A deep learning-based framework for patient-specific radiation dose prediction in beta-emitting radionuclide therapies.
Authors
Affiliations (5)
Affiliations (5)
- Department of Biomedical Engineering, The Catholic University of Korea, 222 Banpo-daero, Seocho-gu, Seoul, Republic of Korea (06591), Seoul, 06591, Korea (the Republic of).
- The Catholic University of Korea, 222 Banpo-daero, Seocho-gu, Seoul, Republic of Korea (06591), Seoul, 06591, Korea (the Republic of).
- The Catholic University of Korea College of Medicine, 222 Banpo-daero, Seocho-gu, Seoul, 06591, Korea (the Republic of).
- Department of Radiology, The Catholic University Seoul Saint Mary's Hospital, 222 Banpo-daero, Seocho-gu, Seoul, Republic of Korea (06591), Seoul, 06591, Korea (the Republic of).
- Department of Radiology, Seoul St. Mary's Hospital, 222 Banpo-daero, Seocho-gu, Seoul, Republic of Korea (06591), Seoul, 06591, Korea (the Republic of).
Abstract
Conventional image-based models for radionuclide therapy dosimetry are typically radionuclide-specific and rely on nuclear medicine (NM) images for training. We developed a deep learning (DL) model that predicts doses for not only training radionuclides but also radionuclides not included in the training data without patient NM images. The DL model was trained to predict voxel dose kernels (VDKs) for beta-emitters using CT-derived density maps and energy spectra. The DL model-derived VDKs were convolved with time-integrated activity to generate patient-specific dose maps. Zero-shot prediction was tested on Ho-166 and Lu-177. The performance of DL model was validated at kernel, phantom, and patient levels. The proposed DL model, conventional DL model trained on Y-90 NM/CT images of 22 patients, voxel S-value (VSV), and organ-level dosimetry (OLINDA/EXM) were benchmarked against Monte Carlo simulation (MC). Training utilized a single CT image, circumventing large patient cohort requirements. The DL model-based VDKs showed strong correlation with MC-based VDKs (R²: 0.99 and 0.91 for test Ho-166 and Lu-177) and, at the phantom level, achieved overall lower errors than VSV in heterogenous region. At the patient level, the proposed DL model predicted organ doses with the smallest differences from MC while reducing computation time from 4.6 hours to 2.6 minutes. For the test Lu-177, the proposed model exhibited good agreement with MC (2.1 Gy, 11.6%), while the conventional model trained using Y-90 showed large discrepancies (129.4 Gy, 657.4%). For the mean tumor dose averaged across the patient cohort for test Ho-166, the proposed DL model yielded the most accurate results with a difference of only 1.1 Gy (2.9%), outperforming multiple VSV (3.8 Gy, 7.2%), single VSV (3.8 Gy, 7.3%), and OLINDA/EXM (1.4 Gy, 4.5%). The proposed DL model enables dose prediction for radionuclides not included in the training data without NM images.