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

Arsenic trioxide depletes cancer stem-like cells and inhibits repopulation of neurosphere derived from glioblastoma by downregulation of Notch pathway.

Toxicology letters·2013
Same author

A prospective, randomized, open-label study comparing the efficacy and safety of preprandial and prandial insulin in combination with acarbose in elderly, insulin-requiring patients with type 2 diabetes mellitus.

Diabetes technology & therapeutics·2013
Same author

Synthesis of the C-18-C-34 fragment of amphidinolides C, C2, and C3.

Organic letters·2013
Same author

Synthesis of the C-1-C-17 fragment of amphidinolides C, C2, C3, and F.

Organic letters·2013
Same author

77Se solid-state NMR of As2Se3, As4Se4 and As4Se3 crystals: a combined experimental and computational study.

Physical chemistry chemical physics : PCCP·2013
Same author

Nanocellulose electroconductive composites.

Nanoscale·2013

Related Experiment Video

Updated: Nov 1, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.1K

A Deep Multi-Task Learning Framework for Brain Tumor Segmentation.

He Huang1, Guang Yang2,3, Wenbo Zhang1

  • 1College of Medical Technology, Zhejiang Chinese Medical University, Hangzhou, China.

Frontiers in Oncology
|June 21, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a deep multi-task learning framework for automated brain tumor segmentation in MRI scans. The novel approach enhances accuracy by integrating a distance transform decoder and multi-depth fusion, achieving a 78% average Dice score.

Keywords:
automatic segmentationbrain tumordeep multi-task learning frameworkmagnetic resonance imagingmulti-depth fusion module

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

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

Published on: April 13, 2013

43.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.8K

Related Experiment Videos

Last Updated: Nov 1, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.1K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

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

Published on: April 13, 2013

43.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.8K

Area of Science:

  • Medical imaging
  • Artificial intelligence
  • Neuro-oncology

Background:

  • Gliomas are the most common primary brain tumors, necessitating accurate segmentation from MRI for effective clinical management.
  • Manual segmentation of brain tumors from MRI is time-consuming and prone to inaccuracies, hindering timely diagnosis and treatment.
  • Existing automated methods struggle with class imbalance and distinguishing tumors from strokes, posing challenges for reliable segmentation.

Purpose of the Study:

  • To develop an automated deep learning framework for accurate brain tumor segmentation in multispectral MRI.
  • To improve segmentation contour accuracy and reduce boundary artifacts using a novel V-Net-based distance transform decoder.
  • To enhance feature extraction capabilities through an integrated multi-depth fusion module in the encoder.

Main Methods:

  • A deep multi-task learning framework incorporating a V-Net-based distance transform decoder and a multi-depth fusion module was proposed.
  • The framework utilizes a weighted combination of loss functions, where distance map prediction regularizes mask prediction for improved contour accuracy.
  • The model was trained and evaluated on multispectral MRI data from the BraTS 2018, 2019, and 2020 datasets.

Main Results:

  • The proposed framework achieved high-quality brain tumor segmentation results.
  • The average Dice similarity coefficient reached 78%, indicating significant improvement in segmentation accuracy.
  • The distance transform decoder effectively refined segmentation contours, reducing rough boundaries.

Conclusions:

  • The developed deep multi-task learning framework demonstrates strong potential for accurate and automated brain tumor segmentation in MRI.
  • The integration of distance transform decoding and multi-depth fusion significantly enhances segmentation performance.
  • This approach offers a promising solution to overcome challenges in brain tumor segmentation, including class imbalance and feature extraction.