Response to letter to the editor regarding: ‘osteoporosis screening and major osteoporotic fracture prediction by cranial computed tomography-derived Hounsfield units: a multi-centre study on opportunistic osteoporosis screening’
Robert Wakolbinger-Habel, Daniel Arian Kraus
Abstract
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBone health and osteoporosis research · Bone Metabolism and Diseases · Vitamin K Research Studies
Dear Editor
We are delighted to receive a forward-looking comment on our study.
We concur with Song et al. [1] that further research for implementation of opportunistic osteoporosis screening by CCT-derived HU into clinical practice focusing on various age groups as well as validation of standardized protocols for different CT scanners is of crucial importance.
A promising application for minimizing clinical workload and inter-rater variability for region of interest placement is the use of artificial intelligence (AI). Especially as the impression of utilization of AI in the context of opportunistic osteoporosis screening to decrease the treatment gap of fragility fractures is rising.
In this context, we already published preliminary results indicating the potential of AI in vertebral fracture detection. We reported a sensitivity of 89.5% and specificity of 98.0% for identification of higher-grade vertebral fractures (Genant 2/3) in CT studies of the chest and abdomen by the prototype of a deep learning AI [2].
Opportunistic osteoporosis screening by CCT derived HU may have a unique selling point as especially elderly patients receive this radiological examination in clinical routing (e.g. to rule out intracranial bleeding). Furthermore, the frontal bone might not be so prone to degenerative changes compared to vertebrae-based HU measurements.
By CCT-based opportunistic osteoporosis screening, a major contribution to prevention of osteoporotic fractures as well as the reduction of treatment gap in patients with sustained fragility fractures could be achieved. Incorporation of AI to standardize and automatize workflows may increase usability in clinical practice. This could also affect public health by potentially decreasing osteoporosis-associated costs, morbidity, mortality and increasing quality of life. However, the integration of AI based approaches into clinical practice still requires future validation studies.
The reference list from the paper itself. Each links out to its DOI / PubMed record.
- 1Song H, Shi L, Zhu J. Letter to the editor regarding: ‘osteoporosis screening and major osteoporotic fracture prediction by cranial computed tomography-derived hounsfield units: a multi-centre study on opportunistic osteoporosis screening. Ann Med. 2025;57(1):2566874. doi:10.1080/07853890.2025.2566874.41017359 PMC 12481525 · doi ↗ · pubmed ↗
- 2Kraus DA, Zandieh S, Haschka J, et al. Opportunistic Vertebral Fracture Detection from Computed Tomography Studies by Artificial Intelligence - preliminary results. J Bone Miner Res. 2023;38:344–344.