A deep learning approach to radiation dose estimation

Abstract

Currently methods for predicting absorbed dose after administering a radiopharmaceutical are rather crude in daily clinical practice. Most importantly, individual tissue density distributions as well as local variations of the concentration of the radiopharmaceutical are commonly neglected. The current study proposes machine learning techniques like Green’s function-based empirical mode decomposition and deep learning methods on U-net architectures in conjunction with soft tissue kernel Monte Carlo (MC) simulations to overcome current limitations in precision and reliability of dose estimations for clinical dosimetric applications. We present a hybrid method (DNN-EMD) based on deep neural networks (DNN) in combination with empirical mode decomposition (EMD) techniques. The algorithm receives x-ray computed tomography (CT) tissue density maps and dose maps, estimated according to the MIRD protocol, i.e. employing whole organ S-values and related time-integrated activities (TIAs), and from measured SPECT distributions of 177Lu radionuclei, and learns to predict individual absorbed dose distributions. In a second step, density maps are replaced by their intrinsic modes as deduced from an EMD analysis. The system is trained using individual full MC simulation results as reference. Data from a patient cohort of 26 subjects are reported in this study. The proposed methods were validated employing a leave-one-out cross-validation technique. Deviations of estimated dose from corresponding MC results corroborate a superior performance of the newly proposed hybrid DNN-EMD method compared to its related MIRD DVK dose calculation. Not only are the mean deviations much smaller with the new method, but also the related variances are much reduced. If intrinsic modes of the tissue density maps are input to the algorithm, variances become even further reduced though the mean deviations are less affected. The newly proposed hybrid DNN-EMD method for individualized radiation dose prediction outperforms the MIRD DVK dose calculation method. It is fast enough to be of use in daily clinical practice.

DblurDoseNet: A Deep Residual Learning Network for Voxel Radionuclide Dosimetry Compensating for SPECT Imaging Resolution

“…Our results also demonstrated the advantage of residual learning framework exploiting the fast DVK approach as an initial estimate, which was not utilized in the prior studies [9,[11][12][13]. An alternative to fast DVK for the initial estimate is to generate a quick MC (low number of histories) estimate, which was not explored here.…”

“…Recently, there is an increase of interest in studies that apply deep neural networks in nuclear medicine applications [6][7][8]. However, deep learning applications [9,[11][12][13] in radionuclide 5 therapy are limited. Akhavanallaf et al [9], employed a modified ResNET [10] that represented voxel S-value kernels [2] to predict the distribution of the deposited energy in whole-body organlevel dosimetry and demonstrated comparable performance to the direct MC approach.…”

Whole-body voxel-based internal dosimetry using deep learning

“…The proposed method is robust and accurate and suitable for direct transfer to other molecular imaging modalities. Its advantages compared with other deep learning-based dosimetry techniques reported in the literature [35,36] are that it does not require whole-body dose maps for the training step. In addition, a single-trained model for a given radionuclide could be employed for all compounds labeled with this radionuclide.…”

“…They fed CT images, representing patient structural features, and static PET images, representing the activity distribution, into the network as input to predict a 3D dose map rate. Gotz et al set out to estimate dose maps of patients who received 177 Lu-PSMA using a modified U-Net network [36]. In this work, the training datasets consisted of a two-channel input, including CT images (i.e., patient-specific density map), MIRD-based voxelscale dose map obtained from SPECT images, and the ground truth obtained from direct MC simulations.…”

Artificial Intelligence and the Medical Physicist: Welcome to the Machine

“…A cornerstone of optimization of clinical imaging protocols is patients' dose estimation, which allows the dose to be balanced with image quality. Dose to the patient can be automatically calculated by DL in CT [49], single-photon emission computed tomography (SPECT) [50], and PET [51]. In interventional radiology, DL has been proposed for skin dose estimation [52].…”