Imaging Data Management
Full course description
Modern imaging technologies have the potential to create vast amounts of imaging data. The imaging professional must understand how to cope with the 4Vs of big data: Volume, Variety, Velocity, and Veracity. The volume of data refers to the size of data that needs to be processed and analysed, and the working professional must be prepared to work with data sizes that range from megabytes to petabytes. The velocity of data refers to the speed at which data are generated, and one must understand how to build pipelines that can scale with the amount of data coming in at any one time. The variety of data refers to the different ways that data are structured – this includes unstructured data such as text, semi-structured data such as data records, and structured data available in standardized data formats. Finally, the veracity of data refers to the quality of data which can affect the whether results can be obtained or whether any meaningful interpretation can be made from the analysis. Overall, this course provides you with a deep understanding of the opportunities, challenges, and practical concerns in working with different kinds of imaging data.
Course objectives
After completing this course, you are able to:
- Explain how images are represented on a computer and what imaging standards are available to store, retrieve and process images.
- Be able to describe, contrast, and use prevalent imaging metadata standards.
- Understand the merits of different imaging platforms (e.g. XNAT) in working with large imaging datasets, and use such platforms in data storage and retrieval.
- Describe strategies for data storage, disaster recovery, and data exchange.
- Make use of public repositories containing public imaging data.
- Apply simple imaging analytics on a single image and multiple image collection
- Recognize potential privacy concerns related to the collection and use of, in order to make image processing practices safe and secure.
- Describe emerging privacy-preserving technologies to safely access and analyse large and small image data collections.
Recommended reading
- Ranschaert, E.R., Morozov, S., & Algra, P.R. (Eds.). (2019). Artificial Intelligence in Medical Imaging: Opportunities, Applications and Risks. Springer. https://doi.org/10.1007/978-3-319-94878-2
- Bui, A.A.T., & Taira, R.K. (Eds.). (2009). Medical Imaging Informatics. Springer. https://doi.org/10.1007/978-1-4419-0385-3
- Branstetter, B.F. (Ed.) (2010). Practical Imaging Informatics. Foundations and Applications for PACS Professionals. https://doi.org/10.1007/978-1-4419-0485-0
- G. Paiva Fonseca