Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Efficient Inference for Large Reasoning Models: A Survey.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

NH600001, an etomidate analogue, provides gastrointestinal endoscopy sedation/anesthesia and reduces adrenocortical depression: two randomized controlled trials.

Nature communications·2026

Same author

Tea-inspired curing modulates chemical composition, volatile aroma, and sensory quality of flue-cured tobacco leaves.

Scientific reports·2026

Same author

A label masked autoencoder for image-guided segmentation label completion.

Patterns (New York, N.Y.)·2026

Same author

Shaking and withering intensity from oolong tea processing alters the chemical and sensory quality of tobacco.

Scientific reports·2026

Same author

Vonoprazan-Tetracycline Dual Regimen as Rescue Therapy for Helicobacter pylori Infection: Randomized Controlled Trial.

Gastroenterology·2026

Search research articles

Related Experiment Video

Updated: Sep 29, 2025

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Published on: May 23, 2025

Edge Constraint and Location Mapping for Liver Tumor Segmentation from Nonenhanced Images.

Jina Zhang¹, Shichao Luo¹, Yan Qiang¹

¹College of Information and Computer, Taiyuan University of Technology, Taiyuan, China.

Computational and Mathematical Methods in Medicine

|March 21, 2022

Summary

Accurate liver tumor segmentation in nonenhanced MRI is challenging due to blurred edges. The proposed Edge Constraint and Localization Mapping Segmentation (ECLMS) model significantly improves segmentation accuracy for nonenhanced liver tumors.

More Related Videos

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Published on: December 2, 2013

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Sep 29, 2025

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Published on: May 23, 2025

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Dual-phase Cone-beam Computed Tomography to See, Reach, and Treat Hepatocellular Carcinoma during Drug-eluting Beads Transarterial Chemo-embolization

Published on: December 2, 2013

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Nonenhanced MRI presents challenges for liver tumor diagnosis due to low contrast and blurred edges, impacting accuracy and speed.
Precise segmentation of liver tumors in nonenhanced MRI is a critical yet difficult task.

Purpose of the Study:

To develop an accurate segmentation model for liver tumors in nonenhanced MRI.
To address the limitations of blurred edges and low contrast in nonenhanced liver MRI.

Main Methods:

Proposed an Edge Constraint and Localization Mapping Segmentation (ECLMS) model.
The ECLMS model incorporates a localization network for prior coarse masks and a dual-branch segmentation network (core and edge branches).
Introduced sSE blocks, dense upward connections, and a bottleneck multiscale module for enhanced feature representation and location mapping.

Main Results:

The ECLMS model achieved a Dice coefficient of 90.23%, precision of 92.25%, and accuracy of 92.39% on a private dataset of 215 subjects.
Demonstrated superior performance compared to existing segmentation methods for nonenhanced liver tumors.
The model effectively captures both core tumor features and detailed edge information.

Conclusions:

The ECLMS model provides an effective solution for accurate liver tumor segmentation in nonenhanced MRI.
The proposed methods enhance the model's ability to localize tumors and capture fine-grained details.
This approach holds significant potential for improving the speed and accuracy of liver tumor diagnosis.