Real Super-Resolution for Proximal Femur: Enhanced Computation of Structural Bone Metrics from Clinical CTs

Download PDF
Open Webpage

Niklas Koser, Marten J. Finck, Felix N. von Brackel, Benjamin Ondruschka, Sören Pirk, Claus C. Glüer

Published: 2025, Last Modified: 29 Nov 2025MICCAI (3) 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Fracture risk due to osteoporosis is a highly prevalent disease with costs in the European Union alone of 56 billion p.a. Accurate assessment of the microarchitecture of the proximal femur (e.g., trabecular thickness, trabecular spacing, bone volume fraction) is essential for assessing bone strength and predicting fracture risk. High resolution (HR) CT provides the necessary spatial resolution. However, for best hip fracture risk assessment HR-CT imaging should be performed at the proximal femur but this would require an unacceptably high level of radiation dose. Therefore, we aimed to investigate whether deep learning based super-resolution (SR) models applied to low-resolution (LR) clinical CT images permit improved assessment of structural parameters.