Search

Background: Scattering photons can seriously contaminate cone‐beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality‐related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation. Purpose: Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed. Methods: Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q‐network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U‐net based scatter estimation approach for comparison. Results: The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal‐to‐noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware‐based beam stop array algorithm to obtain the scatter‐free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB. Conclusions: In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality. [ABSTRACT FROM AUTHOR]

The variability of sea surface temperatures (SSTs) is crucial in climate dynamics, influencing marine ecosystems and human activities. This study leverages graph neural networks (GNNs), specifically a GraphSAGE model, to forecast SSTs and their anomalies (SSTAs), focusing on the global scale structure of climatological data. We introduce an improved graph construction technique for SST teleconnection representation. Our results highlight the GraphSAGE model's capability in 1‐month‐ahead global SST and SSTA forecasting, with SST predictions spanning up to 2 years with a recursive approach. Notably, regions with persistent currents exhibited enhanced SSTA predictability, contrasting with equatorial and Antarctic areas. Our GNN outperformed both the persistence model and traditional methods. Additionally, we offer an SST and SSTA graph data set based on ERA5 and a graph generation tool. This GNN case study has shown how the GraphSAGE can be used in SST and SSTA forecasting, and will provide a foundation for further refinements such as adjusting graph construction, optimizing imbalanced regression techniques for extreme SSTAs, and integrating GNNs with other temporal pattern learning methods to improve long‐term predictions. Plain Language Summary: Have you ever wondered how scientists predict climate changes like warming oceans or unusual weather patterns? Our team is improving these predictions by focusing on sea surface temperatures (SSTs) and SST anomalies (SSTAs)—changes in ocean temperatures that greatly impact our environment and society. Traditionally, scientists use grid‐based machine learning models for these forecasts. We have taken a new approach using graph neural networks (GNNs), which are excellent at learning spatial patterns. This method does not just predict temperatures; it understands how different ocean areas are interconnected. Our technique successfully forecasts SSTs up to 2 years ahead and SSTAs 1 month in advance, particularly in regions with strong ocean currents. This accuracy is crucial for anticipating and preparing for climate impacts on marine and human activities. We have developed tools and data sets for researchers, which will foster advancements in graph‐based climate forecasting. Our findings demonstrate that using appropriate graph re‐sampling and GNNs can help understand the complex climate system. In summary, we are pioneering new ways to predict ocean temperature changes through machine learning, contributing to our understanding of and adaptation to climate change. This work benefits not just scientists, but anyone interested in climate and ocean studies. Key Points: Explores the power of graph representation for global sea surface temperature (SST) and SST anomaly (SSTA) forecastingAddresses the issues with traditional grid‐based models and provides an SST graph data set and a tool for converting SST grid data to graphsShows the efficacy of the GraphSAGE model for global SST and SSTA forecasting and identifies the regions where SSTAs are more predictable [ABSTRACT FROM AUTHOR]