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

You might also read

Related Articles

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

Sort by
Same author

A rapid path planning approach for liver tumor ablation with comprehensive constraints.

BMC medical imaging·2026
Same author

DSA-Former: A Network of Hybrid Variable Structures for Liver and Liver Tumour Segmentation.

The international journal of medical robotics + computer assisted surgery : MRCAS·2024
Same author

Preventing abnormal NF-κB activation and autoimmunity by Otub1-mediated p100 stabilization.

Cell research·2019
Same author

Glucocorticoid programming mechanism for hypercholesterolemia in prenatal ethanol-exposed adult offspring rats.

Toxicology and applied pharmacology·2019
Same author

TMCO1-mediated Ca<sup>2+</sup> leak underlies osteoblast functions via CaMKII signaling.

Nature communications·2019
Same author

Identification of Insulin-Responsive Transcription Factors That Regulate Glucose Production by Hepatocytes.

Diabetes·2019

Related Experiment Video

Updated: May 23, 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

1.0K

MF-ResUnet: A 3D Liver Image Segmentation Method Based on Multi-Scale Feature Fusion.

Jun Qin1, Yang Li1, Guihe Qin2

  • 1College of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China.

The International Journal of Medical Robotics + Computer Assisted Surgery : MRCAS
|May 21, 2025
PubMed
Summary

This study introduces a novel 3D liver segmentation method using multiscale feature fusion. The technique enhances accuracy in segmenting liver parenchyma from CT images, achieving high performance on benchmark datasets.

Keywords:
CT volumesattention mechanismliver segmentationmulti‐scale feature fusion

More Related Videos

Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease
08:41

Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease

Published on: March 24, 2023

1.0K
Hybrid &#181;CT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.1K

Related Experiment Videos

Last Updated: May 23, 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

1.0K
Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease
08:41

Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease

Published on: March 24, 2023

1.0K
Hybrid &#181;CT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.1K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Automatic liver segmentation from CT images is challenging due to variable liver shapes, similar intensity profiles with adjacent organs, and indistinct boundaries.
  • Accurate liver segmentation is crucial for diagnosis and treatment planning in various medical applications.

Purpose of the Study:

  • To develop an advanced 3D liver segmentation method that overcomes existing challenges in medical image analysis.
  • To improve the accuracy and robustness of automatic liver segmentation using deep learning techniques.

Main Methods:

  • A 3D liver segmentation network incorporating multiscale feature fusion.
  • Utilized SE channel attention for feature recalibration and an AMF module for rich spatial information.
  • Introduced the NGAB module to mitigate the effects of dilated convolutions, enhancing feature representation.

Main Results:

  • Achieved a Dice Similarity Coefficient (DSC) of 0.977 on the LiTS2017 dataset.
  • Attained a DSC of 0.967 on the 3DIRCADb dataset, demonstrating high segmentation accuracy.
  • The proposed method effectively captures multiscale characteristics for improved liver segmentation.

Conclusions:

  • The developed method shows significant promise for accurate and efficient automatic liver segmentation.
  • The multiscale feature fusion approach effectively addresses the complexities of liver segmentation in CT images.
  • This work contributes to advancing automated medical image analysis tools for liver-related conditions.