Abstract #4504

Intravoxel Tissue Heterogeneity: One-to-one Correspondence between Non-Gaussian Diffusion MRI Parameters and Histologic Features

Muge Karaman^1,2, Lingdao Sha³, Tingqi Shi¹, Dan Schonfeld^2,3,4, Tibor Valyi-Nagy⁵, and X Joe Zhou^1,2,6

¹Center for Magnetic Resonance Research, University of Illinois at Chicago, Chicago, IL, United States, ²Department of Bioengineering, University of Illinois at Chicago, Chicago, IL, United States, ³Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, IL, United States, ⁴Department of Computer Science, University of Illinois at Chicago, Chicago, IL, United States, ⁵Department of Pathology, University of Illinois at Chicago, Chicago, IL, United States, ⁶Departments of Radiology and Neurosurgery, University of Illinois at Chicago, Chicago, IL, United States

The parameters of the continuous-time random-walk (CTRW) model have been shown to be related to the underlying tissue heterogeneity. However, it has been challenging to establish a rigorous correlation between the CTRW parameters and the gold-standard histology. This is primarily because the histopathological evaluation of tissue heterogeneity is a labor-intensive task. We develop a machine-learning algorithm that quantifies the microscopic tissue heterogeneity revealed by histology as probability maps; and demonstrate a one-to-one correspondence between the CTRW parameters and tissue structural heterogeneity. Our results have provided evidence towards establishing a correlation between the CTRW parameter values and tissue heterogeneity.

This abstract and the presentation materials are available to members only; a login is required.

Join Here