Automated Measurement of Effective Radiation Dose by 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography
2024

Automated Measurement of Radiation Dose in PET/CT Scans

Sample size: 72 publication 10 minutes Evidence: high

Author Information

Author(s): Eom Yujin, Park Yong-Jin, Lee Sumin, Lee Su-Jin, An Young-Sil, Park Bok-Nam, Yoon Joon-Kee

Primary Institution: Ajou University

Hypothesis

Can a deep learning-based automated program standardize the measurement of radiation doses in 18F-FDG PET/CT examinations?

Conclusion

The automated program for calculating the effective dose of torso 18F-FDG PET/CT was developed successfully and showed strong correlation with manual calculations.

Supporting Evidence

  • The automated program showed excellent repeatability and reproducibility.
  • CT ED calculated by the automated program was not significantly different from that calculated by a physician.
  • The PET ED was significantly lower in the newer scanner compared to the older scanner.
  • The total ED was significantly lower with the newer scanner than with the older scanner.

Takeaway

Researchers created a computer program that can quickly and accurately measure radiation doses from PET/CT scans, making it easier for doctors to understand how much radiation patients receive.

Methodology

The study used deep learning to segment CT images and calculate effective doses, comparing results from an automated program with those from a nuclear medicine physician.

Potential Biases

Potential inaccuracies in dose calculations due to incorrect anatomical segmentation when arms are raised during scans.

Limitations

The study was conducted at a single center, and measurement failures occurred due to missing dose report forms and DICOM header information.

Participant Demographics

Group 1: 30 patients (12 male, 18 female, average age 60); Group 2: 42 patients (24 male, 18 female, average age 60).

Statistical Information

P-Value

0.7623

Confidence Interval

95%

Statistical Significance

p<0.0001

Digital Object Identifier (DOI)

10.3390/tomography10120151

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication