A machine learning-based model for a dose point kernel calculation

Abstract

Purpose Absorbed dose calculation by kernel convolution requires the prior determination of dose point kernels (DPK). This study reports on the design, implementation, and test of a multi-target regressor approach to generate the DPKs for monoenergetic sources and a model to obtain DPKs for beta emitters. Methods DPK for monoenergetic electron sources were calculated using the FLUKA Monte Carlo (MC) code for many materials of clinical interest and initial energies ranging from 10 to 3000 keV. Regressor Chains (RC) with three different coefficients regularization/shrinkage models were used as base regressors. Electron monoenergetic scaled DPKs (sDPKs) were used to assess the corresponding sDPKs for beta emitters typically used in nuclear medicine, which were compared against reference published data. Finally, the beta emitters sDPK were applied to a patient-specific case calculating the Voxel Dose Kernel (VDK) for a hepatic radioembolization treatment with $$^{90}$$ 90 Y. Results The three trained machine learning models demonstrated a promising capacity to predict the sDPK for both monoenergetic emissions and beta emitters of clinical interest attaining differences lower than $$10\%$$ 10 % in the mean average percentage error (MAPE) as compared with previous studies. Furthermore, differences lower than $$7 \%$$ 7 % were obtained for the absorbed dose in patient-specific dosimetry comparing against full stochastic MC calculations. Conclusion An ML model was developed to assess dosimetry calculations in nuclear medicine. The implemented approach has shown the capacity to accurately predict the sDPK for monoenergetic beta sources in a wide range of energy in different materials. The ML model to calculate the sDPK for beta-emitting radionuclides allowed to obtain VDK useful to achieve reliable patient-specific absorbed dose distributions required short computation times.

On the Use of Artificial Intelligence for Dosimetry of Radiopharmaceutical Therapies

“…One option for AI-based conversion of units of activity or timeintegrated activity into absorbed dose is to use AI for predicting dose point kernel or S value kernel for different or highly heterogeneous media [50,64,65]. Another method to predict dose point kernel for monoenergetic electrons and several beta-emit-ting radionuclides for various media based on a regressor chain was proposed by Scarinci et al [65].…”

“…One option for AI-based conversion of units of activity or timeintegrated activity into absorbed dose is to use AI for predicting dose point kernel or S value kernel for different or highly heterogeneous media [50,64,65]. Another method to predict dose point kernel for monoenergetic electrons and several beta-emit-ting radionuclides for various media based on a regressor chain was proposed by Scarinci et al [65]. Akhavanallaf et al [50] used a convolutional neural network with 20 layers to estimate specific S value kernel that consider the patient-specific density distribution as derived from the CT image around a defined central voxel.…”