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

High Precision Calibration Algorithm for Binocular Stereo Vision Camera using Deep Reinforcement Learning.

Computational intelligence and neuroscience·2022
Same author

Edge detection algorithm of cancer image based on deep learning.

Bioengineered·2020
Same author

[Effects of Pa-pex 11 gene on penicillin production in Penicillium aurantiogriseum].

Wei sheng wu xue bao = Acta microbiologica Sinica·2010
Same author

Inhibition of lung fluid clearance and epithelial Na+ channels by chlorine, hypochlorous acid, and chloramines.

The Journal of biological chemistry·2010
Same author

Discovery and optimization of novel 3-piperazinylcoumarin antagonist of chemokine-like factor 1 with oral antiasthma activity in mice.

Journal of medicinal chemistry·2010
Same author

Evidence for dimeric BACE-mediated APP processing.

Biochemical and biophysical research communications·2010

Related Experiment Video

Updated: Sep 21, 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

3.0K

Segmentation for Multimodal Brain Tumor Images Using Dual-Tree Complex Wavelet Transform and Deep Reinforcement

Gang Liu1,2, Xiaofeng Li3, Yingjie Cai4

  • 1College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China.

Computational Intelligence and Neuroscience
|June 3, 2022
PubMed
Summary

This study introduces a novel deep reinforcement learning (DRL) and dual-tree complex wavelet transform (DTCWT) algorithm for accurate brain tumor image segmentation. The method effectively removes noise while preserving crucial image details and edges.

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

42.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.4K

Related Experiment Videos

Last Updated: Sep 21, 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

3.0K
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

42.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.4K

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Artificial Intelligence

Background:

  • Accurate medical image segmentation is crucial for computer-aided diagnosis and treatment.
  • Existing methods often struggle with noise and preserving fine details in multimodal brain tumor images.

Purpose of the Study:

  • To propose a novel segmentation algorithm combining deep reinforcement learning (DRL) and dual-tree complex wavelet transform (DTCWT) for multimodal brain tumor images.
  • To enhance segmentation accuracy by effectively removing noise and retaining image features and edges.

Main Methods:

  • Utilized DTCWT for noise identification and transformation into normal pixel points using bivariate concepts.
  • Calculated conditional probabilities for marker points to achieve initial image segmentation.
  • Constructed a DRL framework for optimizing segmentation results through network training with a loss function.

Main Results:

  • The algorithm effectively removed noise from multimodal brain tumor images.
  • Segmented images demonstrated excellent retention of detail features and edges, with high similarity to original images.
  • Achieved a low information loss index (0.18), minimal boundary error (approx. 0.3), and a high F-value, indicating accuracy and efficiency.

Conclusions:

  • The proposed DRL and DTCWT algorithm provides accurate and efficient segmentation of multimodal brain tumor images.
  • The method shows practical applicability due to its ability to preserve image details and minimize segmentation errors.