Performance-aware programming for intraoperative intensity-based image registration on graphics processing units - Takeaways - MDSpire

Performance-aware programming for intraoperative intensity-based image registration on graphics processing units

  • By

  • Martin C. W. Leong

  • Kit-Hang Lee

  • Bowen P. Y. Kwan

  • Yui-Lun Ng

  • Zhiyu Liu

  • Nassir Navab

  • Wayne Luk

  • Ka-Wai Kwok

  • January 23, 2021

  • 0 min

Share

  • 1

    Image registration is essential for aligning medical images, particularly in non-rigid scenarios affected by distortions and deformations.

  • 2

    Intraoperative registration enhances surgical workflows by integrating preoperative images with real-time data, crucial for procedures like cardiac electrophysiology.

  • 3

    Intensity-based registration methods, such as the Demons algorithm, are robust but often slower than geometry-based methods due to intensive computations.

  • 4

    Graphics processing units (GPUs) offer high-throughput computation capabilities, making them suitable for accelerating intensity-based registration algorithms.

  • 5

    The proposed GPU-based optimization framework aims to reduce runtime for non-rigid registration, enhancing performance through performance-aware programming techniques.

Original Source(s)

Performance-aware programming for intraoperative intensity-based image registration on graphics processing units

  • by Martin C. W. Leong, Kit-Hang Lee, Bowen P. Y. Kwan, Yui-Lun Ng, Zhiyu Liu, Nassir Navab, Wayne Luk, Ka-Wai Kwok

  • January 23, 2021

Related Content

Postoperative Step Counts Tied to Surgical Recovery

Wearable-measured mobility—but not heart rate variability or wellness scores—was associated with length of stay, complications, and readmissions

Why Hip Fracture Surgery Timing Matters

Researchers examined how variation in time to hip fracture surgery relates to mortality, complications, length of stay, and functional recovery in older adults.

AI Scribes: Efficiency for Whom?

Unresolved safety, privacy, and regulatory concerns may limit benefits of AI scribes for physicians and patients.