While regions of interest analysis is widely used in quantitative MRI, emphasis usually is placed only on the spatial average and information of spatial heterogeneity is ignored. Texture analysis has gained increasing interest in the context of applying artificial intelligence. These Radiomic tools are now readily available in image analysis tool boxes for more widespread adoption. We illustrate an application of such analysis on quantitative renal MRI, including ADC, ASL and R2* maps. Our results show that several measures of heterogeneity of cortical voxel-wise maps discriminate between healthy and individuals with chronic kidney disease.
This abstract and the presentation materials are available to members only; a login is required.