A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH
| Autor: | Manuel Romero-Gómez, Michael Trauner, Ilan Wapinski, Benjamin Glass, Ryan S Huss, Chuhan Chung, Ling Han, Andrew H. Beck, Kishalve Pethia, Hunter L. Elliott, Robert P. Myers, Amaro Taylor-Weiner, Harsha Pokkalla, Vincent Wai-Sun Wong, Catherine Jia, Michael Christopher Montalto, Rohit Loomba, Zobair M. Younossi, Murray B. Resnick, Eric Lawitz, Stephen A. Harrison, Aditya Khosla, Takeshi Okanoue, G. Mani Subramanian, Quentin M. Anstee, Ross Taliano, Chinmay Shukla, Oscar Carrasco-Zevallos, Robert Najarian, Zachary Goodman, Urmila Khettry |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Liver Cirrhosis
0301 basic medicine Cirrhosis Biopsy Pathological staging Disease Machine learning computer.software_genre Severity of Illness Index law.invention Machine Learning Steatohepatitis/Metabolic Liver Disease 03 medical and health sciences Deep Learning 0302 clinical medicine Randomized controlled trial Artificial Intelligence Non-alcoholic Fatty Liver Disease Fibrosis law Image Processing Computer-Assisted Humans Medicine Liver histology Randomized Controlled Trials as Topic Hepatology business.industry Reproducibility of Results Original Articles medicine.disease 030104 developmental biology Liver Original Article 030211 gastroenterology & hepatology Metric (unit) Artificial intelligence Steatosis business computer |
| Zdroj: | Hepatology (Baltimore, Md.) |
| ISSN: | 1527-3350 0270-9139 |
| DOI: | 10.1002/hep.31750 |
| Popis: | Background and aims Manual histological assessment is currently the accepted standard for diagnosing and monitoring disease progression in NASH, but is limited by variability in interpretation and insensitivity to change. Thus, there is a critical need for improved tools to assess liver pathology in order to risk stratify NASH patients and monitor treatment response. Approach and results Here, we describe a machine learning (ML)-based approach to liver histology assessment, which accurately characterizes disease severity and heterogeneity, and sensitively quantifies treatment response in NASH. We use samples from three randomized controlled trials to build and then validate deep convolutional neural networks to measure key histological features in NASH, including steatosis, inflammation, hepatocellular ballooning, and fibrosis. The ML-based predictions showed strong correlations with expert pathologists and were prognostic of progression to cirrhosis and liver-related clinical events. We developed a heterogeneity-sensitive metric of fibrosis response, the Deep Learning Treatment Assessment Liver Fibrosis score, which measured antifibrotic treatment effects that went undetected by manual pathological staging and was concordant with histological disease progression. Conclusions Our ML method has shown reproducibility and sensitivity and was prognostic for disease progression, demonstrating the power of ML to advance our understanding of disease heterogeneity in NASH, risk stratify affected patients, and facilitate the development of therapies. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text