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 Video

Updated: Jun 17, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

A Novel Network-Level Fused Self-Attention Deep Neural Network for Cervical Cancer Classification from Cervicography

Muhammad Attique Khan1, Fatima Rauf1, Muhammad John Abbas1

  • 1Center of Artificial Intelligence, College of Computer Engineering and Science, Prince Mohammad Bin Fahd University, Al Khobar, Saudi Arabia.

Technology in Cancer Research & Treatment
|February 28, 2026
PubMed
Summary

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

TriDermCancerNet: A hybrid deep learning framework for skin cancer classification.

The Journal of international medical research·2026
Same author

Quantum-enhanced spiking intelligence framework for real-time anomaly detection in industrial internet of things.

Scientific reports·2026
Same author

Eye-hand coordination patterns of progressive and consistent micrographia in Parkinson's disease: neurophysiological correlates.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same author

From local textures to global attention: a hybrid feature fusion network for skin lesion classification.

Scientific reports·2026
Same author

Navigating the Impossible Gallbladder: Bailout Strategies and Culture of Safety in Laparoscopic Cholecystectomy.

Cureus·2026
Same author

ATEdrug: A reliable human-in-the-loop annotation scheme for aspect term extraction and polarity detection in drug reviews.

PloS one·2026

A novel computer-aided diagnosis system accurately classifies cervical cancer from cervicography images using deep learning. This automated approach shows promise for improving early detection in resource-limited settings.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Cervical cancer is a leading cause of death for women globally, particularly in developing countries due to limited screening and expertise.
  • Cervicography images are crucial for diagnosis but present challenges due to high intra-class variability.
  • Automated diagnostic tools are needed to improve accuracy and accessibility.

Purpose of the Study:

  • To develop a fully automated computer-aided diagnosis (CAD) system for cervical cancer classification using cervicography images.
  • To introduce novel deep learning architectures, 11-Parallel Inverted Residual Bottleneck Blocks (11-PIRBnet) and 9-Parallel Inverted Residual blocks with Self-Attention Mechanism (9-PIRSANet).
  • To fuse these modules into a new network, 375NFNet, for enhanced feature extraction and classification.
Keywords:
cervical cancer (CrC)cervicography imagesdeep learninghyperparametersnetworks fusionshallow neural network

Related Experiment Videos

Last Updated: Jun 17, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Main Methods:

  • Data augmentation was employed to address dataset imbalance.
  • The 375NFNet architecture, integrating 11-PIRBnet and 9-PIRSANet, was developed and trained.
  • Hyperparameters were optimized using Bayesian Optimization (BO), and features were classified using a shallow neural network (SNN).

Main Results:

  • The proposed 375NFNet achieved 95.5% accuracy, 95.4% precision, and an AUC of 0.97 on a public cervicography dataset.
  • Significant improvements were observed compared to existing pre-trained techniques in accuracy and precision.
  • The model demonstrated efficiency with a reduced number of trainable parameters.

Conclusions:

  • The 375NFNet architecture offers a highly accurate and efficient method for classifying cervical cancer from cervicography images.
  • This automated CAD system has the potential to be a valuable tool for cervical cancer screening, especially in resource-constrained environments.
  • The study highlights the efficacy of deep learning in overcoming diagnostic challenges posed by image variability.