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

Beyond side effects: treatment-related adverse events are associated with improved survival outcomes in HCC patients on atezolizumab-bevacizumab therapy.

BMC cancer·2026
Same author

Automated segmentation reveals sex-divergent age-related decline in temporalis muscle volume among Asian adults.

Scientific reports·2026
Same author

Advancements in fire-related toxic gas detection and prophylactic strategies: A focus on cyanide concentration analysis and antidote efficacy in controlled smoke inhalation models.

PloS one·2026
Same author

Computational pathology model to predict recurrence-free survival in NMPUC patients on BCG-therapy.

NPJ precision oncology·2026
Same author

Poly(vinyl alcohol)/Chitosan/Glycine Composite-Based Eco-Friendly Biodegradable Triboelectric Nanogenerators.

ACS omega·2026
Same author

Exploring XDH expression as a prognostic marker for urothelial carcinoma.

Discover oncology·2026

Related Experiment Video

Updated: Aug 9, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Development of Deep Learning with RDA U-Net Network for Bladder Cancer Segmentation.

Ming-Chan Lee1, Shao-Yu Wang2, Cheng-Tang Pan1,3

  • 1Department of Mechanical and Electro-Mechanical Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan.

Cancers
|February 25, 2023
PubMed
Summary

This study introduces a novel Residual-Dense Attention U-Net model for identifying bladder and lesions in CT scans. The AI model achieves high accuracy and significantly reduces processing time, aiding medical diagnoses.

Keywords:
DenseNetResNetU-Netbladder cancercomputed tomography

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

471

Related Experiment Videos

Last Updated: Aug 9, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K
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

471

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Deep Learning

Background:

  • Medical imaging, particularly Computed Tomography (CT), is crucial in health examinations.
  • AI-driven image recognition offers potential for enhanced diagnostic accuracy in radiology.
  • Accurate identification and segmentation of organs and lesions in CT scans are vital for patient care.

Purpose of the Study:

  • To develop an advanced deep learning model for precise identification and segmentation of the bladder and its lesions in abdominal CT images.
  • To improve the efficiency and accuracy of medical image analysis using artificial intelligence.
  • To reduce the computational time required for analyzing medical scans.

Main Methods:

  • Utilized a modified U-Net neural network architecture, incorporating ResBlock (from ResNet) and Dense Block (from DenseNet) in the encoder.
  • Integrated Attention Gates in the decoder to focus on relevant image features and suppress irrelevant areas.
  • Developed a Residual-Dense Attention (RDA) U-Net model for organ and lesion identification and segmentation.

Main Results:

  • The RDA U-Net model achieved high accuracy for bladder identification (96% ACC) and lesion identification (93% ACC).
  • Demonstrated strong segmentation performance with Intersection over Union (IoU) values of 0.9505 for the bladder and 0.8024 for lesions.
  • Achieved a low Average Hausdorff Distance (AVGDIST) of 0.02 for the bladder and 0.12 for lesions.
  • Reduced overall training time by up to 44% compared to other convolutional neural networks.

Conclusions:

  • The proposed RDA U-Net model effectively identifies and segments the bladder and lesions in CT images with high accuracy.
  • The integration of residual and dense blocks with attention mechanisms enhances model performance and efficiency.
  • This AI approach shows significant promise for improving the speed and precision of medical image analysis in clinical settings.