A synergistic framework integrating global context and structural features for breast ultrasound lesion detection - Takeaways - MDSpire

A synergistic framework integrating global context and structural features for breast ultrasound lesion detection

  • By

  • Xiangqiong Wu

  • Yujie Tang

  • Yaxuan Zhou

  • Peng Wang

  • June 26, 2026

  • 0 min

Share

  • 1

    Accurate breast lesion detection in ultrasound images is hindered by factors such as speckle noise and low contrast.

  • 2

    A lightweight context-structure synergistic framework based on YOLOv13 was proposed to improve breast lesion detection.

  • 3

    The Dual-Stream Mamba Aggregation and Structure-aware Axial Attention modules enhance contextual and structural feature representation.

  • 4

    The proposed method achieved competitive detection performance with 2.50M parameters and 161.29 FPS on the BUV and WH-BUS datasets.

  • 5

    The framework integrates contextual and structural modeling to address challenges in breast ultrasound image analysis.

Original Source(s)

A synergistic framework integrating global context and structural features for breast ultrasound lesion detection

  • by Xiangqiong Wu, Yujie Tang, Yaxuan Zhou, Peng Wang

  • June 26, 2026

Related Content

Joseph Fraumeni Jr., pioneering cancer genetics researcher, devoted his life to families like mine

Integrative oncology in colorectal cancer: evidence-based strategies from prevention through survivorship

A spatiotemporal state-inference framework for adaptive immunotherapy in glioblastoma