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

AdapHBNA: Adaptive hierarchical spatio-temporal brain network analysis for brain disease detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Systematic characterization of purple acid phosphatases provides targets for improving phosphorus use efficiency in cotton.

Functional & integrative genomics·2026

Same author

Lightweight deep learning framework for intracranial hemorrhage detection in brain CT scans.

Frontiers in medicine·2026

Same author

Design and development of a 1-bit dual-mode metasurface for sub-6 GHz wireless communication systems.

Scientific reports·2026

Same author

IMPACT: A Structured Human-Centered Design Process for Integrating Community Health Worker Insights Into Program Policy in Pakistan.

Global health, science and practice·2026

Same author

Effect of Nurse-Led Intermittent Bladder Catheterization on Recurrence of Female Urethral Stricture following Urethral Dilatation: A Randomized Controlled Trial.

Pakistan journal of medical sciences·2026

Search research articles

Related Experiment Video

Updated: Aug 30, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Discriminative Level Set Method with Deep Supervision for Breast Tumor Segmentation.

Sumaira Hussain¹, Xiaoming Xi², Inam Ullah²

¹School of Computer Science and Technology, Shandong Jianzhu University, Jinan 250101, China; School of Software Engineering, Shandong University, Jinan 250101, China.

Computers in Biology and Medicine

|September 2, 2022

Summary

This study introduces a novel deep-feature embedded level set method for enhanced breast tumor segmentation in ultrasound images. The approach improves accuracy and precision, outperforming existing methods in key segmentation metrics.

Keywords:

Deep learning Discriminative information Level set Medical image segmentation

More Related Videos

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Aug 30, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Medical Imaging
Artificial Intelligence

Background:

Breast tumor segmentation in B-mode ultrasound is crucial for diagnosis.
Traditional level set methods lack semantic information, while deep networks lose low-level details.

Purpose of the Study:

To propose a novel deep-feature embedded level set group for improved breast tumor segmentation.
To leverage rich semantic information from deep networks and preserve low-level details.

Main Methods:

A UNet-based network extracts multi-stage features.
A novel level-set method integrates at each stage for precise feature maps.
A feature-discriminator refines boundary pixels, and multi-stage outputs are combined.

Main Results:

The proposed method significantly outperformed existing techniques in Dice and IoU metrics (p < 0.005).
Achieved superior performance with higher Area Under the ROC Curve (AUC) and lower Mean Absolute Error (MAE).

Conclusions:

The novel method effectively handles segmentation challenges like noise and intensity inhomogeneity.
Demonstrates superior accuracy and similarity for malignant tumor segmentation in complex ultrasound images.