Search research articles

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

Insects as an Alternative Protein Source: A Sustainable Approach to Future Food Security.

Insects·2026

Same author

A hybrid optimized framework with energy shape prior segmentation for brain tumor detection in MRI images.

Digital health·2026

Same author

Enhancing E-health system accuracy using Rendezvous Data Processing Model (RDPM) with IoT-cloud integration.

Digital health·2026

Same author

From Annotation to Prediction: Hospital-Grade Early Seizure Risk Prediction from Adult EEG.

Diagnostics (Basel, Switzerland)·2026

Same author

Total Synthesis of (±)-Dhilirolide U.

Journal of the American Chemical Society·2026

Same author

Enhancing skin lesion classification: a CNN approach with human baseline comparison.

PeerJ. Computer science·2025

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

Search research articles

Related Experiment Video

Updated: Sep 18, 2025

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

LIU-NET: lightweight Inception U-Net for efficient brain tumor segmentation from multimodal 3D MRI images.

Gul E Sehar Shahid¹, Jameel Ahmad², Chaudary Atif Raza Warraich³

¹Department of Artificial Intelligence, University of Management & Technology, Lahore, Pakistan.

Peerj. Computer Science

|June 26, 2025

Summary

This study introduces LIU-Net, a computationally efficient deep learning model for precise brain tumor segmentation. LIU-Net achieves high accuracy on benchmark datasets, improving detection in challenging regions.

Keywords:

3D MRI BraTS 2020 BraTS 2021 Brain tumor segmentation Deep learning Inception-style blocks Medical image analysis U-NET architecture

More Related Videos

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

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Sep 18, 2025

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

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

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Medical Imaging
Artificial Intelligence
Computational Neuroscience

Background:

Accurate brain tumor segmentation is crucial for diagnosis and treatment planning.
Existing deep learning models face challenges like computational complexity and handling diverse tumor characteristics.
Advanced strategies are needed to improve segmentation accuracy, especially in complex or subtle tumor regions.

Purpose of the Study:

To develop a novel, computationally efficient deep learning method for accurate brain tumor segmentation.
To address challenges of computational complexity, gradient vanishing, and feature variations in tumor segmentation.
To introduce the lightweight Inception U-Net (LIU-Net) model for improved medical image analysis.

Main Methods:

Developed LIU-Net, integrating Inception blocks into a U-Net architecture for multiscale feature capture.
Employed a combination of Dice loss and Focal loss to effectively manage class imbalance issues.
Utilized the BraTS 2021 dataset for initial evaluation and the BraTS 2020 dataset for external validation.

Main Results:

LIU-Net achieved high Dice scores on the BraTS 2021 test set: 0.8121 (enhancing tumor), 0.8856 (whole tumor), and 0.8444 (tumor core).
Cross-validation on the BraTS 2020 dataset demonstrated robust performance with Dice scores of 0.8646 (ET), 0.9027 (WT), and 0.9092 (TC).
The model effectively captures multiscale features and preserves spatial information, outperforming existing methods in challenging segmentation scenarios.

Conclusions:

The proposed LIU-Net model demonstrates significant effectiveness and computational efficiency for brain tumor segmentation.
Integrating Inception blocks into the U-Net architecture enhances the ability to capture multiscale features crucial for segmentation accuracy.
LIU-Net shows promise as a valuable tool for medical image segmentation tasks, particularly in oncology.