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

Topological imaging of single-cell CAF heterogeneity for predicting prognosis and adjuvant chemotherapy benefit in pancreatic cancer.

European journal of radiology·2026

Same author

Intelligent compensation method for measurement errors in optical fiber current sensor caused by temperature variation based on the Levy-Weighted-QPSO-NN algorithm.

PloS one·2026

Same author

Neurotoxicity mechanism of polychlorinated biphenyl mediated by dopaminergic system.

Ecotoxicology and environmental safety·2026

Same author

Oleanolic acid alleviates hepatic fibrosis by inhibiting liver macrophage recruitment and polarization.

Molecular immunology·2026

Same author

Expert consensus on robotic radiosurgery system for hepatocellular carcinoma.

Journal of cancer research and therapeutics·2026

Same author

Microenvironmental Regulation of Central Nervous System Myelination and Remyelination.

Journal of integrative neuroscience·2026

Search research articles

Related Experiment Video

Updated: Jul 12, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Brain tumor image segmentation based on improved FPN.

Haitao Sun¹, Shuai Yang², Lijuan Chen¹

¹Department of Radiotherapy Room, Zhongshan Hospital of Traditional Chinese Medicine, ZhongShanGuangdong Province, 528400, China.

BMC Medical Imaging

|October 31, 2023

Summary

An improved Feature Pyramid Network (FPN) model enhances brain tumor segmentation accuracy. This deep learning approach offers superior detail and generalization for clinical diagnosis compared to other methods.

Keywords:

Brain tumor segmentation Full convolutional neural network Improved FPN model U-Net model

More Related Videos

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

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

Related Experiment Videos

Last Updated: Jul 12, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

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

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

Area of Science:

Medical Image Analysis
Deep Learning
Computational Neuroscience

Background:

Automatic brain tumor segmentation is a critical area in medical imaging.
Traditional methods like Full Convolutional Networks (FCNs) struggle with detail loss.

Purpose of the Study:

To improve brain tumor segmentation using an enhanced deep learning model.
To address limitations of traditional methods in capturing tumor details.

Main Methods:

An improved Feature Pyramid Network (FPN) integrated into a U-Net architecture.
Capturing multi-scale contextual information and improving adaptability to various feature scales.

Main Results:

Achieved 99.1% accuracy, 92% DICE, and 86% Jaccard index.
Demonstrated superior performance over existing segmentation models, preserving finer tumor details.

Conclusions:

The proposed FPN-based method effectively segments brain tumors with good generalization.
Offers significant potential for improving clinical diagnosis of brain tumors.