Related Experiment Video
Updated: Oct 7, 2025
Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
Multi-scale information with attention integration for classification of liver fibrosis in B-mode US image
Xiangfei Feng1, Xin Chen2, Changfeng Dong3
1School of Electronic and Information Engineering, South China University of Technology, 510640, China.
Insights
A novel deep learning model accurately classifies liver fibrosis using ultrasound images, achieving 95.66% accuracy. This advancement aids in targeted treatment and recovery for chronic hepatitis B patients.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Hepatology
Background:
- Chronic hepatitis B (CHB) is a prevalent global liver disease.
- Liver fibrosis progression can lead to cirrhosis, liver cancer, and failure.
- Accurate fibrosis staging is crucial for effective CHB treatment and management.
Purpose of the Study:
- To develop a deep convolutional neural network (DCNN) for precise liver fibrosis classification from ultrasound images.
- To enhance classification accuracy through multi-scale feature extraction and attention integration.
Main Methods:
- Proposed a DCNN incorporating pyramid-structured CNN elements for multi-scale feature extraction.
- Implemented a feature distillation method using attention maps to focus on class-relevant features.
- Utilized ultrasound images from 286 participants for model training and testing.
Main Results:
- The DCNN achieved a high classification accuracy of 95.66% on the test dataset.
- The multi-scale feature extraction and attention mechanisms improved classification performance.
- The framework demonstrated promising results in staging liver fibrosis.
Conclusions:
- The developed DCNN framework accurately stages liver fibrosis.
- This technology offers potential for improved clinical treatment strategies for liver fibrosis.
- The findings may facilitate better patient recovery from CHB-related liver conditions.
Background And Objective:
Chronic hepatitis B (CHB) is one of the most common liver diseases in the world, which threats a lot to people's usual life. The increased deposition of fibrotic tissues in livers for patients with CHB may lead to the development of liver cirrhosis, hepatocellular carcinoma, or even liver failure. Accurate fibrosis staging is very important for the targeted treatment of liver fibrosis and its recovery.
Methods:
In this paper, we propose a new deep convolutional neural network (DCNN) with functions of multi-scale information extraction and attention integration for more accurate liver fibrosis classification from ultrasound (US) images. The proposed network uses two pyramid-structured CNN elements to extract multi-scale features from US images. Such a design significantly enlarges the receptive field of the convolution layer, such that more useful information can be explored by the neural network to associate with the final classification. Based on this, a new feature distillation method is also proposed to enhance the ability of deep features derived from multi-scale information. The proposed distillation method employs attention maps to automatically extract class-related features from multi-scale information, which effectively suppress the influence of potential distractors.
Results:
Experimental results on the US liver fibrosis dataset collected from 286 participants show that the proposed deep framework achieves promising classification performance. The proposed method achieves a classification accuracy of 95.66% on the test dataset.
Conclusion:
Our proposed framework could stage liver fibrosis highly accurately. It might provide effective suggestions for the clinical treatment of liver fibrosis that can facilitate its recovery.
More Related Videos
11:05High-definition Fourier Transform Infrared FT-IR Spectroscopic Imaging of Human Tissue Sections towards Improving Pathology
Published on: January 21, 2015
03:38Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
Published on: June 20, 2025
