Application of machine learning to pretherapeutically estimate dosimetry in men with advanced prostate cancer treated with 177Lu-PSMA I&T therapy

Abstract

Purpose Although treatment planning and individualized dose application for emerging prostate-specific membrane antigen (PSMA)-targeted radioligand therapy (RLT) are generally recommended, it is still difficult to implement in practice at the moment. In this study, we aimed to prove the concept of pretherapeutic prediction of dosimetry based on imaging and laboratory measurements before the RLT treatment. Methods Twenty-three patients with metastatic castration-resistant prostate cancer (mCRPC) treated with 177Lu-PSMA I&T RLT were included retrospectively. They had available pre-therapy 68 Ga-PSMA-HEBD-CC PET/CT and at least 3 planar and 1 SPECT/CT imaging for dosimetry. Overall, 43 cycles of 177Lu-PSMA I&T RLT were applied. Organ-based standard uptake values (SUVs) were obtained from pre-therapy PET/CT scans. Patient dosimetry was calculated for the kidney, liver, spleen, and salivary glands using Hermes Hybrid Dosimetry 4.0 from the planar and SPECT/CT images. Machine learning methods were explored for dose prediction from organ SUVs and laboratory measurements. The uncertainty of these dose predictions was compared with the population-based dosimetry estimates. Mean absolute percentage error (MAPE) was used to assess the prediction uncertainty of estimated dosimetry. Results An optimal machine learning method achieved a dosimetry prediction MAPE of 15.8 ± 13.2% for the kidney, 29.6% ± 13.7% for the liver, 23.8% ± 13.1% for the salivary glands, and 32.1 ± 31.4% for the spleen. In contrast, the prediction based on literature population mean has significantly larger MAPE (p < 0.01), 25.5 ± 17.3% for the kidney, 139.1% ± 111.5% for the liver, 67.0 ± 58.3% for the salivary glands, and 54.1 ± 215.3% for the spleen. Conclusion The preliminary results confirmed the feasibility of pretherapeutic estimation of treatment dosimetry and its added value to empirical population-based estimation. The exploration of dose prediction may support the implementation of treatment planning for RLT.

Pre-therapy PET-based voxel-wise dosimetry prediction by characterizing intra-organ heterogeneity in PSMA-directed radiopharmaceutical theranostics

“…To compare our predictions with 3D RPT DoseGAN to the organ-dose guided method, we manually segmented the OAR, and calculated the NRMSE and SSIM within OAR. Additionally, we measured the deviation of the mean absorbed organ dose using the mean absolute with ML-based methods [11]. This approach was developed using SUV features from PET imaging as input, with the corresponding dosimetry of the targeted organ as the ground truth.…”

“…For example, individualized PBPK model parameters can be derived by pre-therapy PET/CT activity concentrations, planar scintigraphy, and tumor volumes, allowing for the individualization of [ 177 Lu]Lu-PSMA-I&T therapy [10]. Artificial intelligence (AI) in medicine has burgeoned over the past decade, with machine learning (ML) particularly holding promise for pre-therapy prediction of dosimetry [11]. Nonetheless, both PBPK-based predictions and our previously developed ML approach are limited to organ-level estimations and do not account for intra-organ heterogeneity, which is crucial for assessing organ toxicity during treatment planning.…”

On the Use of Artificial Intelligence for Dosimetry of Radiopharmaceutical Therapies

“…Furthermore, approaches for AI-based pretherapeutic dosimetry have been investigated, which pave the way for patientspecific treatment planning from the very start. In this regard, Xue et al [68] applied a promising approach that uses standardized uptake value data based on PSMA PET/CT and clinical parameters in combination with different supervised learning methods for pre-therapeutic organ dosimetry for [ 177 Lu]Lu-PSMA-I&T treatment. This approach outperformed dosimetry prediction based on literature population mean with a significantly lower mean absolute percentage error of 15.8 ± 13.2 % versus 25.…”

PBPK-Adapted Deep Learning for Pretherapy Prediction of Voxelwise Dosimetry: In-Silico Proof of Concept

“…On the other side, machine learning has been successfully applied for pre-therapy prediction of dosimetry [25], [26]. Despite the similar restriction in organ-wise prediction, the potential of artificial intelligence (AI) has been demonstrated in dosimetry prediction.…”

“…Deep learning as sub-field of AI, can effectively approximate complex, multidimensional, nonlinear functions in both spatial and temporal domains [27]. Therefore, integrating deep learning into RPT has the potential to offer complementary insights into dose prediction and optimization [25], [26]. However, the performance of deep learning models heavily relies on the quantity of available training data [28].…”