[论文解读] QReLU and m-QReLU: Two novel quantum activation functions to aid medical diagnostics

Luca Parisi, Daniel Neagu+2 more|arXiv (Cornell University)|Oct 15, 2020

COVID-19 diagnosis using AI参考文献 52被引用 13

一句话总结

本文提出了QReLU和m-QReLU两种新型量子启发式激活函数，旨在解决深度学习中的神经元死亡ReLU问题。通过在经典深度学习框架中引入叠加和纠缠等量子原理，作者证明了这些函数在COVID-19和帕金森病检测的医学影像数据集上，相较于标准ReLU变体，能够实现更高的分类准确率、精确率、召回率和F1分数。

ABSTRACT

The ReLU activation function (AF) has been extensively applied in deep neural networks, in particular Convolutional Neural Networks (CNN), for image classification despite its unresolved dying ReLU problem, which poses challenges to reliable applications. This issue has obvious important implications for critical applications, such as those in healthcare. Recent approaches are just proposing variations of the activation function within the same unresolved dying ReLU challenge. This contribution reports a different research direction by investigating the development of an innovative quantum approach to the ReLU AF that avoids the dying ReLU problem by disruptive design. The Leaky ReLU was leveraged as a baseline on which the two quantum principles of entanglement and superposition were applied to derive the proposed Quantum ReLU (QReLU) and the modified-QReLU (m-QReLU) activation functions. Both QReLU and m-QReLU are implemented and made freely available in TensorFlow and Keras. This original approach is effective and validated extensively in case studies that facilitate the detection of COVID-19 and Parkinson Disease (PD) from medical images. The two novel AFs were evaluated in a two-layered CNN against nine ReLU-based AFs on seven benchmark datasets, including images of spiral drawings taken via graphic tablets from patients with Parkinson Disease and healthy subjects, and point-of-care ultrasound images on the lungs of patients with COVID-19, those with pneumonia and healthy controls. Despite a higher computational cost, results indicated an overall higher classification accuracy, precision, recall and F1-score brought about by either quantum AFs on five of the seven bench-mark datasets, thus demonstrating its potential to be the new benchmark or gold standard AF in CNNs and aid image classification tasks involved in critical applications, such as medical diagnoses of COVID-19 and PD.

研究动机与目标

• 为解决深度神经网络中持续存在的神经元死亡ReLU问题，特别是在关键医学诊断应用中的挑战。
• 探索一种颠覆性的量子启发式激活函数设计方法，突破对ReLU的渐进式改进。
• 开发并验证集成叠加和纠缠等量子原理的新型激活函数，应用于经典深度学习架构中。
• 在真实世界的医学影像数据集上评估所提出函数，以提升COVID-19和帕金森病等疾病早期诊断的性能。
• 确立QReLU和m-QReLU作为卷积神经网络在高风险医学影像分类任务中的潜在新基准。

提出的方法

• 作者通过将叠加和纠缠等量子原理应用于Leaky ReLU激活函数作为基线，推导出QReLU和m-QReLU。
• 量子启发式设计嵌入了模拟量子行为的概率态转移机制，从而实现比经典ReLU变体更强的表征能力。
• 函数在TensorFlow和Keras中实现，可无缝集成到标准深度学习流程中，无需依赖量子硬件。
• 模型架构采用两层卷积神经网络进行评估，激活函数应用于全连接层和卷积层。
• 设计中引入受控参数化以模拟量子态演化，m-QReLU通过引入改进的缩放机制增强稳定性。
• 模型在七个基准数据集上进行训练与评估，包括帕金森病患者绘制的螺旋图以及COVID-19、肺炎和健康对照组的床旁肺部超声图像。

实验结果

研究问题

• RQ1 量子启发式激活函数能否有效缓解深度神经网络中的神经元死亡ReLU问题？
• RQ2 在医学影像分类任务中，QReLU和m-QReLU相较于九种标准ReLU基线函数表现如何？
• RQ3 将叠加和纠缠等量子原理整合到经典激活函数中，是否能带来可测量的诊断准确率提升？
• RQ4 在特定医学影像场景中——特别是COVID-19和帕金森病检测中——这些新型激活函数是否展现出更优性能？
• RQ5 QReLU和m-QReLU能否成为关键医学诊断应用中激活函数的新基准或黄金标准？

主要发现

• 在七个基准数据集中的五个上，QReLU和m-QReLU的分类准确率均高于全部九种ReLU基线函数。
• 所提出的函数在多个医学影像任务中表现出更高的精确率、召回率和F1分数，尤其在从螺旋绘图数据中检测帕金森病方面表现突出。
• 在用于COVID-19检测的床旁肺部超声图像上，QReLU和m-QReLU在F1分数和整体准确率方面均优于标准ReLU变体。
• 尽管计算成本更高，量子启发式激活函数在复杂的真实医学影像数据上始终表现出更优性能。
• 结果表明，QReLU和m-QReLU是医学影像分类领域激活函数新基准的有力候选者。
• 在TensorFlow和Keras中开源实现，促进了其在医疗领域量子启发深度学习研究中的广泛应用与进一步探索。