Image space formalism of convolutional neural networks for k-space interpolation.

Purpose: Noise resilience in image reconstructions by scan-specific robust artificial neural networks for k-space interpolation (RAKI) is linked to nonlinear activations in k-space. To gain a deeper understanding of this relationship, an image space formalism of RAKI is introduced for analyzing noise propagation analytically, identifying and characterizing image reconstruction features and to describe the role of nonlinear activations in a human-readable manner.

Theory And Methods: The image space formalism for RAKI inference is employed by expressing nonlinear activations in k-space as element-wise multiplications with activation masks, which transform into convolutions in image space.

Controlling sharpness, SNR, and specific absorption rate for 3D fast-spin echo at 7T by end-to-end learning.

Purpose: To non-heuristically identify dedicated variable flip angle (VFA) schemes optimized for the point-spread function (PSF) and SNR of multiple tissues in 3D FSE sequences with very long echo trains at 7T.

Methods: The proposed optimization considers predefined specific absorption rate (SAR) constraints and target contrast using an end-to-end learning framework. The cost function integrates components for contrast fidelity (SNR) and a penalty term to minimize image blurring (PSF) for multiple tissues.

The Artificial Neural Twin - Process optimization and continual learning in distributed process chains.

Industrial process optimization and control is crucial to increase economic and ecologic efficiency. However, data sovereignty, differing goals, or the required expert knowledge for implementation impede holistic implementation. Further, the increasing use of data-driven AI-methods in process models and industrial sensory often requires regular fine-tuning to accommodate distribution drifts.

Selected annotated instance segmentation sub-volumes from a large scale CT data-set of a historic aircraft.

The Me 163 was a Second World War fighter airplane and is currently displayed in the Deutsches Museum in Munich, Germany. A complete computed tomography (CT) scan was obtained using a large scale industrial CT scanner to gain insights into its history, design, and state of preservation. The CT data enables visual examination of the airplane's structural details across multiple scales, from the entire fuselage to individual sprockets and rivets.

X-ray transmission imaging of waste printed circuit boards for value estimation in recycling using machine learning.

The growing amount of electronic waste is a global challenge: on one hand, it poses a threat to the environment as it may contain toxic or hazardous substances, on the other hand it is a valuable 'urban mine' containing metals like gold and copper. Thus, recycling of electronic waste is not only a measure to reduce environmental pollution but also economically reasonable as prices for raw materials are rising. Within electronic waste, printed circuit boards (PCBs) occupy a prominent position, as they contain most of the valuable material.

3D segmentation of plant root systems using spatial pyramid pooling and locally adaptive field-of-view inference.

Background: The non-invasive 3D-imaging and successive 3D-segmentation of plant root systems has gained interest within fundamental plant research and selectively breeding resilient crops. Currently the state of the art consists of computed tomography (CT) scans and reconstruction followed by an adequate 3D-segmentation process.

Challenge: Generating an exact 3D-segmentation of the roots becomes challenging due to inhomogeneous soil composition, as well as high scale variance in the root structures themselves.

The Detection of Foreign Items in Laundry Industry by Dual-Energy X-ray Transmission-Advantages and Limits.

Firefighters, paramedics, nursing staff, and other occupational groups are in constant need of fast and proper cleaning of their professional workwear, not only during a pandemic. Thus, laundry technology needs to become more efficient and automated. Unfortunately, some steps of the cleaning process, such as finding and removing foreign items from pockets or belts, are still completed manually.

Iterative training of robust k-space interpolation networks for improved image reconstruction with limited scan specific training samples.

Purpose: To evaluate an iterative learning approach for enhanced performance of robust artificial-neural-networks for k-space interpolation (RAKI), when only a limited amount of training data (auto-calibration signals [ACS]) are available for accelerated standard 2D imaging.

Methods: In a first step, the RAKI model was tailored for the case of limited training data amount. In the iterative learning approach (termed iterative RAKI [iRAKI]), the tailored RAKI model is initially trained using original and augmented ACS obtained from a linear parallel imaging reconstruction.

High-Energy Computed Tomography as a Prospective Tool for In Situ Monitoring of Mass Transfer Processes inside High-Pressure Reactors-A Case Study on Ammonothermal Bulk Crystal Growth of Nitrides including GaN.

For the fundamental understanding and the technological development of the ammonothermal method for the synthesis and crystal growth of nitrides, an in situ monitoring technique for tracking mass transport of the nitride throughout the entire autoclave volume is desirable. The feasibility of using high-energy computed tomography for this purpose was therefore evaluated using ex situ measurements. Acceleration voltages of 600 kV were estimated to yield suitable transparency in a lab-scale ammonothermal setup for GaN crystal growth designed for up to 300 MPa operating pressure.