Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 22, 2026BioengineeringOpen Access

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

View Full Paper
Ask AI
Bookmark
Share

Authors

SMShagufta ManzoorUniversity of WahJAJavaria AminRawalpindi Medical UniversityAZAmad ZafarSejong University

Discussion

Loading...

Member takes

Implication

Randomized trial evaluates image segmentation performance in breast cancer detection, suggesting improved accuracy.

Key Points

  • To develop a unified framework for accurate breast cancer image segmentation using multimodal imaging.
  • The framework integrates CNN and Transformer modules for feature extraction.
  • Incremental learning is applied via warm-start fine-tuning using previously trained weights.
  • Performance evaluated on four public datasets and one local dataset, with data augmentation techniques implemented.
  • Achieved Dice scores of 0.974 on ULCM, 0.975 on BUSI, 0.971 on BreastDM, 0.904 on TNBC nuclei segmentation, and 0.982 on BCSD-2024.
  • Outperformed classical U-Net models across all datasets.

Cite This Study

Manzoor et al. (2026) studied this question.

synapsesocial.com/papers/6a0ff3d9d674f7c03778cc4ehttps://doi.org/10.3390/bioengineering13050570
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Hybrid Loss-Driven Attention Residual U-Net with Multiscale Cascaded CBAM for Breast Cancer Segmentation2026 · 1 citations
  2. 2Dataset of breast ultrasound images2019 · 2,362 citations
  3. 3Advanced multimodal for Segmentation and Classification of breast cancer with DenseNet and Optimal Attention approach2025 · 3 citations
  4. 4Hybrid transformer‐based model for mammogram classification by integrating prior and current images2025 · 17 citations
  5. 5Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map2018 · 719 citations