Differentiation of benign and malignant vertebral fractures using a convolutional neural network to extract CT-based texture features

Purpose To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs). Methods A total of 409 patients who underwent routine thor...

Full description

Saved in:
Bibliographic Details
Published in:European spine journal 2023-12, Vol.32 (12), p.4314-4320
Main Authors: Goller, Sophia S., Foreman, Sarah C., Rischewski, Jon F., Weißinger, Jürgen, Dietrich, Anna-Sophia, Schinz, David, Stahl, Robert, Luitjens, Johanna, Siller, Sebastian, Schmidt, Vanessa F., Erber, Bernd, Ricke, Jens, Liebig, Thomas, Kirschke, Jan S., Dieckmeyer, Michael, Gersing, Alexandra S.
Format: Article
Language:English
Subjects:
Benign
Biopsy
Computed tomography
Humans
Labeling
Medicine
Medicine & Public Health
Neural networks
Neural Networks, Computer
Neurosurgery
Original Article
Osteoporosis
Osteoporotic Fractures - diagnosis
Regression analysis
Skewness
Spinal Fractures - diagnosis
Spine
Spine - pathology
Surgical Orthopedics
Tomography, X-Ray Computed - methods
Vertebrae
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs). Methods A total of 409 patients who underwent routine thoracolumbar spine CT at two institutions were included. VFs were categorized as benign or malignant using either biopsy or imaging follow-up of at least three months as standard of reference. Automated detection, labelling, and segmentation of the vertebrae were performed using a CNN-based framework ( https://anduin.bonescreen.de ). Eight TFs were extracted: Variance global , Skewness global , energy, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP). Multivariate regression models adjusted for age and sex were used to compare TFs between benign and malignant VFs. Results Skewness global showed a significant difference between the two groups when analyzing fractured vertebrae from T1 to L6 (benign fracture group: 0.70 [0.64–0.76]; malignant fracture group: 0.59 [0.56–0.63]; and p  = 0.017), suggesting a higher skewness in benign VFs compared to malignant VFs. Conclusion Three-dimensional CT-based global TF skewness assessed using a CNN-based framework showed significant difference between benign and malignant thoracolumbar VFs and may therefore contribute to the clinical diagnostic work-up of patients with VFs.
ISSN:0940-6719
1432-0932
DOI:10.1007/s00586-023-07838-7