Automated segmentation of head CT scans for computer-assisted craniomaxillofacial surgery applying a hierarchical patch-based stack of convolutional neural networks - Takeaways - MDSpire

Automated segmentation of head CT scans for computer-assisted craniomaxillofacial surgery applying a hierarchical patch-based stack of convolutional neural networks

  • By

  • David Steybe

  • Philipp Poxleitner

  • Marc Christian Metzger

  • Leonard Simon Brandenburg

  • Rainer Schmelzeisen

  • Fabian Bamberg

  • Phuong Hien Tran

  • Elias Kellner

  • Marco Reisert

  • Maximilian Frederik Russe

  • June 3, 2022

  • 0 min

Share

  • 1

    Automated segmentation enhances preoperative planning in craniomaxillofacial surgery by providing detailed 3D datasets for resection and reconstruction.

  • 2

    AI applications, particularly CNNs like U-Net, have revolutionized medical image segmentation, improving efficiency and accuracy in complex anatomical regions.

  • 3

    This study focused on a hierarchical patch-based stack of CNNs for segmenting various craniomaxillofacial structures, including bones and soft tissues.

  • 4

    The segmentation network utilized a multiscale approach with nested patches, optimizing spatial resolution and anatomical representation in CT images.

  • 5

    Eighteen craniomaxillofacial structures were segmented from high-resolution CT scans, facilitating improved surgical outcomes and intraoperative navigation.

Original Source(s)

Automated segmentation of head CT scans for computer-assisted craniomaxillofacial surgery applying a hierarchical patch-based stack of convolutional neural networks

  • by David Steybe, Philipp Poxleitner, Marc Christian Metzger, Leonard Simon Brandenburg, Rainer Schmelzeisen, Fabian Bamberg, Phuong Hien Tran, Elias Kellner, Marco Reisert, Maximilian Frederik Russe

  • June 3, 2022

Related Content

AI Scribes Lag Clinicians on Note Quality

A VHA study across 11 vendors finds AI-generated primary care notes score lower than clinician-written notes, with the largest deficits in thoroughness, organization, and usefulness

A shape completion model for corrective osteotomy of distal radius malunion

Deep learning-based segmentation of acute pulmonary embolism in cardiac CT images