Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May;10(3):034505.
doi: 10.1117/1.JMI.10.3.034505. Epub 2023 Jun 5.

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

Miriam Naim Ibrahim  1   2   3 , Raul Blázquez-García  2 , Adi Lightstone  2 , Fankun Meng  4 , Mamatha Bhat  3 , Ahmed El Kaffas  2 , Eranga Ukwatta  1
Affiliations

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

Miriam Naim Ibrahim et al. J Med Imaging (Bellingham). 2023 May.

Abstract

Purpose: Non-alcoholic fatty liver disease (NAFLD) is an increasing global health concern, with a prevalence of 25% worldwide. The rising incidence of NAFLD, an asymptomatic condition, reinforces the need for systematic screening strategies in primary care. We present the use of non-expert acquired point-of-care ultrasound (POCUS) B-mode images for the development of an automated steatosis classification algorithm.

Approach: We obtained a Health Insurance Portability and Accountability Act compliant dataset consisting of 478 patients [body mass index 23.60±3.55, age 40.97±10.61], imaged with POCUS by non-expert health care personnel. A U-Net deep learning (DL) model was used for liver segmentation in the POCUS B-mode images, followed by 224×224 patch extraction of liver parenchyma. Several DL models including VGG-16, ResNet-50, Inception V3, and DenseNet-121 were trained for binary classification of steatosis. All layers of each tested model were unfrozen, and the final layer was replaced with a custom classifier. Majority voting was applied for patient-level results.

Results: On a hold-out test set of 81 patients, the final DenseNet-121 model yielded an area under the receiver operator characteristic curve of 90.1%, sensitivity of 95.0%, and specificity of 85.2% for the detection of liver steatosis. Average cross-validation performance in models using patches of liver parenchyma as input outperformed methods using complete B-mode frames.

Conclusions: Despite minimal POCUS acquisition training, and low-quality B-mode images, it is possible to detect steatosis using DL algorithms. Implementation of this algorithm in POCUS software may offer an accessible, low-cost steatosis screening technology, for use by non-expert health care personnel.

Keywords: deep learning; liver; non-alcoholic fatty liver disease; point-of-care ultrasound; steatosis.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Patient exclusion flow chart.
Fig. 2
Fig. 2
Overview of model development methodology.
See this image and copyright information in PMC

References

    1. Mitra S., De A., Chowdhury A., “Epidemiology of non-alcoholic and alcoholic fatty liver diseases,” Transl. Gastroenterol. Hepatol. 5, 16 (2020).10.21037/tgh.2019.09.08 - DOI - PMC - PubMed
    1. Canadian Liver Foundation, “Liver disease in Canada,” 2022, https://www.liver.ca/wp-content/uploads/2017/09/CLF_LiverDiseaseInCanada...
    1. Benedict M., Zhang X., “Non-alcoholic fatty liver disease: an expanded review,” World J Hepatol 9(16), 715–732 (2017).10.4254/wjh.v9.i16.715 - DOI - PMC - PubMed
    1. Pandyarajan V., et al. , “Screening for nonalcoholic fatty liver disease in the primary care clinic,” Gastroenterol. Hepatol. (N Y) 15(7), 357–365 (2019). - PMC - PubMed
    1. Han A., et al. , “Noninvasive diagnosis of nonalcoholic fatty liver disease and quantification of liver fat with radiofrequency ultrasound data using one-dimensional convolutional neural networks,” Radiology 295(2), 342–350 (2020).RADLAX10.1148/radiol.2020191160 - DOI - PMC - PubMed