AI-Based Acquisition, Reconstruction & Post-Processing
Joshua D Trzasko1
1Mayo Clinic, Rochester, MN, United States
Synopsis
Musculoskeletal (MSK) imaging is a complex area of MRI with unique goals, requirements, and challenges. In recent years, Artificial Intelligence (AI) technologies – including machine (ML) and deep learning (DL) – have facilitated many new capabilities in this field that were previously impossible with conventional imaging technologies. This talk will overview the technical mechanics of AI/ML and discuss how techniques from this field can be applied for MSK MRI, including fast imaging, denoising, superresolution, motion correction, parameter mapping, segmentation, and radiomics. Example applications from recent literature as well as emerging directions of AI/ML technologies for MSK MRI will be discussed.
Target Audience
Clinicians and scientists who are interested in obtaining a basic technical understanding of artificial intelligence (AI) and machine learning (ML) technologies, and how they can be applied for different tasks and applications in musculoskeletal (MSK) MRI. Syllabus
This lecture will briefly cover the following topics:
- Review of key goals, requirements, and challenges in MSK MR imaging
- Introduction to Artificial Intelligence technologies including machine learning (ML) and deep learning (DL), and discussion of how these relate to traditional data processing and analysis tools.
- Overview of technical mechanics of modern AI tools including hardware requirements, popular software tools, curation and use of training data, and deployment mechanics and considerations
- Caveats for using AI/ML methods in clinical practice
- Review of literature example research applications of AI/ML for MSK, including: fast imaging, denoising, superresolution, motion correction, parameter mapping, segmentation, and radiomics
- Discussion of commercially available AI/ML technologies for MSK MRI
- Emerging directions of AI/ML technologies for MSK MRI
Takeaway Messages
Following this lecture, participants should be able to:
- Describe the fundamental differences between AI/ML technologies and traditional data processing and analysis tools
- Explain the key technical components of an AI/ML technology implementation
- Discuss at least 3 MSK MRI applications where AI/ML tools have been applied and detail how they were setup and utilized within each area
Acknowledgements
No acknowledgement found.References
No reference found.
Proc. Intl. Soc. Mag. Reson. Med. 29 (2021)