Scout-Dose-TCM: direct and prospective scout-based estimation of personalized organ and effective doses from tube current modulated CT exams.
Authors
Affiliations (8)
Affiliations (8)
- Department of Radiology, Stanford University, 1201 Welch Road, Stanford, 94305-6104, UNITED STATES.
- Radiology, Stanford University School of Medicine, 1201 Welch Road, Stanford, California, 94305, UNITED STATES.
- Radiology, Stanford University School of Medicine, 1201 Welch Rd, Stanford, California, 94305, UNITED STATES.
- University of Kentucky, 101 Main Building, Lexington, 40506, UNITED STATES.
- University of Pennsylvania Perelman School of Medicine, 3400 Civic Center Blvd, Philadelphia, Pennsylvania, 19104-4306, UNITED STATES.
- GE Healthcare, 3000 N. Grandview Boulevard, Cedarburg, Wisconsin, 53012, UNITED STATES.
- Radiology, Stanford University, 300 Pasteur Dr, Stanford, California, 94305-6104, UNITED STATES.
- Radiology, Stanford University School of Medicine, 1201 Welch Rd, P270, Stanford, California, 94305, UNITED STATES.
Abstract
This study proposes Scout-Dose-TCM for direct, prospective estimation of organ-level and effective doses under tube current modulation (TCM) and compares its performance with two established methods.

Approach: Contrast-enhanced chest-abdomen-pelvis CT exams from 130 adults (120 kVp, TCM) were analyzed. Reference organ doses for six organs (lungs, kidneys, liver, pancreas, bladder, spleen) were calculated using MC-GPU and TotalSegmentator. These data trained Scout-Dose-TCM, a deep-learning model that predicts organ-level doses corresponding to discrete cosine transform (DCT) basis functions, enabling real-time estimation for any TCM profile. The model includes a feature-learning module that extracts information from lateral and frontal scouts and scan range, and a dose-learning module that outputs DCT-based dose estimates. The loss function incorporated the DCT formulation to ensure accurate predictions across variable TCM patterns. For comparison, dose estimation was performed following AAPM Task Group 204 (Global CTDI<sub>vol</sub>) and its TCM-adapted, organ-specific version (Organ CTDI<sub>vol</sub>). The three methods were extended to estimate effective dose and compared against AAPM Report 96, which applies a fixed dose-length product-to-effective-dose conversion factor. Five-fold cross-validation assessed generalizability via mean absolute percentage dose errors and R² correlations with Monte Carlo benchmarks.

Main Results: Mean organ-level absolute percentage errors were 13% (Global CTDI<sub>vol</sub>), 9% (Organ CTDI<sub>vol</sub>), and 7% (Scout-Dose-TCM). The largest discrepancies occurred for the bladder (15%, 13%, and 9%). Scout-Dose-TCM significantly reduced organ-level dose errors versus Global CTDI<sub>vol</sub>(p < 1×10-7) and improved predictions for liver, bladder, and pancreas versus Organ CTDI<sub>vol</sub>(p ≤ 0.005). It also achieved higher R² values and lower effective-dose error (3.01%) than Global (3.87%) and Organ (4.16%) CTDI<sub>vol</sub>, and the AAPM Task Group 96 method (31%).

Significance: Scout-Dose-TCM outperformed Global CTDI<sub>vol</sub>and was comparable to or better than Organ CTDI<sub>vol</sub>for organ and effective dose estimation without requiring segmentations at inference, demonstrating its clinical potential for prospective dose estimation in CT.