PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 27, 2026Biomedical Data Science0 citationsOpen Access

Lightweight U-Net for Semantic Segmentation of Breast Tumors in Ultrasound Images

Semantic Segmentation of Malignant Tumors in Breast Ultrasound Images Based on Lightweight U-Net

View Full Paper

Authors

LYLi Yusen

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved segmentation accuracy in ultrasound images, suggesting a practical approach for real-time diagnosis of breast tumors.

Key Points

  • To improve semantic segmentation of malignant tumors in breast ultrasound images using a lightweight U-Net model.
  • Proposed a lightweight U-Net-based semantic segmentation algorithm with multi-scale supervision.
  • Implemented channel attention mechanisms for enhanced tumor feature extraction.
  • Performed structured pruning and quantized attention training to reduce model size and improve speed.
  • Achieved Dice coefficient of 0.818 for segmentation accuracy.
  • Reduced parameter size by approximately 76.8%.
  • Improved inference speed by about 77.7%.
Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Li Yusen (2026) studied this question.

synapsesocial.com/papers/6a168b280c924ddd1bd5a17dhttps://doi.org/10.47297/wspbdswsp2752-630526.20260601
Ask AI
Helpful
Bookmark
Share
View Full Paper