[论文解读] Towards an Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images

Eduardo Luz, Pedro Silva+2 more|arXiv (Cornell University)|Apr 12, 2020

COVID-19 diagnosis using AI被引用 37

一句话总结

本文提出了一种基于 EfficientNet 架构的高效深度学习模型，并采用分层分类器检测胸部 X 光片中的 COVID-19。该模型在使用比竞争模型少 5 至 30 倍参数的情况下，实现了 93.9% 的总体准确率、96.8% 的敏感度以及 100% 的阳性预测值，显著降低了计算成本。

ABSTRACT

Confronting the pandemic of COVID-19, is nowadays one of the most prominent challenges of the human species. A key factor in slowing down the virus propagation is the rapid diagnosis and isolation of infected patients. The standard method for COVID-19 identification, the Reverse transcription polymerase chain reaction method, is time-consuming and in short supply due to the pandemic. Thus, researchers have been looking for alternative screening methods and deep learning applied to chest X-rays of patients has been showing promising results. Despite their success, the computational cost of these methods remains high, which imposes difficulties to their accessibility and availability. Thus, the main goal of this work is to propose an accurate yet efficient method in terms of memory and processing time for the problem of COVID-19 screening in chest X-rays. Methods: To achieve the defined objective we exploit and extend the EfficientNet family of deep artificial neural networks which are known for their high accuracy and low footprints in other applications. We also exploit the underlying taxonomy of the problem with a hierarchical classifier. A dataset of 13,569 X-ray images divided into healthy, non-COVID-19 pneumonia, and COVID-19 patients is used to train the proposed approaches and other 5 competing architectures. Finally, 231 images of the three classes were used to assess the quality of the methods. Results: The results show that the proposed approach was able to produce a high-quality model, with an overall accuracy of 93.9%, COVID-19, sensitivity of 96.8% and positive prediction of 100%, while having from 5 to 30 times fewer parameters than other than the other tested architectures. Larger and more heterogeneous databases are still needed for validation before claiming that deep learning can assist physicians in the task of detecting COVID-19 in X-ray images.

研究动机与目标

• 应对 RT-PCR 检测方法的局限性所带来的快速且可及的 COVID-19 筛查的迫切需求。
• 降低现有基于 X 光片的 COVID-19 检测深度学习模型的高计算成本，以提高可及性。
• 开发一种在保持高准确率的同时，最小化内存和处理时间需求的模型。
• 在包含 13,569 张 X 光片的多样化数据集上验证模型，分为三类：健康、非 COVID-19 肺炎和 COVID-19。
• 探索分层分类在多类别医学影像分析中提升模型效率和性能的潜力。

提出的方法

• 针对胸部 X 光片中的 COVID-19 检测，适配并扩展了以高准确率和低计算开销著称的 EfficientNet 系列深度神经网络。
• 实施分层分类器，将分类任务划分为多个层级，以提高效率和决策清晰度。
• 在包含 13,569 张标记为健康、非 COVID-19 肺炎或 COVID-19 的 X 光片数据集上训练模型。
• 在包含 231 张图像的独立测试集上评估性能，以确保模型的鲁棒性和泛化能力。
• 将所提模型的性能和参数量与另外五种深度学习架构进行对比。
• 通过使用在 ImageNet 上预训练的权重初始化模型，利用迁移学习原理以加速收敛并提升性能。

实验结果

研究问题

• RQ1 基于 EfficientNet 的模型是否能在保持低计算成本的同时，实现对胸部 X 光片中 COVID-19 检测的高诊断准确率？
• RQ2 分层分类在多类别 X 光片分析中如何提升 COVID-19 检测的效率和性能？
• RQ3 与现有深度学习架构相比，所提模型在不牺牲准确率的前提下，参数量减少了多少？
• RQ4 在真实世界测试集中，该模型检测实际 COVID-19 病例的敏感度和阳性预测值分别是多少？
• RQ5 考虑到当前数据集的局限性，该模型的泛化能力如何？未来还需要哪些额外数据以支持更广泛的临床验证？

主要发现

• 所提模型在 231 张 X 光片的测试集上实现了 93.9% 的总体准确率。
• 该模型对 COVID-19 病例表现出 96.8% 的高敏感度，表明其具备强大的真阳性识别能力。
• 阳性预测值达到 100%，意味着在测试集中所有预测为 COVID-19 的病例均被正确识别。
• 该模型的参数量仅为其他五种测试的深度学习架构的 5 到 30 分之一，显著降低了内存和处理需求。
• 尽管性能表现优异，本研究仍承认需要更大且更多样化的数据集以支持更广泛的临床部署。
• EfficientNet 与分层分类的结合在医学影像应用中有效平衡了准确率与效率。