Jove
Visualize
Contact Us

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

A Pyramid Architecture-Based Deep Learning Framework for Breast Cancer Detection.

BioMed research international·2021
Same author

Effects of maximal sodium and potassium conductance on the stability of Hodgkin-Huxley model.

Computational and mathematical methods in medicine·2014
Same author

A pipeline for neuron reconstruction based on spatial sliding volume filter seeding.

Computational and mathematical methods in medicine·2014
Same author

Apoptosis-inducing effect and structural basis of Polygonatum cyrtonema lectin and chemical modification properties on its mannose-binding sites.

BMB reports·2008
Same author

The catalytic intermediate stabilized by a "down" active site loop for diaminopimelate decarboxylase from Helicobacter pylori. Enzymatic characterization with crystal structure analysis.

The Journal of biological chemistry·2008
Same author

Monitoring prostate thermal therapy with diffusion-weighted MRI.

Magnetic resonance in medicine·2008
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 Experiment Video

Updated: Oct 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

561

CST: A Multitask Learning Framework for Colorectal Cancer Region Mining Based on Transformer.

Dong Sui1, Kang Zhang1, Weifeng Liu1

  • 1School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China.

Biomed Research International
|October 21, 2021
PubMed
Summary

This study introduces a novel AI framework, CST, for accurate colorectal cancer detection and segmentation in medical images. The transformer-based approach improves diagnostic efficiency and accuracy, offering a new AI pathway for colorectal cancer screening.

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

981

Related Experiment Videos

Last Updated: Oct 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

561
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

981

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Colorectal cancer remains a leading cause of cancer-related mortality.
  • Accurate tumor region diagnosis is critical but time-consuming and prone to inter-observer variability.
  • Automated detection and segmentation of colorectal cancer from CT/MRI images present significant challenges.

Purpose of the Study:

  • To develop a novel, unified framework for joint colorectal cancer region detection and segmentation.
  • To enhance detection accuracy using an autoencoder-based image-level decision approach.
  • To provide an AI-driven alternative for colorectal cancer screening.

Main Methods:

  • Proposed a novel transfer learning protocol named CST (Colorectal cancer Segmentation and Detection).
  • Utilized a transformer model for joint detection and segmentation of colorectal cancer regions.
  • Incorporated an autoencoder-based image-level decision mechanism to improve slice-level accuracy.

Main Results:

  • The CST framework demonstrated superior performance in both detection and segmentation tasks compared to traditional one-stage and two-stage object detection methods.
  • The integrated autoencoder approach enhanced the overall accuracy of cancer slice identification.
  • The study validates the efficacy of the proposed AI framework for colorectal cancer diagnosis.

Conclusions:

  • The CST framework offers an effective and accurate AI solution for colorectal cancer region detection and segmentation.
  • This novel approach can significantly reduce diagnostic time and inter-observer variability.
  • The proposed method provides a promising new pathway for AI-assisted colorectal cancer screening.