To cope with inter-subject variability of anatomical features, the organ-level dosimetry approach was later extended by developing habitus-specific and patient-specific computational models. This approach assumes a uniform activity distribution within each organ and ignores individual anatomical characteristics. These quantitative parameters are modeled based on a reference computational model. The traditional MIRD technique is based on organ-level dosimetry using time-integrated activity and radionuclide S-values, which represents the mean absorbed dose to a target organ per radioactive decay in a source organ. In current clinical practice, patient dose monitoring is commonly based on simplified models, such as those derived by the Medical Internal Radiation Dose Committee (MIRD) formalism. In this framework, personalized dose estimation is crucial for optimizing clinical procedures while minimizing the risk of radiation-induced toxicity. Dose calculation in nuclear medicine is tightly linked to this approach. Precision medicine aims at shifting from the current one-size fits-all strategy to an individualized model. Personalized medicine is a new paradigm aiming at improving healthcare while lowering the costs, thus offering great potential for patient-specific diagnosis and optimal treatment. The proposed DNN-based WB internal dosimetry exhibited comparable performance to the direct Monte Carlo approach while overcoming the limitations of conventional dosimetry techniques in nuclear medicine. In organ-level dosimetry, the MRAE between the proposed method and MSV, SSV, and Olinda/EXM were 5.1%, 21.8%, and 23.5%, respectively. The MRAE of estimated absorbed dose between DNN, MSV, and SSV with respect to the MC simulation reference were 2.6%, 3%, and 49%, respectively. Bland and Altman analysis showed the lowest dose bias (2.6%) and smallest variance (CI: − 6.6, + 1.3) for DNN. The predicted specific voxel S-value kernels exhibited good agreement with the MC-based kernels serving as reference with a mean relative absolute error (MRAE) of 4.5 ± 1.8 (%).
The dose map predicted using the DNN was compared with the reference generated using MC simulations and two MIRD-based methods, including Single and Multiple S-Values (SSV and MSV) and Olinda/EXM software package. Accordingly, specific S-value kernels are inferred from the trained model and whole-body dose maps constructed in a manner analogous to the voxel-based MIRD formalism, i.e., convolving specific voxel S-values with the activity map. The training dataset consists of density maps obtained from CT images and the reference voxelwise S-values generated using Monte Carlo simulations. In this context, we employed a Deep Neural Network (DNN) to predict the distribution of deposited energy, representing specific S-values, from a single source in the center of a 3D kernel composed of human body geometry. We extended the voxel-scale MIRD approach from single S-value kernel to specific S-value kernels corresponding to patient-specific anatomy to construct 3D dose maps using hybrid emission/transmission image sets. Hence, we propose a novel method to perform whole-body personalized organ-level dosimetry taking into account the heterogeneity of activity distribution, non-uniformity of surrounding medium, and patient-specific anatomy using deep learning algorithms. In the era of precision medicine, patient-specific dose calculation using Monte Carlo (MC) simulations is deemed the gold standard technique for risk-benefit analysis of radiation hazards and correlation with patient outcome.