Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

8.2K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
8.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Analysis of clinical features of AECOPD at different altitudes and GOLD stages in high-altitude regions.

BMJ open respiratory research·2026
Same author

MFST-GCN: A Sleep Stage Classification Method Based on Multi-Feature Spatio-Temporal Graph Convolutional Network.

Brain sciences·2026
Same author

RIS-UNet: A Multi-Level Hierarchical Framework for Liver Tumor Segmentation in CT Images.

Entropy (Basel, Switzerland)·2025
Same author

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery.

Environmental science & technology·2024
Same author

Effect of fire and post-fire management on soil microbial communities in a lower subtropical forest ecosystem after a mountain fire.

Journal of environmental management·2023
Same author

The rapid start-up of CANON process through adding partial nitration sludge to ANAMMOX system.

Journal of environmental management·2023

Related Experiment Video

Updated: Oct 30, 2025

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
06:09

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

1.5K

A Multi-Scale and Multi-Level Fusion Approach for Deep Learning-Based Liver Lesion Diagnosis in Magnetic Resonance

Yuchai Wan1, Zhongshu Zheng2, Ran Liu3

  • 1Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048, China.

Life (Basel, Switzerland)
|July 2, 2021
PubMed
Summary

This study introduces a novel deep learning approach for liver lesion diagnosis using multi-scale magnetic resonance images. The method enhances diagnostic accuracy and provides explainable AI for clinical transparency.

Keywords:
computer-aided diagnosisdeep learningliver cancermulti-level fusionmulti-scale representationvisual explanation

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.4K

Related Experiment Videos

Last Updated: Oct 30, 2025

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
06:09

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

1.5K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.4K

Area of Science:

  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare
  • Oncology Diagnostics

Background:

  • Existing computer-aided diagnosis (CAD) methods for liver cancer often use single-scale image analysis, limiting information capture.
  • Deep learning models in medical imaging lack explainability, hindering clinical trust and adoption.
  • Liver lesion diagnosis from magnetic resonance images (MRI) requires sophisticated analysis to differentiate benign and malignant findings.

Purpose of the Study:

  • To develop an explainable deep learning framework for liver lesion diagnosis on MRI.
  • To improve diagnostic accuracy by integrating multi-scale and multi-level image information.
  • To enhance the transparency of deep learning models for clinicians through visualization.

Main Methods:

  • Proposed a Convolutional Neural Network (CNN) based multi-scale and multi-level fusing approach (MMF-CNN).
  • Implemented a multi-scale representation strategy to capture local and semi-local image features.
  • Developed a multi-level fusion technique combining feature and decision levels for robust classification.
  • Integrated explainability through visualization of network attention maps and a novel scoring method.

Main Results:

  • The MMF-CNN approach demonstrated effectiveness across various state-of-the-art deep learning architectures.
  • Multi-scale analysis successfully encoded complementary local and semi-local image information.
  • The multi-level fusion strategy enhanced the robustness of the diagnostic classifier.
  • Visualization techniques provided transparent insights into the deep neural network's decision-making process.

Conclusions:

  • The proposed MMF-CNN framework offers a significant advancement in explainable AI for liver lesion diagnosis.
  • Integrating multi-scale and multi-level information improves diagnostic performance in medical image analysis.
  • Explainable AI is crucial for clinical acceptance and effective application of deep learning in radiology.