Hollis Potter

Keywords: Musculoskeletal: Joints

MRI provides unparalleled evaluation of regional joint anatomy. The structural composition of tissues is reflected in both morphologic and quantitative MRI, which has links to material properties and response to mechanical load.  This talk will discuss knee anatomy with a focus on articular cartilage, fibrocartilaginous meniscus, and ligament/tendon, drawing insights into tissue relaxometry as a function of histopathology and function. Imaging data provide information about response to injury and repair, and quantitative evaluation of ACL reconstruction, the repaired meniscus, and tendinopathy will further be provided, with a focus on T2, T2* and T1rho mapping, with and without applied load.  

Jung-Ah Choi

Keywords: Musculoskeletal: Skeletal, Musculoskeletal: Muscular, Musculoskeletal: Joints

In this session, I will review the role of MR imaging in evaluation of musculoskeletal infection with discussion of the use of gadolinium in MRI in imaging of infection. Especially, I will discuss the role of MRI in DM foot for differential diagnosis of infection vs. neuropathy with a brief review of advanced techniques. Lastly, I will talk about postoperative MRI after surgical treatment of musculoskeletal infection. 

Jutta Ellermann

Shanshan Wang

Keywords: Image acquisition: Machine learning, Image acquisition: Reconstruction

Deep learning (DL) has emerged as a leading approach in accelerating MR imaging. MR imaging involves physics-based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data-driven approaches. Our review will introduce the significant challenges faced by such knowledge-driven DL approaches in the context of fast MR imaging along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods.

Erik Dam

Keywords: Image acquisition: Machine learning

Deep learning (DL) methods can generally learn to spot anything that a radiologist can see. We will demonstrate impressive examples of segmentation of organs, automated radiologist scorings, and adaptive MR protocols that optimize the workflow and patient outcome across musculoskeletal and neurological disorders. We will add some intuition on how DL works but also highlight caveats since deep learning is not intelligent and only knows what it has been presented during training. This challenges generalization to other scanner models, protocols, pathological variations, and to other patient populations. Deployment of DL solutions therefore also relies on alert radiology experts.

Akshay Chaudhari

Keywords: Musculoskeletal: Joints, Image acquisition: Machine learning

This presentation will cover the fundamentals of some latest-generation machine learning techniques, including large language models (LLMs), contrastive image-language pretraining (CLIP), and score-based generative diffusion models. Potential applications of these novel technologies to musculoskeletal and broader MRI applications will be discussed.  

Sharmila Majumdar