基于便携式医疗设备的快速疾病诊断的卷积神经网络量化研究案例

A Case Study of Quantizing Convolutional Neural Networks for Fast Disease Diagnosis on Portable Medical Devices.

机构信息

School of Computer Science Engineering, Kyungpook National University, Daegu 41566, Korea.

Department of Radiology, Kyungpook National University Chilgok Hospital, Kyungpook National University, Daegu 41404, Korea.

出版信息

Sensors (Basel). 2021 Dec 29;22(1):219. doi: 10.3390/s22010219.

DOI:10.3390/s22010219

PMID:35009760

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8749713/

Abstract

Recently, the amount of attention paid towards convolutional neural networks (CNN) in medical image analysis has rapidly increased since they can analyze and classify images faster and more accurately than human abilities. As a result, CNNs are becoming more popular and play a role as a supplementary assistant for healthcare professionals. Using the CNN on portable medical devices can enable a handy and accurate disease diagnosis. Unfortunately, however, the CNNs require high-performance computing resources as they involve a significant amount of computation to process big data. Thus, they are limited to being used on portable medical devices with limited computing resources. This paper discusses the network quantization techniques that reduce the size of CNN models and enable fast CNN inference with an energy-efficient CNN accelerator integrated into recent mobile processors. With extensive experiments, we show that the quantization technique reduces inference time by 97% on the mobile system integrating a CNN acceleration engine.

摘要

最近，卷积神经网络（CNN）在医学图像分析中的关注度迅速增加，因为它们能够比人类更快、更准确地分析和分类图像。因此，CNN 变得越来越流行，并作为医疗保健专业人员的辅助工具。在便携式医疗设备上使用 CNN 可以实现便捷、准确的疾病诊断。然而，不幸的是，CNN 需要高性能的计算资源，因为它们涉及大量的计算来处理大数据。因此，它们仅限于使用计算资源有限的便携式医疗设备。本文讨论了网络量化技术，该技术可以减小 CNN 模型的大小，并使用集成到最新移动处理器中的节能 CNN 加速器实现快速的 CNN 推断。通过广泛的实验，我们表明，量化技术在集成 CNN 加速引擎的移动系统上可以将推断时间减少 97%。