Efe Ozkaya

Synthetic radiographs, including OpenAI’s ChatGPT-generated ones, are not easily distinguishable from authentic radiographs by either radiologists or large language models; physician training and dedicated tools are crucial to mitigate risks.

MR elastography demonstrated excellent stiffness measurement precision and test-retest repeatability across five study centers, 10 scanners, three manufacturers, two field strengths, two MR elastography sequences, and three phantoms mimicking different degrees of liver stiffness.

Magnetic Resonance Elastography (MRE) is a developing imaging technique that enables non-invasive estimation of tissue mechanical properties through the combination of induced mechanical displacements in the tissue and Magnetic Resonance Imaging (MRI). The mechanical drivers necessary to produce shear waves in the tissue have been a focus of engineering effort in the development and refinement of MRE. The potential targeting of smaller and stiffer tissues calls for increases in actuation frequency and refinement of mechanical driver positioning. Furthermore, the anisotropic nature of soft tissues results in driver position related changes in observed displacement wave patterns. These challenges motivate the investigation and development of the concept of active MRE driver positioning through visual servoing under MR imaging. Objective: This work demonstrates the initial prototype of an MRE driver positioning system, allowing capture of displacement wave patterns from various mechanical vibration loading angles under different vibration frequencies through MR imaging. Methods: Three different configurations of the MRE driver positioning robot are tested with an intervertebral disc (IVD) shaped gel phantom. Results: Both the octahedral shear stress signal to noise ratio (OSS-SNR) and estimated stiffness show statistically significant dependence on driver configuration in each of the three phantom IVD regions. Conclusion: This dependence demonstrates that driver configuration is a critical factor in MRE, and that the developed robot is capable of producing a range of configurations. Significance: This work presents the first demonstration of an active, imaging guided MRE driver positioning system, with significance for the future application of MRE to a wider range of human tissues.