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: May 28, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Sequential Transfer Learning for Multi-Domain Breast Image Segmentation Using a Transformer-Enhanced Hybrid U-Net.

Shagufta Manzoor1, Javaria Amin2, Amad Zafar3

  • 1Department of Computer Science, University of Wah, Wah Cantt 47040, Pakistan.

Bioengineering (Basel, Switzerland)
|May 27, 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

Deep Q-Learning for Gastrointestinal Disease Detection and Classification.

Bioengineering (Basel, Switzerland)·2025
Same author

MRI-Driven Alzheimer's Disease Diagnosis Using Deep Network Fusion and Optimal Selection of Feature.

Bioengineering (Basel, Switzerland)·2024
Same author

Enhancing Oral Squamous Cell Carcinoma Detection Using Histopathological Images: A Deep Feature Fusion and Improved Haris Hawks Optimization-Based Framework.

Bioengineering (Basel, Switzerland)·2024
Same author

Enhancing Skin Lesion Detection: A Multistage Multiclass Convolutional Neural Network-Based Framework.

Bioengineering (Basel, Switzerland)·2023
Same author

An Isolated CNN Architecture for Classification of Finger-Tapping Tasks Using Initial Dip Images: A Functional Near-Infrared Spectroscopy Study.

Bioengineering (Basel, Switzerland)·2023
Same author

BU-DLNet: Breast Ultrasonography-Based Cancer Detection Using Deep-Learning Network Selection and Feature Optimization.

Bioengineering (Basel, Switzerland)·2023

This study introduces an advanced deep learning framework for accurate breast cancer detection using multimodal imaging. The novel CNN-Transformer model significantly improves segmentation accuracy across diverse datasets, outperforming traditional methods.

Area of Science:

  • Medical Imaging and Artificial Intelligence
  • Computational Pathology
  • Oncology

Background:

  • Breast cancer remains a leading cause of mortality in women globally, necessitating improved detection systems.
  • Accurate segmentation of breast cancer in multimodal imaging is crucial for effective diagnosis and treatment planning.

Purpose of the Study:

  • To present a unified deep learning framework for breast cancer segmentation utilizing multimodal imaging (histopathology, MRI, mammogram, ultrasound).
  • To integrate Convolutional Neural Networks (CNNs) with Transformer modules for enhanced feature extraction and contextual understanding.
  • To evaluate the framework's performance across multiple public and local datasets.

Main Methods:

  • Developed an encoder-decoder architecture with Residual Blocks for feature extraction, progressively downsampling spatial dimensions.
Keywords:
diceimagingincremental learningresidualsegmentation

Related Experiment Videos

Last Updated: May 28, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

  • Incorporated a Transformer encoder in the bottleneck to capture long-range dependencies using multi-head self-attention.
  • Employed advanced training strategies including Dice and binary cross-entropy loss, gradient clipping, learning rate scheduling (ReduceLROnPlateau), early stopping, data augmentation, and incremental learning (warm-start fine-tuning).

    • Main Results:

    • Achieved high Dice scores across diverse datasets: 0.974 (BUS-UCLM), 0.975 (BUSI), 0.971 (BreastDM), 0.904 (TNBC NucleiSegmentation), and 0.982 (BCSD-2024).
    • The proposed CNN-Transformer framework demonstrated superior performance compared to classical U-Net models.
    • The model exhibited robustness and generalization capabilities due to applied data augmentation and incremental learning techniques.

    Conclusions:

    • The unified CNN-Transformer framework offers a powerful and accurate solution for multimodal breast cancer segmentation.
    • The integration of Transformer modules effectively enhances the model's ability to understand global and local contextual information.
    • This approach holds significant potential for improving the accuracy and reliability of computer-aided breast cancer detection systems.