Improving CT-CBCT deformable image registration for cervical cancer adaptive radiotherapy using a deep learning approach - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Enhancing Deformable Image Registration of CT-CBCT for Cervical Cancer Adaptive Radiotherapy Through a Deep Learning Framework

  • By

  • Chengjian Xiao

  • Chunlan Huang

  • Weixiang Lin

  • Feilong Tian

  • Youxing Zeng

  • July 6, 2026

Share

  • 1

    A deep learning framework was developed to enhance CT-CBCT deformable image registration for cervical cancer adaptive radiotherapy.

  • 2

    The framework integrates convolutional and transformer modules to capture multi-scale anatomical features effectively.

  • 3

    The proposed method achieved high Dice scores and improved deformation regularity on both internal and external datasets.

  • 4

    Boundary alignment improvements were particularly notable in high-contrast regions, enhancing registration robustness.

  • 5

    The method demonstrated better generalization and accuracy in boundary-sensitive metrics, addressing intensity inconsistencies.

Original Source(s)

Improving CT-CBCT deformable image registration for cervical cancer adaptive radiotherapy using a deep learning approach

  • by Chengjian Xiao, Chunlan Huang, Weixiang Lin, Feilong Tian, Youxing Zeng

  • July 6, 2026

Related Content

Editorial: Multi-omics interrogation of tumor-associated macrophages: paving the way for next-generation cancer immunotherapies

Prognostic superiority of volumetric PET parameters (MTV and TLG) over SUV in advanced non-small-cell lung cancer: a systematic review and meta-analysis of univariate and multivariate evidence

Innovative pathological and therapeutic approaches for poorly cohesive gastric cancer