Performance-aware programming for intraoperative intensity-based image registration on graphics processing units.

Martin C W LeongKit-Hang LeeBowen P Y KwanYui-Lun NgZhiyu LiuNassir NavabWayne LukKa-Wai Kwok

Published in: International journal of computer assisted radiology and surgery (2021)

The computation bottlenecks in diffeomorphic log-demons are pinpointed, analyzed, and resolved using various GPU performance-aware programming techniques. The proposed fast computation on basic image operations not only enhances the computation of diffeomorphic log-demons, but is also potentially extended to speed up many other intensity-based approaches. Our implementation is open-source on GitHub at https://bit.ly/2PYZxQz .

Keyphrases

deep learning
high intensity
primary care
healthcare
quality improvement