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

Viral pneumonia detection during the COVID-19 pandemic using deep learning and DCGAN-based data augmentation.

Scientific reports·2026
Same author

Ethical concerns and strategies for implementing artificial intelligence in healthcare: a review of empirical studies.

BMC medical ethics·2026
Same author

Deep learning-based automatic segmentation and classification for cervical cancer detection using an improved U-Net and ensemble methods.

Scientific reports·2026
See all related articles

Related Experiment Video

Updated: Sep 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

528

SPP-SegNet and SE-DenseNet201: A Dual-Model Approach for Cervical Cell Segmentation and Classification.

Betelhem Zewdu Wubineh1, Andrzej Rusiecki1, Krzysztof Halawa1

  • 1Faculty of Information and Communication Technology, Wroclaw University of Science and Technology, 50-370 Wroclaw, Poland.

Cancers
|July 12, 2025
PubMed
Summary

This study introduces advanced deep learning models, SPP-SegNet and SE-DenseNet201, for automated cervical cancer detection from Pap smear images. These models significantly improve segmentation and classification accuracy, aiding early diagnosis.

Keywords:
SE-DenseNet201SegNetcervical cancerclassificationimage segmentation

More Related Videos

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
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.7K

Related Experiment Videos

Last Updated: Sep 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

528
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
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.7K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Oncology

Background:

  • Cervical cancer is a major global health concern, with manual Pap smear analysis being time-consuming and error-prone.
  • Automating the analysis of cervical cell images can improve diagnostic efficiency and accuracy.

Purpose of the Study:

  • To develop and evaluate novel deep learning models for automated segmentation and classification of cervical cancer cells.
  • To enhance the accuracy and efficiency of cervical cancer detection using AI.

Main Methods:

  • A novel SegNet-based spatial pyramid pooling (SPP-SegNet) model was developed for image segmentation, incorporating SPP bottleneck and atrous convolution for multiscale feature extraction.
  • A Squeeze-and-Excitation-based (SE-DenseNet201) model was used for classification, utilizing segmentation outputs or bounding box inputs.
  • The models were evaluated on the Pomeranian and SIPaKMeD datasets.

Main Results:

  • SPP-SegNet achieved high segmentation accuracy: 98.53% on Pomeranian and 94.15% on SIPaKMeD datasets, outperforming standard SegNet.
  • SE-DenseNet201 demonstrated strong classification performance, achieving 93% accuracy on Pomeranian and 99% on SIPaKMeD datasets for binary classification.

Conclusions:

  • The proposed SPP-SegNet and SE-DenseNet201 models show significant potential for automating cervical cell segmentation and classification.
  • These AI-driven tools can facilitate earlier and more accurate detection and diagnosis of cervical cancer.