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 Experiment Videos

An EfficientNet-based hierarchical dual-encoder framework for multi-scale gastrointestinal disease detection.

Routhu Srinivasa Rao1, Dasari Siva Krishna2, Kolipakula Jhatesh Gupta3

  • 1Department of Information and Communication Engineering, Chosun University, Gwangju, 61452, Republic of Korea.

Scientific Reports
|June 19, 2026
PubMed
Summary

Related Concept Videos

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

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy

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 solid...

You might also read

Related Articles

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

Sort by
Same author

Centrifugal pump analysis and prediction in cavitation using RapidMiner tool and machine learning algorithms.

Scientific reports·2026
Same author

Deep locomotion prediction learning over biosensors, ambient sensors, and computer vision.

PloS one·2026
Same author

BONE-Net: A novel hybrid deep-learning model for effective osteoporosis detection.

PloS one·2025
Same author

Autonomous vehicle surveillance through fuzzy C-means segmentation and DeepSORT on aerial images.

PeerJ. Computer science·2025
Same author

A hybrid super learner ensemble for phishing detection on mobile devices.

Scientific reports·2025
Same author

StopSpamX: A multi modal fusion approach for spam detection in social networking.

MethodsX·2025
Same journal

Peripheral B-cell receptor repertoire predicts immune-related adverse events following immune checkpoint inhibitor therapy in advanced renal cell carcinoma.

Scientific reports·2026
Same journal

Effects of black soldier fly (Hermetia illucens L.) larvae zoocompost on the mineral element content of blue honeysuckle berries.

Scientific reports·2026
Same journal

Investigation on absorption refrigeration performance of R1243zf with imidazolium ionic liquid as the working pairs.

Scientific reports·2026
Same journal

DeepTriage-CN: integrating clinical text with vital signs for emergency department admission prediction in an aging population.

Scientific reports·2026
Same journal

Gold nanoparticles as dual-action antiviral agents: disruption of SARS-CoV-2 viral envelopes and RNA integrity.

Scientific reports·2026
Same journal

Comparison of capillary microsampling and venous blood for multi-pathogen serosurveillance.

Scientific reports·2026
See all related articles
This summary is machine-generated.

This study introduces a novel dual-backbone convolutional framework for improved gastrointestinal (GI) disease diagnosis from endoscopic images. The advanced model enhances diagnostic accuracy by integrating local details and global context, outperforming existing methods.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Gastrointestinal (GI) diseases pose a significant global health challenge.
  • Accurate and timely diagnosis of GI conditions is crucial for effective patient management.
  • Current diagnostic methods for endoscopic images require enhancement for improved accuracy.

Purpose of the Study:

  • To develop and validate a novel dual-backbone convolutional neural network (CNN) framework for enhanced diagnosis of GI diseases using endoscopic imagery.
  • To integrate fine-grained local details with high-level global context for more robust image analysis.
  • To improve the accuracy and efficiency of automated GI disease detection.

Main Methods:

  • A dual-backbone CNN framework combining EfficientNet-B0 and EfficientNet-B4 was designed.
Keywords:
ClassificationDeep learningEfficientnetGastrointestinal

Related Experiment Videos

  • Feature streams were fused using residual learning, channel attention (CBAM), and 1x1 convolutions.
  • Techniques such as MixUp augmentation, Stochastic Weight Averaging (SWA), and dropout regularization were employed to enhance generalization and prevent overfitting.

    • Main Results:

    • The proposed framework achieved an overall accuracy of 84.11% and a Macro-F1-score of 72.11%.
    • The dual-backbone approach consistently outperformed single-backbone EfficientNet variants and other baseline models.
    • The method demonstrated effective adaptive emphasis on diagnostically relevant regions and suppression of background noise.

    Conclusions:

    • The developed dual-backbone CNN framework offers superior performance for diagnosing GI diseases from endoscopic images compared to existing methods.
    • The integration of diverse feature extraction capabilities and advanced training techniques leads to improved diagnostic accuracy and robustness.
    • This AI-driven approach holds significant potential for advancing clinical outcomes in gastroenterology through more precise and efficient disease detection.