Fully-deformable 3D image registration in two seconds
This provides faster medical image analysis for clinicians, though it is incremental as it builds on existing variational approaches.
The paper tackles the problem of slow 3D image registration by developing a highly parallel GPU-based method, achieving an average runtime of 1.99 seconds on real-world CT scans with a 32.53x speedup compared to CPU and ranking third on a benchmark with 0.32 seconds average runtime.
We present a highly parallel method for accurate and efficient variational deformable 3D image registration on a consumer-grade graphics processing unit (GPU). We build on recent matrix-free variational approaches and specialize the concepts to the massively-parallel manycore architecture provided by the GPU. Compared to a parallel and optimized CPU implementation, this allows us to achieve an average speedup of 32.53 on 986 real-world CT thorax-abdomen follow-up scans. At a resolution of approximately $256^3$ voxels, the average runtime is 1.99 seconds for the full registration. On the publicly available DIR-lab benchmark, our method ranks third with respect to average landmark error at an average runtime of 0.32 seconds.