Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network

Objectives The aim of this study was to develop a deep convolutional neural network (DCNN) for the prediction of the METAVIR score using B-mode ultrasonography images. Methods Datasets from two tertiary academic referral centers were used. A total of 13,608 ultrasonography images from 3446 patients who underwent surgical resection, biopsy, or transient elastography were used for training a DCNN for the prediction of the METAVIR score. Pathological specimens or estimated METAVIR scores derived from transient elastography were used as a reference standard. A four-class model (F0 vs. F1 vs. F23 vs. F4) was developed. Diagnostic performance of the algorithm was validated on a separate internal test set of 266 patients with 300 images and external test set of 572 patients with 1232 images. Performance in classification of cirrhosis was compared between the DCNN and five radiologists. Results The accuracy of the four-class model was 83.5% and 76.4% on the internal and external test set, respectively. The area under the receiver operating characteristic curve (AUC) for classification of cirrhosis (F4) was 0.901 (95% confidence interval [CI], 0.865–0.937) on the internal test set and 0.857 (95% CI, 0.825–0.889) on the external test set, respectively. The AUC of the DCNN for classification of cirrhosis (0.857) was significantly higher than that of all five radiologists (AUC range, 0.656–0.816; p value < 0.05) using the external test set. Conclusions The DCNN showed high accuracy for determining METAVIR score using ultrasonography images and achieved better performance than that of radiologists in the diagnosis of cirrhosis. Key Points • DCNN accurately classified the ultrasonography images according to the METAVIR score. • The AUROC of this algorithm for cirrhosis assessment was significantly higher than that of radiologists. • DCNN using US images may offer an alternative tool for monitoring liver fibrosis.

[1]  Asociacion Latinoamericana para el Estudio del Higado.  EASL-ALEH Clinical Practice Guidelines: Non-invasive tests for evaluation of liver disease severity and prognosis. , 2015, Journal of hepatology.

[2]  William M. Lee,et al.  Complication rate of percutaneous liver biopsies among persons with advanced chronic liver disease in the HALT-C trial. , 2010, Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association.

[3]  Jialin Peng,et al.  Automatic 3D liver segmentation based on deep learning and globally optimized surface evolution , 2016, Physics in medicine and biology.

[4]  O. Abe,et al.  Liver Fibrosis: Deep Convolutional Neural Network for Staging by Using Gadoxetic Acid-enhanced Hepatobiliary Phase MR Images. , 2017, Radiology.

[5]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[6]  N. Afdhal,et al.  Diagnosis and quantitation of fibrosis. , 2008, Gastroenterology.

[7]  D. Conte,et al.  Severe liver fibrosis or cirrhosis: accuracy of US for detection--analysis of 300 cases. , 2003, Radiology.

[8]  Guy Cloutier,et al.  Ultrasound Elastography and MR Elastography for Assessing Liver Fibrosis: Part 2, Diagnostic Performance, Confounders, and Future Directions. , 2015, AJR. American journal of roentgenology.

[9]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[10]  S. Park,et al.  Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and Prediction. , 2018, Radiology.

[11]  D. Woodfield.  Hepatocellular carcinoma. , 1986, The New Zealand medical journal.

[12]  J. Duncan,et al.  Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI , 2019, European Radiology.

[13]  Bernadette A. Thomas,et al.  Global, regional, and national age–sex specific all-cause and cause-specific mortality for 240 causes of death, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[14]  Ping Zhang,et al.  Neighborhood-pixels algorithm combined with Sono-CT in the diagnosis of cirrhosis: an experimental study. , 2006, Ultrasound in medicine & biology.

[15]  P. Lakhani,et al.  Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks. , 2017, Radiology.

[16]  E. Finkelstein,et al.  Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes , 2017, JAMA.

[17]  T. Asselah,et al.  Direct comparison of diagnostic performance of transient elastography in patients with chronic hepatitis B and chronic hepatitis C , 2012, Liver international : official journal of the International Association for the Study of the Liver.

[18]  B. Stotland,et al.  Liver biopsy complications and routine ultrasound. , 1996, The American journal of gastroenterology.

[19]  Ioan Sporea,et al.  EFSUMB Guidelines and Recommendations on the Clinical Use of Liver Ultrasound Elastography, Update 2017 (Long Version) , 2017, Ultraschall in der Medizin - European Journal of Ultrasound.

[20]  O. Abe,et al.  Deep learning for staging liver fibrosis on CT: a pilot study , 2018, European Radiology.

[21]  A. B. Sukhomlinov,et al.  [Liver cirrhosis]. , 1989, Fel'dsher i akusherka.

[22]  F. Azzaroli,et al.  Noninvasive Assessment of Portal Hypertension in Advanced Chronic Liver Disease: An Update , 2018, Gastroenterology research and practice.

[23]  June-Goo Lee,et al.  Deep Learning in Medical Imaging: General Overview , 2017, Korean journal of radiology.

[24]  Cheol Min Park,et al.  Usefulness of standard deviation on the histogram of ultrasound as a quantitative value for hepatic parenchymal echo texture; preliminary study. , 2006, Ultrasound in medicine & biology.

[25]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[26]  Jin-Young Choi,et al.  Development and Validation of a Deep Learning System for Staging Liver Fibrosis by Using Contrast Agent-enhanced CT Images in the Liver. , 2018, Radiology.

[27]  V. de Lédinghen,et al.  Prospective comparison of transient elastography, Fibrotest, APRI, and liver biopsy for the assessment of fibrosis in chronic hepatitis C. , 2005, Gastroenterology.

[28]  Siddharth Singh,et al.  American Gastroenterological Association Institute Technical Review on the Role of Elastography in Chronic Liver Diseases. , 2017, Gastroenterology.

[29]  M. Rugge,et al.  Liver biopsy sampling in chronic viral hepatitis. , 2004, Seminars in liver disease.

[30]  Rosa Gilabert,et al.  Ultrasonographic evaluation of liver surface and transient elastography in clinically doubtful cirrhosis. , 2010, Journal of hepatology.

[31]  Paul Calès,et al.  Sources of variability in histological scoring of chronic viral hepatitis , 2005, Hepatology.

[32]  Siddharth Singh,et al.  American Gastroenterological Association Institute Guideline on the Role of Elastography in the Evaluation of Liver Fibrosis. , 2017, Gastroenterology.

[33]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[34]  Julien Vergniol,et al.  Noninvasive tests for fibrosis and liver stiffness predict 5-year outcomes of patients with chronic hepatitis C. , 2011, Gastroenterology.

[35]  A. Aghemo,et al.  US features of liver surface nodularity as a predictor of severe fibrosis in chronic hepatitis C. , 2005, Radiology.

[36]  F. Cainelli.  Liver diseases in developing countries. , 2012, World journal of hepatology.

[37]  Davide Castelvecchi,et al.  Can we open the black box of AI? , 2016, Nature.

[38]  Chang Hee Lee,et al.  Prediction of liver cirrhosis, using diagnostic imaging tools. , 2015, World journal of hepatology.

[39]  Bernadette A. Thomas,et al.  Global, regional, and national age–sex specific all-cause and cause-specific mortality for 240 causes of death, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[40]  Johannes T Heverhagen,et al.  State-of-the-art imaging of liver fibrosis and cirrhosis: A comprehensive review of current applications and future perspectives , 2015, European journal of radiology open.

[41]  Emmanuel A Tsochatzis,et al.  Liver cirrhosis , 2014, The Lancet.

[42]  M. Soresi,et al.  Non invasive tools for the diagnosis of liver cirrhosis. , 2014, World journal of gastroenterology.