Fully Automatic Liver Attenuation Estimation Combing CNN Segmentation and Morphological Operations

PURPOSE Manually tracing regions of interest (ROIs) within the liver is the de facto standard method for measuring liver attenuation on computed tomography (CT) in diagnosing nonalcoholic fatty liver disease (NAFLD). However, manual tracing is resource intensive. To address these limitations and to expand the availability of a quantitative CT measure of hepatic steatosis, we propose the automatic liver attenuation ROI-based measurement (ALARM) method for automated liver attenuation estimation. METHODS The ALARM method consists of two major stages: (1) deep convolutional neural network (DCNN)-based liver segmentation and (2) automated ROI extraction. First, liver segmentation was achieved using our previously developed SS-Net. Then, a single central ROI (center-ROI) and three circles ROI (periphery-ROI) were computed based on liver segmentation and morphological operations. The ALARM method is available as an open source Docker container (https://github. com/MASILab/ALARM). RESULTS 246 subjects with 738 abdomen CT scans from the African American-Diabetes Heart Study (AA-DHS) were used for external validation (testing), independent from the training and validation cohort (100 clinically acquired CT abdominal scans). From the correlation analyses, the proposed ALARM method achieved Pearson correlations = 0.94 with manual estimation on liver attenuation estimations. When evaluating the ALARM method for detection of nonalcoholic fatty liver disease (NAFLD) using the traditional cut point of <40 HU, the center-ROI achieved substantial agreements (Kappa=0.79) with manual estimation, while the periphery-ROI method achieved "excellent" agreement (Kappa=0.88) with manual estimation. The automated ALARM method had reduced variability compared to manual measurements as indicated by a smaller standard deviation. CONCLUSIONS We propose a fully automated liver attenuation estimation method termed ALARM by combining DCNN and morphological operations, which achieved "excellent" agreement with manual estimation for fatty liver detection. The entire pipeline is implemented as a Docker container which enables users to achieve liver attenuation estimation in five minutes per CT exam. This article is protected by copyright. All rights reserved.

[1]  Xiangyu Zhang,et al.  Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Moyses Szklo,et al.  Liver Attenuation, Pericardial Adipose Tissue, Obesity, and Insulin Resistance: The Multi‐Ethnic Study of Atherosclerosis (MESA) , 2011, Obesity.

[3]  Udo Hoffmann,et al.  Genome-Wide Association Analysis Identifies Variants Associated with Nonalcoholic Fatty Liver Disease That Have Distinct Effects on Metabolic Traits , 2011, PLoS genetics.

[4]  N. Goyal,et al.  Preoperative CT evaluation of potential donors in living donor liver transplantation , 2014, Indian Journal of Radiology and Imaging.

[5]  J. Fleiss,et al.  Statistical methods for rates and proportions , 1973 .

[6]  S. S. Lee,et al.  Radiomics and Deep Learning: Hepatic Applications , 2020, Korean journal of radiology.

[7]  DeMarc Hickson,et al.  Fatty Liver, Abdominal Visceral Fat, and Cardiometabolic Risk Factors: The Jackson Heart Study , 2011, Arteriosclerosis, thrombosis, and vascular biology.

[8]  A. Viera,et al.  Understanding interobserver agreement: the kappa statistic. , 2005, Family medicine.

[9]  R. Kronmal,et al.  Multi-Ethnic Study of Atherosclerosis: objectives and design. , 2002, American journal of epidemiology.

[10]  Michael Charlton,et al.  The diagnosis and management of nonalcoholic fatty liver disease: Practice guidance from the American Association for the Study of Liver Diseases , 2018, Hepatology.

[11]  Sang Won Lee,et al.  Macrovesicular hepatic steatosis in living liver donors: use of CT for quantitative and qualitative assessment. , 2006, Radiology.

[12]  Shunxing Bao,et al.  Splenomegaly segmentation using global convolutional kernels and conditional generative adversarial networks , 2017, Medical Imaging.

