[Applications of artificial intelligence in radiology]. / Anwendungsspektrum der künstlichen Intelligenz in der Radiologie.

BACKGROUND: Artificial intelligence (AI) is increasingly finding its way into routine radiological work. OBJECTIVE: Presentation of the current advances and applications of AI along the entire radiological patient journey. METHODS: Systematic literature review of established AI techniques and current research projects, with reference to consensus recommendations. RESULTS: The applications of AI in radiology cover a wide range, starting with AI-supported scheduling and indications assessment, extending to AI-enhanced image acquisition and reconstruction techniques that have the potential to reduce radiation doses in computed tomography (CT) or acquisition times in magnetic resonance imaging (MRI), while maintaining comparable image quality. These include computer-aided detection and diagnosis, such as fracture recognition or nodule detection. Additionally, methods such as worklist prioritization and structured reporting facilitated by large language models enable a rethinking of the reporting process. The use of AI promises to increase the efficiency of all steps of the radiology workflow and an improved diagnostic accuracy. To achieve this, seamless integration into technical workflows and proven evidence of AI systems are necessary. CONCLUSION: Applications of AI have the potential to profoundly influence the role of radiologists in the future.

Wildtype heterogeneity contributes to clonal variability in genome edited cells.

Genome editing tools such as CRISPR/Cas9 enable the rapid and precise manipulation of genomes. CRISPR-based genome editing has greatly simplified the study of gene function in cell lines, but its widespread use has also highlighted challenges of reproducibility. Phenotypic variability among different knockout clones of the same gene is a common problem confounding the establishment of robust genotype-phenotype correlations. Optimized genome editing protocols to enhance reproducibility include measures to reduce off-target effects. However, even if current state-of-the-art protocols are applied phenotypic variability is frequently observed. Here we identify heterogeneity of wild-type cells as an important and often neglected confounding factor in genome-editing experiments. We demonstrate that isolation of individual wild-type clones from an apparently homogenous stable cell line uncovers significant phenotypic differences between clones. Strikingly, we observe hundreds of differentially regulated transcripts (477 up- and 306 downregulated) when comparing two populations of wild-type cells. Furthermore, we show a variety of cellular and biochemical alterations in different wild-type clones in a range that is commonly interpreted as biologically relevant in genome-edited cells. Heterogeneity of wild-type cells thus contributes to variability in genome-edited cells when these are generated through isolation of clones. We show that the generation of monoclonal isogenic wild-type cells prior to genomic manipulation reduces phenotypic variability. We therefore propose to generate matched isogenic control cells prior to genome editing to increase reproducibility.