A multi-channel deep learning approach for lung cavity estimation using hyperpolarized gas and proton MRI
Joshua Russell Astley, Alberto M Biancardi, Helen Marshall, Paul JC Hughes, Guilhem J Collier, Laurie J Smith, James Eaden, Jim M Wild, Bilal Tahir
Hyperpolarized (HP) gas MRI enables quantification of regional lung ventilation via clinical biomarkers such as the ventilation defect percentage (VDP). VDP is computed from segmentations derived from spatially co-registered functional HP gas MRI and structural proton ($^1$H)-MRI; although these scans are acquired at similar inflation levels, misalignments are frequent, requiring a lung cavity estimation (LCE). Here, we propose a multi-channel deep learning method for generating LCEs using HP gas and $^1$H-MRI. We compare the performance of the proposed method to single-channel alternatives.
Thursday 7th July
Poster Session 2.2 - onsite 11:00 - 12:00, virtual 15:20 - 16:20 (UTC+2)