Abstract #1725

Deep Learning Model for Liver MRI Segmentation

Amber Michele Mittendorf¹, Lawrence Ngo¹, Erol Bozdogan¹, Mohammad Chaudhry¹, Steven Chen¹, Gemini Janas^1,2, Jacob Johnson³, Zhe Zhu¹, Maciej Mazurowski¹, and Mustafa R Bashir^1,2,4

¹Department of Radiology, Duke University Medical Center, Durham, NC, United States, ²Center for Advanced Magnetic Resonance Imaging, Duke University Medical Center, Durham, NC, United States, ³Department of Radiology, University of Wisconsin, Madison, WI, United States, ⁴Department of Medicine, Gastroenterology, Duke University Medical Center, Durham, NC, United States

Hepatic segmentation is an important but tedious clinical task used in a variety of applications. Existing techniques are relatively narrow in scope, requiring a particular type of MRI sequence or CT for accurate segmentation. We developed a Convolutional Neural Network (CNN) capable of automated liver segmentation on single-shot fast spin echo, T1-weighted, or opposed phase proton-density (OP-PD) weighted sequences using separate training/validation and testing data sets. Compared to human segmenters, the CNN performed well, with volumetric DICE coefficients of 0.92-0.95. The CNN performed least consistently on OP-PD sequences, which had the smallest number of cases in the training/validation data set.

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

Join Here