limited, Mumbai, India
-
- Caroll A. Co
- Social and Scientific Systems, Durham, NC, USA
-
- Keith R. Shockley
- Biostatistics and Computational Biology Branch, Division of Intramural Research, National Institute of Environmental Health Sciences, Research Triangle Park, NC, USA
-
- Emily Singletary
- Experimental Pathology Laboratories, Inc, Research Triangle Park, NC, USA
-
- Mark F. Cesta
- National Toxicology Program, National Institute of Environmental Health Sciences, Research Triangle Park, NC, USA
-
- Heath C. Thomas
- Aclairo Pharmaceutical Development Group, Vienna, VA, USA
-
- Vivian S. Chen
- Charles River Laboratories Inc, Durham, NC, USA
-
- Kristen Hobbie
- Integrated Laboratory Systems, LLC, Research Triangle Park, NC, USA
-
- Torrie A. Crabbs
- Experimental Pathology Laboratories, Inc, Research Triangle Park, NC, USA
説明
<jats:p> 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. </jats:p>
収録刊行物
-
- Toxicologic Pathology
-
Toxicologic Pathology 49 (4), 888-896, 2020-12-08
SAGE Publications