Voxel-Based Internal Dosimetry for 177Lu-Labeled Radiopharmaceutical Therapy Using Deep Residual Learning

Keon Min Kim; Min Sun Lee; Min Seok Suh; Gi Jeong Cheon; Jae Sung Lee

doi:10.1007/s13139-022-00769-z

Voxel-Based Internal Dosimetry for ¹⁷⁷Lu-Labeled Radiopharmaceutical Therapy Using Deep Residual Learning

Nucl Med Mol Imaging. 2023 Apr;57(2):94-102. doi: 10.1007/s13139-022-00769-z. Epub 2022 Sep 1.

Authors

Keon Min Kim^{1

2

3}, Min Sun Lee⁴, Min Seok Suh^{5

6}, Gi Jeong Cheon^{5

6}, Jae Sung Lee^{1

2

3

5

6}

Affiliations

¹ Interdisciplinary Program in Bioengineering, Seoul National University Graduate School, Seoul, 03080 South Korea.
² Integrated Major in Innovative Medical Science, Seoul National University Graduate School, Seoul, 03080 South Korea.
³ Artificial Intelligence Institute, Seoul National University, Seoul, 08826 South Korea.
⁴ Environmental Radioactivity Assessment Team, Nuclear Emergency & Environmental Protection Division, Korea Atomic Energy Research Institute, Daejeon, 34057 Korea.
⁵ Department of Nuclear Medicine, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03080 South Korea.
⁶ Institute of Radiation Medicine, Medical Research Center, Seoul National University, Seoul, 03080 South Korea.

Abstract

Purpose: In this study, we propose a deep learning (DL)-based voxel-based dosimetry method in which dose maps acquired using the multiple voxel S-value (VSV) approach were used for residual learning.

Methods: Twenty-two SPECT/CT datasets from seven patients who underwent ¹⁷⁷Lu-DOTATATE treatment were used in this study. The dose maps generated from Monte Carlo (MC) simulations were used as the reference approach and target images for network training. The multiple VSV approach was used for residual learning and compared with dose maps generated from deep learning. The conventional 3D U-Net network was modified for residual learning. The absorbed doses in the organs were calculated as the mass-weighted average of the volume of interest (VOI).

Results: The DL approach provided a slightly more accurate estimation than the multiple-VSV approach, but the results were not statistically significant. The single-VSV approach yielded a relatively inaccurate estimation. No significant difference was noted between the multiple VSV and DL approach on the dose maps. However, this difference was prominent in the error maps. The multiple VSV and DL approach showed a similar correlation. In contrast, the multiple VSV approach underestimated doses in the low-dose range, but it accounted for the underestimation when the DL approach was applied.

Conclusion: Dose estimation using the deep learning-based approach was approximately equal to that in the MC simulation. Accordingly, the proposed deep learning network is useful for accurate and fast dosimetry after radiation therapy using ¹⁷⁷Lu-labeled radiopharmaceuticals.

Keywords: 3D U-net; Deep learning; Dose kernel; Monte Carlo simulation; Radiation dosimetry; Radionuclide therapy.

© The Author(s), under exclusive licence to Korean Society of Nuclear Medicine 2022, Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.