Post

New research · Radiology
NPJ digital medicine · 1d
AI / informaticsNPJ digital medicine · 2026

Whole body CT attenuation and volume charts from routine clinical scans via LLM report filtering.

Christian Wachinger, Bernhard Renger, Christopher Späth … Marcus Makowski
Read paper
RadiologyAI / informatics

Whole-body reference charts established for 106 anatomical structures using CT scans.

Whole body CT attenuation and volume charts from routine clinical scans via LLM report filtering.

Christian Wachinger et al. · NPJ digital medicine · 2026
Background

Interpreting quantitative CT biomarkers, such as organ volume and tissue attenuation, requires large-scale healthy reference distributions.

Methods

Longitudinal analyses reveal structure- and contrast-dependent changes distinct from cross-sectional trends.

n = over 350,000 CT examinations
106
Results
anatomical structures
whole-body reference charts were created for this many different body parts
n = over 350,000 CT examinations
More results

However, creating these is challenging because clinical datasets are often heavily enriched with pathology.

Here, we develop an evidence-grounded, cross-verified large language model (LLM) ensemble to filter pathological findings from radiology reports, enabling the construction of pathology-reduced cohorts from over 350,000 CT examinations.

“
Conclusion

These resources facilitate covariate-adjusted centile scoring from routine CT, supporting standardized quantitative phenotyping, multi-site imaging studies, and scalable opportunistic screening research.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Review
10-60 mGy
the range of radiation exposure to the baby from belly or pelvis CT scans
Cross-sectional
56.5%
More than half of computed tomography reports did not mention tumor deposits.
Cohort Study
6.7%
Among hereditary hemorrhagic telangiectasia patients re-imaged, 6.7% had clinically significant liver arteriovenous malformations.
Cohort Study
kappa = 0.819-0.838
adjudicated CT reports showed excellent agreement with the final diagnosis
AI / Informatics
0.87 million
the AI model learned from nearly a million image-report pairs
Guideline
“In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.”
Study
5.24 million
the number of brain scans used to train the new artificial intelligence model
AI / Informatics
OR = 6.15
Large language models were much more likely to answer easier questions correctly than harder ones