[论文解读] COV-ELM classifier: An Extreme Learning Machine based identification of COVID-19 using Chest-Ray Images

Sheetal Rajpal, Naveen Kumar+1 more|arXiv (Cornell University)|Jul 16, 2020

COVID-19 diagnosis using AI参考文献 51被引用 8

一句话总结

本文提出COV-ELM，一种基于三阶段极限学习机（ELM）的框架，用于将胸部X光片分类为三类：COVID-19、正常和肺炎。通过利用ELM的快速训练和强泛化能力，该模型实现了0.95的宏平均F1得分和0.94 ± 0.02的敏感度，优于最先进方法，且通过LIME实现临床相关的可解释性，基于超像素归因。

ABSTRACT

Coronaviruses constitute a family of viruses that gives rise to respiratory diseases. As COVID-19 is highly contagious, early diagnosis of COVID-19 is crucial for an effective treatment strategy. However, the RT-PCR test which is considered to be a gold standard in the diagnosis of COVID-19 suffers from a high false-negative rate. Chest X-ray (CXR) image analysis has emerged as a feasible and effective diagnostic technique towards this objective. In this work, we propose the COVID-19 classification problem as a three-class classification problem to distinguish between COVID-19, normal, and pneumonia classes. We propose a three-stage framework, named COV-ELM. Stage one deals with preprocessing and transformation while stage two deals with feature extraction. These extracted features are passed as an input to the ELM at the third stage, resulting in the identification of COVID-19. The choice of ELM in this work has been motivated by its faster convergence, better generalization capability, and shorter training time in comparison to the conventional gradient-based learning algorithms. As bigger and diverse datasets become available, ELM can be quickly retrained as compared to its gradient-based competitor models. The proposed model achieved a macro average F1-score of 0.95 and the overall sensitivity of ${0.94 \pm 0.02} at a 95% confidence interval. When compared to state-of-the-art machine learning algorithms, the COV-ELM is found to outperform its competitors in this three-class classification scenario. Further, LIME has been integrated with the proposed COV-ELM model to generate annotated CXR images. The annotations are based on the superpixels that have contributed to distinguish between the different classes. It was observed that the superpixels correspond to the regions of the human lungs that are clinically observed in COVID-19 and Pneumonia cases.

研究动机与目标

• 通过开发一种基于医学影像的替代诊断方法，解决RT-PCR检测COVID-19时高假阴性率的问题。
• 通过将COVID-19分类视为三分类问题（COVID-19、正常和肺炎），提高诊断准确性。
• 利用极限学习机（ELM）实现比基于梯度的深度学习模型更快的训练速度和更好的泛化能力。
• 集成LIME，通过识别影响分类决策的肺部区域，生成可解释的、具有临床相关性的解释。

提出的方法

• 采用三阶段框架：第一阶段进行预处理和图像转换，第二阶段使用预训练的CNN进行深度特征提取，第三阶段进行ELM分类。
• 利用极限学习机（ELM）实现快速、非迭代的训练，隐藏层权重随机初始化，输出权重通过解析解求解。
• 采用LIME通过识别影响分类的显著超像素，生成局部可解释的、与模型无关的解释。
• 使用一个多样化且公开可用的胸部X光片数据集，对模型在三个不同类别上进行训练和验证。
• 通过单层前馈网络结合S型激活函数，并采用解析最小二乘法求解输出权重，优化ELM模型。
• 使用宏平均F1得分和95%置信区间的敏感度验证模型性能，以确保鲁棒性和可靠性。

实验结果

研究问题

• RQ1 与二分类或多疾病方法相比，三分类分类框架是否能提高胸部X光片中COVID-19检测的准确性？
• RQ2 在基于胸部X光片的COVID-19分类中，极限学习机是否在训练速度和泛化能力方面优于传统的基于梯度的学习算法？
• RQ3 鉴于其快速微调能力，ELM模型在数据有限或需重新训练的情况下，能否保持高性能？
• RQ4 LIME生成的解释是否能突出与临床观察一致的、解剖学上相关的肺部区域，特别是在COVID-19和肺炎病例中？

主要发现

• COV-ELM模型实现了0.95的宏平均F1得分，表明在所有三类中均表现出色。
• 在95%置信区间下，模型敏感度为0.94 ± 0.02，证实其对COVID-19病例具有高检测能力。
• 在胸部X光片的三分类场景中，COV-ELM优于最先进机器学习模型。
• LIME归因突出了与临床相关的肺部区域，与COVID-19和肺炎相关，增强了模型的可解释性。
• 基于ELM的方法相比传统基于梯度的模型，实现了更快的训练速度和更好的泛化能力。
• LIME生成的视觉解释与放射学发现一致，支持临床医生对模型预测结果的信任。