[13]  T. Manolio,et al.  Overview of the Jackson Heart Study: a study of cardiovascular diseases in African American men and women. , 1999, The American journal of the medical sciences.

[14]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[15]  I. Wanless,et al.  Fatty liver hepatitis (steatohepatitis) and obesity: An autopsy study with analysis of risk factors , 1990, Hepatology.

[16]  D E Manyari,et al.  Prognostic implications of echocardiographically determined left ventricular mass in the Framingham Heart Study. , 1990, The New England journal of medicine.

[17]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[18]  Fang-Chi Hsu,et al.  Hepatic Steatosis and Subclinical Cardiovascular Disease in a Cohort Enriched for Type 2 Diabetes: The Diabetes Heart Study , 2008, The American Journal of Gastroenterology.

[19]  Mary E Rinella,et al.  Nonalcoholic fatty liver disease: a systematic review. , 2015, JAMA.

[20]  Dong Li,et al.  Computed tomography scans in the evaluation of fatty liver disease in a population based study: the multi-ethnic study of atherosclerosis. , 2012, Academic radiology.

[21]  Jiang Hsieh,et al.  Computed Tomography: Principles, Design, Artifacts, and Recent Advances, Fourth Edition , 2022 .

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  S. Curley,et al.  Comparison of CT methods for determining the fat content of the liver. , 2007, AJR. American journal of roentgenology.

[24]  F. Brancati,et al.  The prevalence and etiology of elevated aminotransferase levels in the United States , 2003, American Journal of Gastroenterology.

[25]  K. Cusi,et al.  The Diagnosis and Management of Non-alcoholic Fatty Liver Disease: Practice Guideline by the American Association for the Study of Liver Diseases, American College of Gastroenterology, and the American Gastroenterological Association , 2012, The American Journal of Gastroenterology.

[26]  Robin Strand,et al.  Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies , 2017, Scientific Reports.

[27]  Vincent Wai-Sun Wong,et al.  Screening diabetic patients for non-alcoholic fatty liver disease with controlled attenuation parameter and liver stiffness measurements: a prospective cohort study , 2015, Gut.

[28]  Shaohua Kevin Zhou,et al.  Less is More: Simultaneous View Classification and Landmark Detection for Abdominal Ultrasound Images , 2018, MICCAI.

[29]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Dirk Merkel,et al.  Docker: lightweight Linux containers for consistent development and deployment , 2014 .

[31]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[32]  Pamela J Schreiner,et al.  Early adult risk factor levels and subsequent coronary artery calcification: the CARDIA Study. , 2007, Journal of the American College of Cardiology.

[33]  Bennett A Landman,et al.  Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning , 2015, Medical Image Anal..

[34]  Joseph A Maldjian,et al.  Review of the Diabetes Heart Study (DHS) family of studies: a comprehensively examined sample for genetic and epidemiological studies of type 2 diabetes and its complications. , 2010, The review of diabetic studies : RDS.

[35]  Donald W. Bowden,et al.  Associations of coronary artery calcified plaque density with mortality in type 2 diabetes: the Diabetes Heart Study , 2018, Cardiovascular Diabetology.

[36]  Alex P. Reiner,et al.  Sex and race differences in the prevalence of fatty liver disease as measured by computed tomography liver attenuation in European American and African American participants of the NHLBI family heart study , 2012, European journal of gastroenterology & hepatology.

[37]  James G Terry,et al.  Associations between nonalcoholic fatty liver disease and subclinical atherosclerosis in middle-aged adults: the Coronary Artery Risk Development in Young Adults Study. , 2014, Atherosclerosis.

[38]  B. Everitt,et al.  Statistical methods for rates and proportions , 1973 .

[39]  James G Terry,et al.  Computed tomography-derived cardiovascular risk markers, incident cardiovascular events, and all-cause mortality in nondiabetics: the Multi-Ethnic Study of Atherosclerosis , 2014, European journal of preventive cardiology.