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

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

  • By

  • Ehsan Amini

  • Georg Hille

  • Janine Hürtgen

  • Alexey Surov

  • Sylvia Saalfeld

  • September 25, 2025

  • 0 min

Share

  • 1

    Acute pulmonary embolism (APE) is a critical cardiovascular condition with mortality rates up to 30%, necessitating prompt diagnosis and treatment.

  • 2

    Computer tomographic pulmonary angiography (CTPA) is the gold standard for APE diagnosis, providing essential parameters for risk stratification.

  • 3

    Deep learning techniques, particularly semantic segmentation, are being explored to enhance the accuracy and efficiency of APE detection in CTPA images.

  • 4

    This study evaluates two advanced neural network architectures, nnU-Net and VT-UNet, for effective segmentation of APE in 3D CTPA images.

  • 5

    Manual segmentation of APE is labor-intensive, but deep learning approaches can significantly reduce the time required for accurate annotations.

Original Source(s)

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

  • by Ehsan Amini, Georg Hille, Janine Hürtgen, Alexey Surov, Sylvia Saalfeld

  • September 25, 2025

Related Content

Experiences in Clinical Implementation of Online Adaptive Radiotherapy for Prostate Cancer: Enhancing Treatment Efficiency

Evaluation of Six-Degree-of-Freedom Registration Errors in Various Anatomical Regions During Head and Neck Radiotherapy Using Uniform CBCT Conditions

Optimal Use of Computed Tomography in Diagnosing Internal Herniation After Roux-en-Y Gastric Bypass: A Proposition for the Application of a Radiological Prediction Score