Uncertainty estimation for trust attribution to speed-of-sound reconstruction with variational networks - Takeaways - MDSpire

Uncertainty estimation for trust attribution to speed-of-sound reconstruction with variational networks

  • By

  • Sonia Laguna

  • Lin Zhang

  • Can Deniz Bezek

  • Monika Farkas

  • Dieter Schweizer

  • Rahel A. Kubik-Huch

  • Orcun Goksel

  • June 10, 2025

  • 0 min

Share

  • 1

    Breast cancer detection requires efficient techniques due to the limitations of current diagnostic methods like mammography and MRI.

  • 2

    Speed-of-sound (SoS) imaging offers a non-ionizing, real-time alternative for differentiating malignant and benign breast lesions.

  • 3

    This study introduces uncertainty estimation in SoS imaging to enhance trust in acquisition frame selection and reconstruction accuracy.

  • 4

    The proposed method applies a novel normalized uncertainty metric for improved trust attribution in regression tasks related to SoS.

  • 5

    The framework demonstrates clinical feasibility for breast cancer diagnosis, marking the first in vivo application of variational networks for SoS reconstruction.

Original Source(s)

Uncertainty estimation for trust attribution to speed-of-sound reconstruction with variational networks

  • by Sonia Laguna, Lin Zhang, Can Deniz Bezek, Monika Farkas, Dieter Schweizer, Rahel A. Kubik-Huch, Orcun Goksel

  • June 10, 2025

Related Content

UroFusion-X: a unified multimodal deep learning framework for robust diagnosis, subtyping, and prognosis of urological cancers

Assessment of the effectiveness of a polypropylene onlay mesh in the prevention of laparoscopic trocar-site incisional hernia in high-risk patients. A randomized clinical trial

Three-dimensional image guidance for diagnosis and treatment of adrenal disease: a systematic review