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

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy01:26

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy

131
This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
131

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

EnsemDeepCADx: Empowering Colorectal Cancer Diagnosis with Mixed-Dataset Features and Ensemble Fusion CNNs on Evidence-Based CKHK-22 Dataset.

Bioengineering (Basel, Switzerland)·2023
Same author

Dexterous Identification of Carcinoma through ColoRectalCADx with Dichotomous Fusion CNN and UNet Semantic Segmentation.

Computational intelligence and neuroscience·2022
Same author

Containerized Architecture Performance Analysis for IoT Framework Based on Enhanced Fire Prevention Case Study: Rwanda.

Sensors (Basel, Switzerland)·2022
Same author

Non-invasive technique to detect diabetic retinopathy based on Electrooculography signal using machine learning classifiers.

Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine·2022
Same author

Speed Management Strategy: Designing an IoT-Based Electric Vehicle Speed Control Monitoring System.

Sensors (Basel, Switzerland)·2021
Same author

Non-invasive thyroid detection based on electroglottogram signal using machine learning classifiers.

Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine·2021

Related Experiment Video

Updated: Aug 20, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

177

ColoRectalCADx: Expeditious Recognition of Colorectal Cancer with Integrated Convolutional Neural Networks and Visual

Akella S Narasimha Raju1, Kayalvizhi Jayavel1, T Rajalakshmi2

  • 1Department of Networking and Communications, School of Computing, SRM Institute of Science and Technology, Kattankulathur, 603203 Chennai, India.

Computational and Mathematical Methods in Medicine
|November 21, 2022
PubMed
Summary

ColoRectalCADx, a deep learning system, enhances colorectal cancer detection using 21 convolutional neural networks (CNNs) and other models. It achieves high accuracy in identifying polyps and malignancies, improving computer-assisted diagnosis (CADx).

More Related Videos

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.4K
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

605

Related Experiment Videos

Last Updated: Aug 20, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

177
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.4K
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

605

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Oncology

Background:

  • Colorectal cancer detection relies on colonoscopy, with current computer-assisted diagnosis (CADx) systems limited by deep learning methods and lack of mixed datasets.
  • Existing CADx systems often do not incorporate diverse datasets, potentially limiting their diagnostic accuracy and generalizability.

Purpose of the Study:

  • To develop and evaluate ColoRectalCADx, a novel deep learning-based CADx system for enhanced colorectal cancer detection.
  • To integrate multiple deep learning models, including convolutional neural networks (CNNs), support vector machine (SVM), and long short-term memory (LSTM), for improved polyp and malignancy identification.

Main Methods:

  • The ColoRectalCADx system employs a five-stage pipeline: CNNs, SVM, LSTM, gradient-weighted class activation mapping (Grad-CAM) for visual explanation, and U-Net for semantic segmentation.
  • The system utilizes a mixed dataset comprising CVC Clinic DB, Kvasir2, and Hyper Kvasir, and incorporates 9 individual and 12 integrated CNNs (total 21 CNNs).
  • Transfer learning functions are combined with SVM classification, followed by CNN to LSTM classification, and advanced analysis using Grad-CAM and U-Net for polyp and malignancy detection.

Main Results:

  • Individual CNN DenseNet-201 (87.1% training, 84.7% testing accuracy) and integrated CNN ADaDR-22 (84.61% training, 82.17% testing accuracy) demonstrated the highest efficiency for cancer detection within the CNN+LSTM model.
  • ColoRectalCADx accurately identified cancer using DenseNet-201 and ADaDR-22.
  • Grad-CAM visualizations with CNN DenseNet-201 precisely depicted polyps, while CNN U-Net accurately identified malignant polyps.

Conclusions:

  • The proposed ColoRectalCADx system, leveraging a combination of deep learning models and mixed datasets, significantly improves the accuracy of colorectal cancer detection.
  • The integration of CNNs, LSTM, Grad-CAM, and U-Net provides a robust framework for identifying polyps and malignancies, with specific CNN architectures showing superior performance.
  • ColoRectalCADx demonstrates potential for advancing computer-assisted diagnosis in gastroenterology, offering precise visualization and accurate detection of cancerous lesions.