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

• Published in: Nuclear medicine and molecular imaging Vol. 57; no. 2; pp. 94 - 102
• Main Authors: Kim, Keon Min, Lee, Min Sun, Suh, Min Seok, Cheon, Gi Jeong, Lee, Jae Sung
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.04.2023; Springer Nature B.V
• Subjects: Cardiology; Deep learning; Dosimeters; Dosimetry; Imaging; Lutetium isotopes; Medicine; Medicine & Public Health; Nuclear Medicine; Oncology; Original; Original Article; Orthopedics; Radiation therapy; Radiochemistry; Radiology; Deep learning; Radionuclide therapy; Radiation dosimetry; 3D U-net; Dose kernel; Monte Carlo simulation
• ISSN: 1869-3474; 1869-3482
• DOI: 10.1007/s13139-022-00769-z

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 177 Lu-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 177 Lu-labeled radiopharmaceuticals.