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
. 2022 Mar 17:2022:9601470.
doi: 10.1155/2022/9601470. eCollection 2022.

Study on the Grading Model of Hepatic Steatosis Based on Improved DenseNet

Ruwen Yang  1 , Yaru Zhou  1 , Weiwei Liu  2 , Hongtao Shang  2
Affiliations

Study on the Grading Model of Hepatic Steatosis Based on Improved DenseNet

Ruwen Yang et al. J Healthc Eng. .

Abstract

To achieve intelligent grading of hepatic steatosis, a deep learning-based method for grading hepatic steatosis was proposed by introducing migration learning in the DenseNet model, and the effectiveness of the method was verified by applying it to the practice of grading hepatic steatosis. The results show that the proposed method can significantly reduce the number of model iterations and improve the model convergence speed and prediction accuracy by introducing migration learning in the deep learning DenseNet model, with an accuracy of more than 85%, sensitivity of more than 94%, specificity of about 80%, and good prediction performance on the training and test sets. It can also detect hepatic steatosis grade 1 more accurately and reliably, and achieve automated and more accurate grading, which has some practical application value.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflicts of interest regarding this work.

Figures

Figure 1
Figure 1
Dense connection of DenseNet blocks.
Figure 2
Figure 2
Example of mDixon slice image.
Figure 3
Figure 3
Performance comparison before and after model transfer learning.
Figure 4
Figure 4
Confusion matrix of model prediction results.
Figure 5
Figure 5
Model performance iteration curve.
Figure 6
Figure 6
Variation curve of liver fat content with age.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Yazan Q., Tahir A., Chowdhury M. E. H., et al. Detection and Severity classification of COVID-19 in CT images using deep learning[J] Diagnostics . 2021;11(5):p. 893. - PMC - PubMed
    1. Montalbo F. J. P. Diagnosing Covid-19 chest x-rays with a lightweight truncated DenseNet with partial layer freezing and feature fusion. Biomedical Signal Processing and Control . 2021;68:102583–102589. doi: 10.1016/j.bspc.2021.102583. - DOI - PMC - PubMed
    1. Marwa B. J., Koubaa A., Benjdira B., Ammar A., Hamam H. COVID-19 diagnosis in chest X-rays using deep learning and majority Voting[J] Applied Sciences . 2021;11(6):2884–2887.
    1. Liu Z., Zhu Y., Yuan Y., et al. 3D DenseNet deep learning based preoperative Computed Tomography for detecting myasthenia gravis in patients with thymoma. Frontiers in Oncology . 2021;11:p. 631964. doi: 10.3389/fonc.2021.631964. - DOI - PMC - PubMed
    1. Abtin R., Babaie M., Maleki D., et al. Tizhoosh. Fine-tuning and training of DenseNet for histopathology image Representation using TCGA diagnostic Slides[J] Medical Image Analysis . 2021;69:102032–102036. - PubMed

LinkOut - more resources