13 April 2018, Paris, France: Deep-learning approaches to pattern recognition in liver biopsy samples have moved one step closer to clinical application, with a new study reporting a good correlation between an automated image analysis system and an expert reviewer for the identification of key markers of disease activity in a pre-clinical model of non-alcoholic steatohepatitis (NASH). The study reported today at The International Liver Congress™ 2018 in Paris, France, found that deep-learning algorithms applied using open-source pathology software (QuPath1) could accurately identify cell histology patterns consistent with lobular inflammation and hepatocellular ballooning - markers of disease activity that are essential to establish the diagnosis and severity of NASH.2
Non-alcoholic steatohepatitis is the progressive form of non-alcoholic fatty liver disease (NAFLD), in which excessive fat accumulates in the liver of individuals who do not have a history of alcohol abuse.2,3 NAFLD is regarded as a hepatic manifestation of metabolic syndrome, with the number of individuals with NAFLD/NASH increasing rapidly worldwide, in parallel with the increasing prevalence of obesity.3 Although clinical algorithms based on blood test results are being developed to identify patients with progressive NASH,4-6 liver biopsy remains essential to establish both the diagnosis of NASH and the severity of the disease.2
'The histological evaluation of NASH by microscopy is time consuming and limited by inter- and intra-observer variability', explained Mr John Brozek from the French biotechnology company, GENFIT, which is developing the deep-learning system. 'We have been working to eliminate the subjectivity associated with interpreting histological images and have recently used deep-learning technologies to quantify histological patterns associated with NASH in an animal model'.7,8
In the study presented today by Mr Brozek, animal models (rats or mice fed a choline-deficient, L-amino-acid-defined diet supplemented with cholesterol) were used to evaluate hepatocellular ballooning and lobular inflammation in liver biopsy samples. An expert histopathologist determined the ballooning and inflammation scores for all the animals included in the study, and deep-learning models were constructed to detect and analyze these histological features. An initial training set (n=31) was used to calibrate ballooning and inflammation for subsequent prediction of these histological features in four independent cohorts (n=271).
According to Mr Brozek, the deep-learning system was able to predict cell histological patterns relating to ballooning and inflammation with accuracies of 98% and 91%, respectively. Excellent agreement was observed between the expert and fully automated scores of ballooning at a cellular level for each of the cohorts (k=0.84 and k=0.81). An excellent correlation was also observed with the full tissue samples (k=0.71), and between whole slide imaging-based automatic scoring of inflammation on the training cohort (Rho=0.907).
'Deep-learning-based scoring systems allow an exhaustive and reproducible analysis of all cells in a biopsy sample, and they can analyze specific regions of cells that can be difficult to interpret manually, even if you are an expert', said Mr Brozek. 'Our automated scoring system for ballooning and inflammation showed a high correlation with expert evaluation and it is ready to be used for high-throughput activity scoring in pre-clinical studies or, in the near future, as a companion diagnostic tool for clinical application'.
'There are key challenges in the consistency of liver biopsy interpretation and machine learning offers the promise of a more standardized, objective approach that allows for the analysis of biopsies in clinical trials', said Prof. Phil Newsome from the Queen Elizabeth Hospital and University of Birmingham, UK, and EASL Governing Board Member.
About The International Liver Congress™
This annual congress is the biggest event in the EASL calendar, attracting scientific and medical experts from around the world to learn about the latest in liver research. Attending specialists present, share, debate and conclude on the latest science and research in hepatology, working to enhance the treatment and management of liver disease in clinical practice. This year, the congress is expected to attract approximately 10,000 delegates from all corners of the globe. The International Liver Congress™ 2018 will take place from 11¬-15 April 2018 at the Paris Convention Centre, Paris, France.
About The European Association for the Study of the Liver (EASL)
Since its foundation in 1966, this not-for-profit organization has grown to over 4,000 members from all over the world, including many of the leading hepatologists in Europe and beyond. EASL is the leading liver association in Europe, having evolved into a major European association with international influence, and with an impressive track record in promoting research in liver disease, supporting wider education and promoting changes in European liver policy.
For more information, please contact the ILC Press Office at:
- Email: email@example.com
- Telephone: +41 (0) 22 807 29 88
Onsite location reference
Session title: Poster Late Breakers
Time, date and location of session: 09.00-17.00, 12 April 2018, Poster Area
Presenter: John Brozek
Abstract: A deep-learning approach for pattern recognition allows rapid and reproducible quantification of histological NASH parameters: integration into the QuPath platform (5737)
John Brozek is an employee of GENFIT.
1. Bankhead P, et al. QuPath: open source software for digital pathology image analysis. Sci Rep. 2017;7(1):16878.
2. European Association for the Study of the Liver (EASL); European Association for the Study of Diabetes (EASD); European Association for the Study of Obesity (EASO). EASL-EASD-EASO Clinical Practice Guidelines for the management of non-alcoholic fatty liver disease. J Hepatol. 2016;64(6):1388-402.
3. Takahashi Y, et al. Histopathology of nonalcoholic fatty liver disease/nonalcoholic steatohepatitis. World J Gastroenterol. 2014;20(42):15539-48.
4. Sanyal A, et al. A new method including the quantification of circulating miRNAs allows the efficient identification of NASH patients at risk who should be treated. J Hepatol. 2016;64(2):S717.
5. Harrison S, et al. A new non-invasive diagnostic score to monitor change in disease activity and predict fibrosis evolution in patients with NASH. J Hepatol. 2017;66:S1-876 (LBP-534).
6. Hanf R, et al. Validation of NIS4 algorithm for detection of NASH at risk of cirrhosis in 467 NAFLD patients prospectively screened for inclusion in the Resolve-IT trial. J Hepatol. 2018: Abstract #LBP-020. doi: 10.1016/S0168-8278(17)30030-2.
7. Rexhepaj E, et al. Pattern recognition and quantification of hepatic fibrosis in NASH preclinical models using deep-learning based image analysis. AASLD LiverLearning®. 2017;194171. Abstract #620.
8. Rexhepaj E, et al. Quantification of fibrosis staging and collagen proportionate area in NASH pre-clinical models using a fully-automated deep-learning approach. AASLD LiverLearning®. 2017;194172. Abstract #621. ?