Fast GPU 3D Diffeomorphic Image Registration

arXiv2004.08893MaRDI QIDQ6338994

Author name not available (Why is that?)

Publication date: 19 April 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 $256^3$ clinical images in less than 6 seconds on a single NVIDIA Tesla V100. This amounts to over 20$imes$ speed-up over the current version of CLAIRE and over 30$imes$ speed-up over existing GPU implementations.

Has companion code repository: https://github.com/andreasmang/claire

Mathematics Subject Classification ID

No records found.

This page was built for publication: Fast GPU 3D Diffeomorphic Image Registration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6338994)