Anatomy-Weighted CTDIvol from Routine CT Metadata: A Patient-Specific, Multi-Vendor Study Using Deep-Learning Segmentation

Abstract

Simple Summary CT scanners report a single dose number for the whole scan, yet the dose is delivered unevenly across organs. We built an open, freely available software pipeline that uses deep-learning segmentation to outline each abdominal organ on routine CT images and then derives a patient-specific, organ-level dose index directly from data the scanner already records. Across scans from four manufacturers, we found that this organ-level information can be recovered for some scanners but is entirely absent for others because the values it needs were not kept in the archived scan records. All software, results, and data provenance are fully open, so the work can be reproduced and extended.