TY - GEN
T1 - Generative Adversarial Registration for Improved Conditional Deformable Templates
AU - Dey, Neel
AU - Ren, Mengwei
AU - Dalca, Adrian V.
AU - Gerig, Guido
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Deformable templates are essential to large-scale medical image registration, segmentation, and population analysis. Current conventional and deep network-based methods for template construction use only regularized registration objectives and often yield templates with blurry and/or anatomically implausible appearance, confounding downstream biomedical interpretation. We reformulate deformable registration and conditional template estimation as an adversarial game wherein we encourage realism in the moved templates with a generative adversarial registration framework conditioned on flexible image covariates. The resulting templates exhibit significant gain in specificity to attributes such as age and disease, better fit underlying group-wise spatiotemporal trends, and achieve improved sharpness and centrality. These improvements enable more accurate population modeling with diverse covariates for standardized downstream analyses and easier anatomical delineation for structures of interest.
AB - Deformable templates are essential to large-scale medical image registration, segmentation, and population analysis. Current conventional and deep network-based methods for template construction use only regularized registration objectives and often yield templates with blurry and/or anatomically implausible appearance, confounding downstream biomedical interpretation. We reformulate deformable registration and conditional template estimation as an adversarial game wherein we encourage realism in the moved templates with a generative adversarial registration framework conditioned on flexible image covariates. The resulting templates exhibit significant gain in specificity to attributes such as age and disease, better fit underlying group-wise spatiotemporal trends, and achieve improved sharpness and centrality. These improvements enable more accurate population modeling with diverse covariates for standardized downstream analyses and easier anatomical delineation for structures of interest.
UR - http://www.scopus.com/inward/record.url?scp=85121194308&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121194308&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.00390
DO - 10.1109/ICCV48922.2021.00390
M3 - Conference contribution
AN - SCOPUS:85121194308
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 3909
EP - 3921
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -