Diagnostic accuracy of deep learning vs. human raters for detecting osteoporotic vertebral compression fractures in routine CT scans - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Comparative Diagnostic Performance of Deep Learning Algorithms and Human Evaluators in Identifying Osteoporotic Vertebral Compression Fractures on Routine CT Imaging

  • By

  • Evamaria O. Riedel

  • David Schinz

  • Matthias Keicher

  • Sebastian Rühling

  • Malek El Husseini

  • Chantal Pellegrini

  • Thomas Baum

  • Michael Dieckmeyer

  • Luca Malagutti

  • Isabel Seeger

  • Anna S. Walburga

  • Benedikt Wiestler

  • Nico Sollmann

  • Maximilian T. Löffler

  • Arthur Wagner

  • Jan S. Kirschke

  • February 24, 2026

Share

  • 1

    Osteoporotic vertebral compression fractures significantly impact public health, especially among the elderly, due to increased morbidity and healthcare costs.

  • 2

    Deep learning algorithms can enhance the accuracy and efficiency of diagnosing osteoporotic fractures from CT images compared to human evaluators.

  • 3

    The study evaluated four deep learning models and eight human raters using data from 3548 vertebrae across 331 patients.

  • 4

    Fracture detection was assessed at patient and vertebral levels, focusing on clinically relevant moderate or severe fractures.

  • 5

    The datasets used for training and evaluation were collected from routine clinical CT examinations, ensuring a diverse representation of spinal morphology.

Original Source(s)

Diagnostic accuracy of deep learning vs. human raters for detecting osteoporotic vertebral compression fractures in routine CT scans

  • by Evamaria O. Riedel, David Schinz, Matthias Keicher, Sebastian Rühling, Malek El Husseini, Chantal Pellegrini, Thomas Baum, Michael Dieckmeyer, Luca Malagutti, Isabel Seeger, Anna S. Walburga, Benedikt Wiestler, Nico Sollmann, Maximilian T. Löffler, Arthur Wagner, Jan S. Kirschke

  • February 24, 2026

Related Content

AI may estimate chest fluid with similar efficacy to radiologists

A general-purpose AI model performed comparably to experienced readers, but substantial errors highlighted the limits of chest radiography for quantifying pleural fluid.

Abdominal symmetry index after reconstruction of traumatic lumbar hernia with dual polypropylene mesh: a comparative CT-based study

Evidence-Based Imaging Pathway for Atrial Fibrillation Ablation