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

UCTLFANet: a low-rank fine-tuning model for microalgae image segmentation.

Scientific reports·2026
Same author

Comparison of DLIR-H and ASIR algorithms for image reconstruction in low-dose chest CT of pediatric mycoplasma pneumoniae pneumonia: a cross-sectional study.

Translational pediatrics·2026
Same author

Red OLED with efficiency of 25.6% at 10,000 cd m<sup>-2</sup> based on selenium embedding multiple resonance framework.

Light, science & applications·2026
Same author

Recent progress of narrowband iridium(III) complexes for organic light-emitting diodes.

Materials horizons·2026
Same author

Vibrational-State-Regulated Hot-Band Thermal Activation for Anti-Stokes Luminescence.

The journal of physical chemistry letters·2026
Same author

Constructing High-Efficiency and Stable Hyperfluorescence Blue OLEDs via TADF Sensitizers with Very Short Delayed Lifetimes.

Angewandte Chemie (International ed. in English)·2025

Related Experiment Video

Updated: Aug 14, 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

2.9K

A comparative study of attention mechanism based deep learning methods for bladder tumor segmentation.

Qi Zhang1, Yinglu Liang1, Yi Zhang1

  • 1School of Information Technology & Management, University of International Business & Economics, Beijing 100029, China.

International Journal of Medical Informatics
|January 12, 2023
PubMed
Summary

This study introduces an attention mechanism-based cystoscopic image segmentation (ACS) model for improved bladder tumor detection. The ACS model significantly enhances tumor segmentation accuracy, offering a valuable tool for clinical cystoscopy procedures.

Keywords:
Attention mechanismBladder cancerDeep learningImage segmentationIntelligent diagnosis

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

476
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

601

Related Experiment Videos

Last Updated: Aug 14, 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

2.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

476
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

601

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Artificial intelligence (AI) aids tumor segmentation in medical imaging, but its application in cystoscopic images is underexplored.
  • Accurate segmentation of bladder tumors from cystoscopic images is crucial for diagnosis and treatment planning.

Purpose of the Study:

  • To compare various attention modules for enhancing bladder tumor segmentation using cystoscopic images.
  • To introduce a novel Attention mechanism based Cystoscopic images Segmentation (ACS) model for improved performance.

Main Methods:

  • A comprehensive comparison of attention modules was conducted on cystoscopic images (2017-2022).
  • The proposed ACS model integrates mixed attention (channel and spatial), guidance and fusion attention, and inception attention modules.
  • These modules are strategically placed in the encoder-decoder path, skip connections, and at the pixel level to optimize feature extraction and fusion.

Main Results:

  • The ACS model demonstrated superior tumor segmentation performance compared to existing methods.
  • Achieved a Dice score of 82.7% and Mean Intersection over Union (MIoU) of 69%.

Conclusions:

  • The ACS model significantly outperforms traditional U-Net based methods for bladder tumor segmentation.
  • The ACS model is a promising AI-powered tool to assist physicians in tumor segmentation during cystoscopy.