Fast GPU 3D diffeomorphic image registration
2020
Abstract 3D image registration is one of the most fundamental and computationally expensive operations in medical image analysis. Here, we present a mixed-precision, Gauss–Newton–Krylov solver for diffeomorphic registration of two images. Our work extends the publicly available CLAIRE library to GPU architectures. Despite the importance of image registration, only a few implementations of large deformation diffeomorphic registration packages support GPUs. Our contributions are new algorithms to significantly reduce the run time of the two main computational kernels in CLAIRE : calculation of derivatives and scattered-data interpolation. We deploy (i) highly-optimized, mixed-precision GPU-kernels for the evaluation of scattered-data interpolation, (ii) replace Fast-Fourier-Transform (FFT)-based first-order derivatives with optimized 8th-order finite differences, and (iii) compare with state-of-the-art CPU and GPU implementations. As a highlight, we demonstrate that we can register 25 6 3 clinical images in less than 6 s on a single NVIDIA Tesla V100. This amounts to over 20 × speed-up over the current version of CLAIRE and over 30 × speed-up over existing GPU implementations.
Keywords:
-
Correction
-
Source
-
Cite
-
Save
83
References
1
Citations
NaN
KQI