Affiliation:
1. Politecnico di Milano, Italy
Abstract
Healthcare is a pivotal research field, and medical imaging is crucial in many applications. Therefore finding new architectural and algorithmic solutions would benefit highly repetitive image processing procedures. One of the most complex tasks in this sense is image registration, which finds the optimal geometric alignment among 3D image stacks and is widely employed in healthcare and robotics. Given the high computational demand of such a procedure, hardware accelerators are promising real-time and energy-efficient solutions, but they are complex to design and integrate within software pipelines. Therefore, this work presents an automation framework called
Hephaestus
that generates efficient 3D image registration pipelines combined with reconfigurable accelerators. Moreover, to alleviate the burden from the software, we codesign software-programmable accelerators that can adapt at run-time to the image volume dimensions.
Hephaestus
features a cross-platform abstraction layer that enables transparently high-performance and embedded systems deployment. However, given the computational complexity of 3D image registration, the embedded devices become a relevant and complex setting being constrained in memory; thus, they require further attention and tailoring of the accelerators and registration application to reach satisfactory results. Therefore, with
Hephaestus
, we also propose an approximation mechanism that enables such devices to perform the 3D image registration and even achieve, in some cases, the accuracy of the high-performance ones. Overall,
Hephaestus
demonstrates 1.85× of maximum speedup, 2.35× of efficiency improvement with respect to the State of the Art, a maximum speedup of 2.51× and 2.76× efficiency improvements against our software, while attaining state-of-the-art accuracy on 3D registrations.
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Software
Reference31 articles.
1. AMD-Xilinx. 2021. PYNQ: Python for Productivity v2.7. https://github.com/Xilinx/PYNQ/tree/image_v2.7
2. Parag Bhosale, Marius Staring, Zaid Al-Ars, and Floris F Berendsen. 2018. GPU-based stochastic-gradient optimization for non-rigid medical image registration in time-critical applications. In Medical Imaging 2018: Image Processing, Vol. 10574. International Society for Optics and Photonics, 105740R.
3. A survey of image registration techniques
4. A Novel VLSI Architecture of CORDIC Based Image Registration
5. Serving DNNs in Real Time at Datacenter Scale with Project Brainwave
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Starlight: A kernel optimizer for GPU processing;Journal of Parallel and Distributed Computing;2024-05