Meeting Banner
Abstract #3560

Comparison of 3D convolutional neural networks and loss functions for ventilated lung segmentation using multi-nuclear hyperpolarized gas MRI

Joshua R Astley1,2, Alberto M Biancardi1, Paul J Hughes1, Laurie J Smith1, Helen Marshall1, Guilhem J Collier1, James Eaden1, Nicholas D Weatherley1, Jim M Wild1, and Bilal A Tahir1,2
1POLARIS, University of Sheffield, Sheffield, United Kingdom, 2Oncology and Metabolism, University of Sheffield, Sheffield, United Kingdom

Deep learning has shown great promise for numerous medical image segmentation tasks, including delineation of ventilated lung volumes from hyperpolarized gas MRI. We previously demonstrated the utility of a VNet convolutional neural network (CNN), trained on a combination of 3He and 129Xe scans, in producing accurate segmentations that outperform conventional methods. In this work, we compared the performance of several 3D CNNs and loss functions for segmentation of ventilated lungs on a significantly larger and more diverse multi-nuclear hyperpolarised gas MRI dataset using several training strategies. We observe that the UNet CNN provides the best performing model for our dataset.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords