Direct reconstruction of positron emission tomography (PET) data using deep neural networks is a growing field of research. Initial results are promising, but often the networks are complex, memory utilization inefficient, produce relatively small 2D image slices (e.g., 128×128), and low count rate reconstructions are of varying quality. This paper proposes FastPET, a novel direct reconstruction convolutional neural network that is architecturally simple, memory space efficient, works for non-trivial 3D image volumes and is capable of processing a wide spectrum of PET data including low-dose and multi-tracer applications. FastPET uniquely operates on a histo-image (i.e., image-space) representation of the raw data enabling it to reconstruct 3D image volumes 67x faster than Ordered Subsets Expectation Maximization (OSEM). We detail the FastPET method trained on whole-body and low-dose whole-body data sets and explore qualitative and quantitative aspects of reconstructed images from clinical and phantom studies. Additionally, we explore the application of FastPET on a neurology data set containing multiple different tracers. The results show that not only are the reconstructions very fast, but the images are high quality and have lower noise than iterative reconstructions.

<!-- *** Custom HTML *** --> Purpose: Neural network image reconstruction directly from measurement data is a relatively new field of research, which until now has been limited to producing small single-slice images (e.g., 1 × 128 × 128). We proposed a more efficient network design for positron emission tomography called DirectPET, which is capable of reconstructing multislice image volumes (i.e., 16 × 400 × 400) from sinograms. Approach: Large-scale direct neural network reconstruction is accomplished by addressing the associated memory space challenge through the introduction of a specially designed Radon inversion layer. Using patient data, we compare the proposed method to the benchmark ordered subsets expectation maximization (OSEM) algorithm using signal-to-noise ratio, bias, mean absolute error, and structural similarity measures. In addition, line profiles and full-width half-maximum measurements are provided for a sample of lesions. Results: DirectPET is shown capable of producing images that are quantitatively and qualitatively similar to the OSEM target images in a fraction of the time. We also report on an experiment where DirectPET is trained to map low-count raw data to normal count target images, demonstrating the method’s ability to maintain image quality under a low-dose scenario. Conclusion: The ability of DirectPET to quickly reconstruct high-quality, multislice image volumes suggests potential clinical viability of the method. However, design parameters and performance boundaries need to be fully established before adoption can be considered.

Tomographic image reconstruction is often formulated as a regularized weighted least squares (RWLS) problem optimized by iterative algorithms that are either inherently algebraic or derived from a statistical point of view. This paper compares a modified version of simultaneous iterative reconstruction technique (SIRT), which is of the former type, with a version of separable quadratic surrogates (SQS), which is of the latter type. We show that the two algorithms minimize the same criterion function using similar forms of preconditioned gradient descent. We present near-optimal relaxation for both based on eigenvalue bounds and include a heuristic extension for use with ordered subsets. We provide empirical evidence that SIRT and SQS converge at the same rate for all intents and purposes. For context, we compare their performance with an implementation of preconditioned conjugate gradient. The illustrative application is X-ray CT of luggage for aviation security.

The complexity and throughput of computer networks are rapidly increasing as a result of the proliferation of interconnected devices, data-driven applications, and remote working. Providing situational awareness for computer networks requires monitoring and analysis of network data to understand normal activity and identify abnormal activity. A scalable platform to process and visualize data in real time for large-scale networks enables security analysts and researchers to not only monitor and study network flow data but also experiment and develop novel analytics. In this paper, we introduce InSight2, an open-source platform for manipulating both streaming and archived network flow data in real time that aims to address the issues of existing solutions such as scalability, extendability, and flexibility. Case-studies are provided that demonstrate applications in monitoring network activity, identifying network attacks and compromised hosts and anomaly detection.

The results of an experimental study on the oxidation behavior of loaded gasoline particulate filters (GPFs) from a gasoline direct injection (GDI) engine are reported. PM was loaded on uncatalyzed cordierite GPF mini-cores by exposure to exhaust from a light-duty GDI engine operating during a rich acceleration condition on four fuels: 100% gasoline (E0); a 30% blend of ethanol in gasoline (E30); a 24% blend of isobutanol in gasoline (iBu24); or a 48% blend of isobutanol in gasoline (iBu48). The oxidative reactivities of these four types of PM were investigated as a function of temperature. Compared with E0, particulate matter (PM) from the ethanol blend showed a significant shift to lower temperature activity, whereas both isobutanol blends produced PM requiring higher temperatures to achieve complete oxidation. The oxidation kinetics of the E0 and E30 PM were studied in more detail. These cores were used in pulsed-oxidation studies to explore the oxidation kinetics of the PM throughout a stepwise burnout (i.e., regeneration). The results suggest that the reactivity of PM on GPF cores is sensitive to both its environmental history and the type of fuel being used. A unique neutron-imaging study was also performed on E0 and E30-loaded GPF cores to study how the PM layer thicknesses change during a stepwise burnout.

Endpoint Detection and Response (EDR) systems play a crucial role in continuously monitoring endpoint activities to detect, analyze, and respond to cybersecurity threats in real time. Traditional agent-based EDR systems rely on software agents installed on endpoints for data collection, which can be impractical due to the large number of devices, their mobility, and privacy concerns. In contrast, agentless EDR systems aim to overcome these limitations by remotely collecting network and host data, but they face challenges in precise data attribution because of the transient nature of network addresses. Achieving a fully zero-configuration agentless EDR system remains a significant challenge. This paper introduces InMesh, an innovative system that can identify and monitor endpoints without relying on network addressing or software agents. The effectiveness of the approach is demonstrated using real-world data.