A deep learning-based framework for patient-specific radiation dose prediction in beta-emitting radionuclide therapies

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: R² correlation of 0.99 for Ho-166 and 0.91 for Lu-177 in zero-shot prediction

• Primary Outcome: Voxel dose kernel prediction accuracy compared to Monte Carlo simulation

• Nnt Or Sensitivity: Computation time reduction from 4.6 hours to 2.6 minutes (98.9% reduction)

• Confidence Interval: Not reported

Clinical Application

High feasibility using standard CT imaging without additional nuclear medicine scans Highly relevant to Australian nuclear medicine practice; could enhance PBS-funded radionuclide therapies by improving dosimetry accuracy and efficiency Patients receiving beta-emitting radionuclide therapy (Y-90, Ho-166, Lu-177) in nuclear medicine departments

Abstract

Objective.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.Approach.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, voxelS-value (VSV), and organ-level dosimetry (OLINDA/EXM) were benchmarked against Monte Carlo simulation (MC).Main results.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 heterogeneous 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 h to 2.6 min. 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%).Significance.The proposed DL model enables dose prediction for radionuclides not included in the training data without NM images.

References

1. 1.Ha, S., Kang, H., Kang, D. S., Jang, J., Oh, J. S., & Sung, W. (2026). A deep learning-based framework for patient-specific radiation dose prediction in beta-emitting radionuclide therapies. Physics in Medicine and Biology. https://doi.org/10.1088/1361-6560/ae5375