Abstract #4078
Automatic lung segmentation for hyperpolarized gas MRI using transferred generative adversarial network and three-view aggregation
Shih-Kang Chao1, Ummul Afia Shammi2, Lucia Flors-Blasco3, Talissa Altes4, John Mugler5,6, Craig Meyer5,6, Jaime Mata6, Wilson Miller6, and Robert Thomen2,4
1Department of Statistics, University of Missouri, Columbia, MO, United States, 2Department of Biomedical, Biological & Chemical Engineering, University of Missouri, Columbia, MO, United States, 3Keck School of Medicine, University of Southern California, Los Angeles, CA, United States, 4Department of Radiology, University of Missouri, Columbia, MO, United States, 5Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, United States, 6Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, VA, United States
Synopsis
We evaluate an automatic lung segmentation approach that aggregates the predicted mask of coronal, axial, and sagittal views generated by a deep conditional generative adversarial network (GAN) whose only input is the hyperpolarized gas (HPG) MRI. On five test subjects with ventilation defect percentages [VDP] of 25-38%, our method achieved an average Dice score of 87.72, and above 90 on a healthy control subject. The slice-wise Dice score had an average correlation of 0.72 with the human expert and a median correlation of -0.79 with VDP, and both are significant for 4 out of 5 test patients at level 1%.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
