Print Email Facebook Twitter GPU-based stochastic-gradient optimization for non-rigid medical image registration in time-critical applications Title GPU-based stochastic-gradient optimization for non-rigid medical image registration in time-critical applications Author Bhosale, P.S. (Leiden University Medical Center) Staring, M. (TU Delft Pattern Recognition and Bioinformatics; Leiden University Medical Center) Al-Ars, Z. (TU Delft Computer Engineering) Berendsen, Floris F. (Leiden University Medical Center) Contributor Angelini, Elsa D. (editor) Landman, Bennett A. (editor) Date 2018 Abstract Currently, non-rigid image registration algorithms are too computationally intensive to use in time-critical applications. Existing implementations that focus on speed typically address this by either parallelization on GPU-hardware, or by introducing methodically novel techniques into CPU-oriented algorithms. Stochastic gradient descent (SGD) optimization and variations thereof have proven to drastically reduce the computational burden for CPU-based image registration, but have not been successfully applied in GPU hardware due to its stochastic nature. This paper proposes 1) NiftyRegSGD, a SGD optimization for the GPU-based image registration tool NiftyReg, 2) random chunk sampler, a new random sampling strategy that better utilizes the memory bandwidth of GPU hardware. Experiments have been performed on 3D lung CT data of 19 patients, which compared NiftyRegSGD (with and without random chunk sampler) with CPU-based elastix Fast Adaptive SGD (FASGD) and NiftyReg. The registration runtime was 21.5s, 4.4s and 2.8s for elastix-FASGD, NiftyRegSGD without, and NiftyRegSGD with random chunk sampling, respectively, while similar accuracy was obtained. Our method is publicly available at https://github.com/SuperElastix/NiftyRegSGD. Subject GPGPUmemory access optimizationNon-rigid image registrationrandom chunk samplingstochastic gradient descent To reference this document use: http://resolver.tudelft.nl/uuid:611c4637-6acc-4812-b5f1-8cd66530b0fa DOI https://doi.org/10.1117/12.2293098 Publisher SPIE, Bellingham, WA ISBN 9781510616370 Source Medical Imaging 2018: Image Processing Event Medical Imaging 2018: Ultrasonic Imaging and Tomography, 2018-02-10 → 2018-02-15, Houston, United States Series Proceedings of SPIE, 0277-786X, 10574 Part of collection Institutional Repository Document type conference paper Rights © 2018 P.S. Bhosale, M. Staring, Z. Al-Ars, Floris F. Berendsen Files PDF 45239393_105740R.pdf 642.37 KB Close viewer /islandora/object/uuid:611c4637-6acc-4812-b5f1-8cd66530b0fa/datastream/OBJ/view