A framework for prediction of personalized pediatric nuclear medical dosimetry based on machine learning and Monte Carlo techniques.

Objective:A methodology is introduced for the development of an internal dosimetry prediction toolkit for nuclear medical pediatric applications. The proposed study exploits Artificial Intelligence techniques using Monte Carlo simulations as ground truth for accurate prediction of absorbed doses per organ prior to the imaging acquisition considering only personalized anatomical characteristics of any new pediatric patient.Approach:GATE Monte Carlo simulations were performed using a population of computational pediatric models to calculate the specific absorbed dose rates (SADRs) in several organs. A simulated dosimetry database was developed for 28 pediatric phantoms (age range 2-17 years old, both genders) and 5 different radiopharmaceuticals. Machine Learning regression models were trained on the produced simulated dataset, with leave one out cross validation for the prediction model evaluation. Hyperparameter optimization and ensemble learning techniques for a variation of input features were applied for achieving the best predictive power, leading to the development of a SADR prediction toolkit for any new pediatric patient for the studied organs and radiopharmaceuticals.Main results. SADR values for 30 organs of interest were calculated via Monte Carlo simulations for 28 pediatric phantoms for the cases of five radiopharmaceuticals. The relative percentage uncertainty in the extracted dose values per organ was lower than 2.7%. An internal dosimetry prediction toolkit which can accurately predict SADRs in 30 organs for five different radiopharmaceuticals, with mean absolute percentage error on the level of 8% was developed, with specific focus on pediatric patients, by using Machine Learning regression algorithms, Single or Multiple organ training and Artificial Intelligence ensemble techniques. Significance: A large simulated dosimetry database was developed and utilized for the training of Machine Learning models. The developed predictive models provide very fast results (<2 s) with an accuracy >90% with respect to the ground truth of Monte Carlo, considering personalized anatomical characteristics and the biodistribution of each radiopharmaceutical. The proposed method is applicable to other medical dosimetry applications in different patients' populations.

HPC+ in the medical field: Overview and current examples.

BACKGROUND: To say data is revolutionising the medical sector would be a vast understatement. The amount of medical data available today is unprecedented and has the potential to enable to date unseen forms of healthcare. To process this huge amount of data, an equally huge amount of computing power is required, which cannot be provided by regular desktop computers. These areas can be (and already are) supported by High-Performance-Computing (HPC), High-Performance Data Analytics (HPDA), and AI (together "HPC+"). OBJECTIVE: This overview article aims to show state-of-the-art examples of studies supported by the National Competence Centres (NCCs) in HPC+ within the EuroCC project, employing HPC, HPDA and AI for medical applications. METHOD: The included studies on different applications of HPC in the medical sector were sourced from the National Competence Centres in HPC and compiled into an overview article. Methods include the application of HPC+ for medical image processing, high-performance medical and pharmaceutical data analytics, an application for pediatric dosimetry, and a cloud-based HPC platform to support systemic pulmonary shunting procedures. RESULTS: This article showcases state-of-the-art applications and large-scale data analytics in the medical sector employing HPC+ within surgery, medical image processing in diagnostics, nutritional support of patients in hospitals, treating congenital heart diseases in children, and within basic research. CONCLUSION: HPC+ support scientific fields from research to industrial applications in the medical area, enabling researchers to run faster and more complex calculations, simulations and data analyses for the direct benefit of patients, doctors, clinicians and as an accelerator for medical research.

Elemental Depth Profiling of Intact Metal-Organic Framework Single Crystals by Scanning Nuclear Microprobe.

The growing field of MOF-catalyst composites often relies on postsynthetic modifications for the installation of active sites. In the resulting MOFs, the spatial distribution of the inserted catalysts has far-reaching ramifications for the performance of the system and thus needs to be precisely determined. Herein, we report the application of a scanning nuclear microprobe for accurate and nondestructive depth profiling of individual UiO-66 and UiO-67 (UiO = Universitetet i Oslo) single crystals. Initial optimization work using native UiO-66 crystals yielded a microbeam method which avoided beam damage, while subsequent analysis of Zr/Hf mixed-metal UiO-66 crystals demonstrated the potential of the method to obtain high-resolution depth profiles. The microbeam method was further used to analyze the depth distribution of postsynthetically introduced organic moieties, revealing either core-shell or uniform incorporation can be obtained depending on the size of the introduced molecule, as well as the number of carboxylate binding groups. Finally, the spatial distribution of platinum centers that were postsynthetically installed in the bpy binding pockets of UiO-67-bpy (bpy = 5,5'-dicarboxyy-2,2'-bipyridine) was analyzed by microbeam and contextualized. We expect that the method presented herein will be applicable for characterizing a wide variety of MOFs subjected to postsynthetic modifications and provide information crucial for their optimization as functional materials.

On the Z1-dependence of electronic stopping in TiN.

We present a thorough experimental study of electronic stopping of H, He, B, N, Ne and Al ions in TiN with the aim to learn about the energy loss mechanisms of slow ions. The energy loss was measured by means of time-of-flight medium-energy ion scattering. Thin films of TiN on silicon with a δ-layer of W at the TiN/Si interface were used as targets. We compare our results to non-linear density functional theory calculations, examining electron-hole pair excitations by screened ions in a free electron gas in the static limit, with a density equivalent to the expected value for TiN. These calculations predict oscillations in the electronic stopping power for increasing atomic number Z1 of the projectile. An increasing discrepancy between our experimental results and predictions by theory for increasing Z1 was observed. This observation can be attributed to contributions from energy loss channels different from electron-hole pair excitation in binary Coulomb collisions.

Uniform distribution of post-synthetic linker exchange in metal-organic frameworks revealed by Rutherford backscattering spectrometry.

Rutherford backscattering spectrometry (RBS) has been used for the first time to study post-synthetic linker exchange (PSE) in metal-organic frameworks. RBS is a non-invasive method to quantify the amount of introduced linker, as well as providing a means for depth profiling in order to identify the preferred localization of the introduced linker. The exchange of benzenedicarboxylate (bdc) by similarly sized 2-iodobenzenedicarboxylate (I-bdc) proceeds considerably slower than migration of I-dbc through the UiO-66 crystal. Consequently, the I-bdc is found evenly distributed throughout the UiO-66 samples, even at very short PSE exposure times.