Whole-body CT attenuation and volume charts from routine clinical scans via evidence-grounded LLM report filtering

TL;DR

This study develops an LLM-based filtering system to create healthy reference distributions from large clinical CT datasets, enabling standardized quantitative analysis of organ volumes and tissue attenuation.

Contribution

It introduces an ensemble of LLMs for pathology filtering and constructs comprehensive, covariate-adjusted reference charts for 106 anatomical structures from routine CT scans.

Findings

Successfully filtered pathological findings from over 350,000 CT exams.

Established reference charts accounting for age, sex, contrast, and acquisition parameters.

Revealed structure- and contrast-dependent longitudinal changes.

Abstract

Interpreting quantitative CT biomarkers, such as organ volume and tissue attenuation, requires large-scale healthy reference distributions. 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. Five LLMs, first, flag structure-level abnormality candidates grounded in verbatim report evidence and, second, resolve disagreements via cross-verification. Using distribution-aware generalized additive models for location, scale, and shape, we establish comprehensive whole-body reference charts for 106 anatomical structures (volumes and attenuation) across adulthood, accounting for age, sex, contrast enhancement, and acquisition parameters. Longitudinal analyses reveal structure- and contrast-dependent changes distinct from cross-sectional trends. These resources facilitate covariate-adjusted centile scoring from routine CT, supporting standardized quantitative phenotyping, multi-site imaging studies, and scalable opportunistic screening research.