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

Multiobjective framework for hardware and quality aware approximate Gaussian filtering toward energy efficient ultrasound image denoising.

Scientific reports·2026
Same author

Incremental learning approach for semantic segmentation of skin histology images.

Scientific reports·2026
Same author

Acceptance as a Response to Suffering: Insights from World Religious and Philosophical Traditions.

Journal of religion and health·2026
Same author

ViT-Stain: Vision transformer-driven virtual staining for skin histopathology via global contextual learning.

PloS one·2026
Same author

VISGAB: Virtual staining-driven GAN benchmarking for optimizing skin tissue histology.

Scientific reports·2025
Same author

Mathematical modeling of heart rate tracking in motion affected PPG signals.

Scientific reports·2025

Related Experiment Video

Updated: Jun 11, 2025

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

2.7K

A Modified Deep Semantic Segmentation Model for Analysis of Whole Slide Skin Images.

Muhammad Zeeshan Asaf1, Hamid Rasul1, Muhammad Usman Akram2

  • 1Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad, 44000, Pakistan.

Scientific Reports
|October 8, 2024
PubMed
Summary

This study introduces an improved deep semantic segmentation model for biomedical image analysis. The novel approach enhances accuracy in segmenting non-melanoma skin cancer images, aiding computer-aided diagnosis.

Keywords:
EfficientNet-B3Ensemble modelSemantic segmentationU-NetWhole slide image segmentation

More Related Videos

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

Related Experiment Videos

Last Updated: Jun 11, 2025

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

2.7K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Histopathology

Background:

  • Automated biomedical image segmentation is crucial for computer-aided diagnosis but faces challenges due to image variations.
  • Current semantic segmentation models can be complex and slow, hindering the processing of large datasets.
  • There is a need for efficient and accurate image processing techniques for biomedical segmentation.

Purpose of the Study:

  • To develop a modified deep semantic segmentation model for reliable biomedical image segmentation.
  • To improve the accuracy and efficiency of segmenting non-melanoma skin cancer in histopathology images.
  • To address the limitations of existing models in handling variations in color, texture, and shape.

Main Methods:

  • A modified deep semantic segmentation model was developed using the EfficientNet-B3 backbone integrated with the UNet architecture.
  • The model was trained on a histopathology dataset specifically for non-melanoma skin cancer segmentation.
  • The model was designed to segment images into 12 distinct classes.

Main Results:

  • The proposed model demonstrated superior performance compared to existing methods.
  • Average class accuracy increased from 79% to 83%.
  • Overall accuracy saw a significant improvement, rising from 85% to 94%.

Conclusions:

  • The modified EfficientNet-B3-UNet model offers a reliable and accurate solution for biomedical image segmentation.
  • This approach enhances the capabilities of computer-aided diagnosis systems for detecting abnormalities.
  • The improved accuracy and efficiency make it suitable for processing large-scale histopathology datasets.