Abstract #2315

Absolute Quantification of Stem Cell Transplant in MRI

Muhammad Jamal Afridi¹, Arun Ross², and Erik M Shapiro³

¹Department of Radiology, Department of Computer Science, Michigan State University, East Lansing, MI, United States, ²Department of Computer Science, Michigan State University, East Lansing, MI, United States, ³Department of Radiology, Michigan State University, East Lansing, MI, United States

We describe an image analysis strategy for quantifying the location and number of transplanted stem cells from MRI images. MRI-based single cell detection facilitates the use of machine learning algorithms for spot detection. Using convolutional neural networks, automatic and intelligent cell enumeration was first developed on in vitro agarose samples containing a known number of labeled cell mimics. Then, the validated image analysis approach was used to quantify stem cell transplants in rodent brains. An accuracy of 99.8% was achieved on in vitro samples and 94.6% on in vivo examples.

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

Join Here