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

Automatic segmentation and PI-RADS grading of prostate cancer for biparametric MRI.

Frontiers in medicine·2026
Same author

Fibrosis of Periprostatic Adipose Tissue: A Potential Marker of Prostate Cancer Aggressiveness.

Cancers·2026
Same author

Feature Augmentation-Based Adaptive Neural Network Control for Quadrotors.

Sensors (Basel, Switzerland)·2026
Same author

Multi-Perturbation Consistency Learning for Semi-Supervised Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2025
Same author

Coordinated Dual-Fin Actuation of Bionic Ocean Sunfish Robot for Multi-Modal Locomotion.

Biomimetics (Basel, Switzerland)·2025
Same author

Gland- and cell-level heterogeneity in the prostate: A narrative review of related diseases.

Current urology·2025

Related Experiment Video

Updated: Jul 18, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

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

Published on: December 15, 2023

2.5K

Attention-guided multi-scale learning network for automatic prostate and tumor segmentation on MRI.

Yuchun Li1, Yuanyuan Wu1, Mengxing Huang1

  • 1State Key Laboratory of Marine Resource Utilization in South China Sea, College of Information and Communication Engineering, Hainan University, Haikou 570288, China.

Computers in Biology and Medicine
|August 23, 2023
PubMed
Summary

This study introduces a novel deep learning network for segmenting prostate and prostate cancer in MRI scans. The method achieves high accuracy, improving image-guided diagnosis and surgical planning for prostate cancer patients.

Keywords:
Deep supervisionDiffusion weighted imagingFeature fusionMultiscale attentionProstatic cancer

More Related Videos

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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Related Experiment Videos

Last Updated: Jul 18, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

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

Published on: December 15, 2023

2.5K
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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Accurate segmentation of prostate and cancerous tumors in MRI is crucial for image-guided diagnosis and surgical planning.
  • Challenges include subtle morphological differences, blurred boundaries, and uneven tissue classification.
  • Existing segmentation methods struggle with the complexity of prostate cancer detection in MRI.

Purpose of the Study:

  • To develop and evaluate a novel deep learning network for enhanced segmentation of prostate and prostatic cancer in male pelvic MRI.
  • To improve the accuracy and reliability of automated segmentation for clinical applications.

Main Methods:

  • A novel prostate and prostatic cancer segmentation network utilizing a double branch attention-driven multi-scale learning approach for MRI.
  • Dual branch structure with multi-scale attention module for feature extraction at different scales.
  • Feature fusion module for comprehensive context information and deep supervision for precise learning representation.

Main Results:

  • The proposed network demonstrated superior performance compared to existing techniques for prostate and tumor segmentation in male pelvic MRI datasets.
  • Achieved Dice Similarity Coefficient (DSC) values of 91.65% for prostate and 84.39% for prostatic cancer segmentation.
  • Maintained high correlation and consistency with expert manual segmentation.

Conclusions:

  • The developed deep learning method offers accurate automatic segmentation of prostate and prostate cancer from MRI.
  • This advancement holds significant clinical importance for improving diagnostic accuracy and treatment planning.
  • The approach enhances image-guided clinical diagnosis and supports precise surgical interventions.