arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.01730cs.AR
收藏

面向边缘GPU的多AI模型流水线,用于加速MRI重建与分析

Edge GPU Aware Multiple AI Model Pipeline for Accelerated MRI Reconstruction and Analysis

Department of Computer and Information Engineering, Khalifa University(计算机与信息工程系,哈利法大学)

Ashiyana Abdul Majeed, Mahmoud Meribout, Safa Mohammed Sali

AI总结:

本文针对边缘设备多模型硬件加速研究不足的问题,提出面向边缘GPU的多AI模型流水线,通过引擎调度、层分配与GAN模型微调,在Jetson设备上实现MRI重建诊断近150帧/秒、精度提升5%、性能翻倍的效果。

摘要:

AI的发展极大优化了医学成像流程,让患者诊断速度更快,但针对带硬件加速的多模型系统的优化研究仍十分有限。随着专用边缘设备不断涌现,高效利用其加速器的重要性日益凸显。本文提出一种硬件加速方法,可同时实现从CT图像到MRI(磁共振成像)的重建与诊断。通过调用现代NVIDIA边缘GPU内置的硬件引擎并结合调度技术,系统实现了近150帧每秒的实时吞吐性能。本文研究的硬件引擎包括Jetson AGX Xavier与Jetson AGX Orin两款设备均配备的GPU和DLA(深度学习加速器)。研究对多个AI模型不同层的硬件分配进行了优化,以缩短各硬件引擎之间的空闲等待时间。此外,研究对对应GAN(生成对抗网络)模型的AI模型进行了微调,使其无需回退到GPU引擎执行,同时不损失精度。事实上,经过微调的边缘GPU感知AI模型的精度提升了5%。研究进一步对两个微调后的GPU感知GAN模型进行硬件分配,结果证明:通过在NVIDIA Jetson AGX Xavier与Orin设备上进行合理的任务划分,其性能可达原始模型的两倍。上述结果验证了并行采用硬件感知模型用于医学图像分析与诊断的有效性。

英文摘要:

Advancements in AI have greatly enhanced the medical imaging process, making it quicker to diagnose patients. However, very few have investigated the optimization of a multi-model system with hardware acceleration. As specialized edge devices emerge, the efficient use of their accelerators is becoming increasingly crucial. This paper proposes a hardware-accelerated method for simultaneous reconstruction and diagnosis of \ac{MRI} from \ac{CT} images. Real-time performance of achieving a throughput of nearly 150 frames per second was achieved by leveraging hardware engines available in modern NVIDIA edge GPU, along with scheduling techniques. This includes the GPU and the \ac{DLA} available in both Jetson AGX Xavier and Jetson AGX Orin, which were considered in this paper. The hardware allocation of different layers of the multiple AI models was done in such a way that the ideal time between the hardware engines is reduced. In addition, the AI models corresponding to the \ac{GAN} model were fine-tuned in such a way that no fallback execution into the GPU engine is required without compromising accuracy. Indeed, the accuracy corresponding to the fine-tuned edge GPU-aware AI models exhibited an accuracy enhancement of 5\%. A further hardware allocation of two fine-tuned GPU-aware GAN models proves they can double the performance over the original model, leveraging adequate partitioning on the NVIDIA Jetson AGX Xavier and Orin devices. The results prove the effectiveness of employing hardware-aware models in parallel for medical image analysis and diagnosis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