A deep learning anthropomorphic model observer for a detection task in PET.

Background: Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task-based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO.

Data driven surrogate signal extraction for dynamic PET using selective PCA: time windows versus the combination of components.

Respiratory motion correction is beneficial in positron emission tomography (PET), as it can reduce artefacts caused by motion and improve quantitative accuracy. Methods of motion correction are commonly based on a respiratory trace obtained through an external device (like the real time position management system) or a data driven method, such as those based on dimensionality reduction techniques (for instance principal component analysis (PCA)). PCA itself being a linear transformation to the axis of greatest variation.

Ecotoxicological evaluation of surface waters in Northern Namibia.

The increasing pressure on freshwater systems due to intensive anthropogenic use is a big challenge in central-northern Namibia and its catchment areas, the Kunene and the Kavango Rivers, and the Cuvelai-Etosha Basin, that provide water for more than 1 million people. So far, there is no comprehensive knowledge about the ecological status and only few knowledge about the water quality. Therefore, it is crucial to learn about the state of the ecosystem and the ecological effects of pollutants to ensure the safe use of these resources.

Sequential deep learning image enhancement models improve diagnostic confidence, lesion detectability, and image reconstruction time in PET.

Background: Investigate the potential benefits of sequential deployment of two deep learning (DL) algorithms namely DL-Enhancement (DLE) and DL-based time-of-flight (ToF) (DLT). DLE aims to enhance the rapidly reconstructed ordered-subset-expectation-maximisation algorithm (OSEM) images towards block-sequential-regularised-expectation-maximisation (BSREM) images, whereas DLT aims to improve the quality of BSREM images reconstructed without ToF. As the algorithms differ in their purpose, sequential application may allow benefits from each to be combined.

Results of an international interlaboratory study on dioxin-like activities in drinking-, river surface- and wastewater using DR CALUX bioassay.

Aquatic animals and consumers of aquatic animals are exposed to increasingly complex mixtures of known and as-yet-unknown chemicals with dioxin-like toxicities in the water cycle. Effect- and cell-based bioanalysis can cover known and yet unknown dioxin and dioxin-like compounds as well as complex mixtures thereof but need to be standardized and integrated into international guidelines for environmental testing. In an international laboratory testing (ILT) following ISO/CD 24295 as standard procedure for rat cell-based DR CALUX un-spiked and spiked extracts of drinking-, surface-, and wastewater were validated to generate precision data for the development of the full ISO-standard.