Abstract #1247

U-Net-based deep convolutional neural network for detection of superparamagnetic drug-eluting particles used for liver chemoembolization

NING LI^1,2, Cyril Tous^1,2, Phillip Fei^1,2, Ivan P Dimov^1,2, Simon Lessard^1,2, Urs O. Häfeli³, Sylvain Martel⁴, An Tang^1,2, and Gilles Soulez^1,2

¹Centre de recherche du Centre hospitalier de l’Université de Montréal (CRCHUM), Montreal, QC, Canada, ²Université de Montréal, Montreal, QC, Canada, ³University of British Columbia, Vancouver, BC, Canada, ⁴Polytechnique Montréal, Montreal, QC, Canada

Synopsis

Magnetic steering of superparamagnetic drug-eluting particles (SMDEPs) loaded with anti-tumor drugs across hepatic arteries is a promising technique to perform segmental liver embolization for patients with hepatocellular carcinomas (HCCs). These aggregates (20 ± 6 SMDEPs) are sequentially released with a specially designed injector through a catheter in the proper hepatic artery of a swine placed in an MRI. Manual segmentation was previously done to localize and count the particles (volume of the artifact) in each lobe. We propose to train a U-net over this pre-existing database. Dice similarity coefficient, accuracy, and precision were respectively 99.1%, 98.3%, and 84.6%.

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

Join Here