Quality improvement in radiology reporting by imaging informatics and machine learning

Allard Olthof

    Research output: ThesisThesis fully internal (DIV)

    570 Downloads (Pure)


    This thesis aims to explore the application of imaging informatics and machine learning to improve the quality of radiology reporting.
    Feedback contributes to the identification of potential areas of improvement. Therefore, quality management in radiology could benefit from the implementation of feedback systems. Chapter 2 studies feedback from referring physicians, and chapter 3 demonstrates the implementation of a peer feedback system among radiologists.
    Structured reporting results in less variation among radiologists, and it encourages them to follow guidelines. The studies of chapters 4 and 5 demonstrate the successful application of structured reporting in oncological CT reports and critical findings communication.
    The branch of AI that deals with text is natural language processing (NLP). In chapters 6, 7, and 8, different NLP methods are compared, resulting in a pipeline to classify radiology reports on a large scale. The extracted information can be used for quality assurance and scientific research. In chapter 9, AI applications in the field of neuroradiology are systematically assessed. The results demonstrate that these new tools mainly support the radiologist and extend the radiologist's possibilities by providing quantitative analysis of radiological examinations.
    In conclusion, improved insight by human feedback or automatically extracted data provides radiologists with opportunities to improve reporting and the information quality delivered by radiology reporting. Structured reporting and AI applications allow radiologists to enhance their reports further and increase the positive impact on patient care.
    Original languageEnglish
    QualificationDoctor of Philosophy
    Awarding Institution
    • University of Groningen
    • van Ooijen, Peter, Supervisor
    • de Groot, Jan Cees, Co-supervisor
    • Cornelissen, Ludo, Co-supervisor
    Award date26-May-2021
    Place of Publication[Groningen]
    Publication statusPublished - 2021

    Cite this