[论文解读] COVID-19 Detection in Chest X-Ray Images using a New Channel Boosted CNN

Saddam Hussain Khan, Anabia Sohail+1 more|arXiv (Cornell University)|Dec 8, 2020

COVID-19 diagnosis using AI被引用 6

一句话总结

本文提出CB-STM-RENet，一种新型的通道增强卷积神经网络架构，通过分离-转换-合并（STM）模块捕捉区域、边缘和纹理特征，并结合基于迁移学习的辅助通道，提升新冠肺炎胸部X光片的特征学习能力。该方法在具有挑战性的CoV-NonCoV-15k数据集上实现了97%的检测准确率和93%的精确率，优于现有技术。

ABSTRACT

COVID-19 is a highly contagious respiratory infection that has affected a large population across the world and continues with its devastating consequences. It is imperative to detect COVID-19 at the earliest to limit the span of infection. In this work, a new classification technique CB-STM-RENet based on deep Convolutional Neural Network (CNN) and Channel Boosting is proposed for the screening of COVID-19 in chest X-Rays. In this connection, to learn the COVID-19 specific radiographic patterns, a new convolution block based on split-transform-merge (STM) is developed. This new block systematically incorporates region and edge-based operations at each branch to capture the diverse set of features at various levels, especially those related to region homogeneity, textural variations, and boundaries of the infected region. The learning and discrimination capability of the proposed CNN architecture is enhanced by exploiting the Channel Boosting idea that concatenates the auxiliary channels along with the original channels. The auxiliary channels are generated from the pre-trained CNNs using Transfer Learning. The effectiveness of the proposed technique CB-STM-RENet is evaluated on three different datasets of chest X-Rays namely CoV-Healthy-6k, CoV-NonCoV-10k, and CoV-NonCoV-15k. The performance comparison of the proposed CB-STM-RENet with the existing techniques exhibits high performance both in discriminating COVID-19 chest infections from Healthy, as well as, other types of chest infections. CB-STM-RENet provides the highest performance on all these three datasets; especially on the stringent CoV-NonCoV-15k dataset. The good detection rate (97%), and high precision (93%) of the proposed technique suggest that it can be adapted for the diagnosis of COVID-19 infected patients. The test code is available at https://github.com/PRLAB21/COVID-19-Detection-System-using-Chest-X-Ray-Images.

研究动机与目标

• 开发一种深度学习模型，能够准确区分新冠肺炎、健康及非新冠肺炎的胸部X光片。
• 通过一种新型的分离-转换-合并（STM）卷积模块，整合区域、边缘和纹理信息，增强特征表示能力。
• 通过引入基于迁移学习生成的辅助通道（称为“通道增强”）提升模型判别能力。
• 验证模型在多样化胸部X光数据集（包括严格测试集）上的鲁棒性与泛化能力。

提出的方法

• 设计了一种新型的分离-转换-合并（STM）卷积模块，将特征在并行分支中处理，分别聚焦于区域同质性、边缘检测和纹理变化。
• STM模块通过空间变换和特征融合，提取对识别X光片中细微新冠肺炎特征至关重要的多层次表征。
• 通过将预训练CNN（如ResNet）生成的辅助特征图与主网络的特征图拼接，实现通道增强。
• 利用迁移学习生成辅助通道，借助预训练权重在标注数据有限的情况下提升特征学习能力。
• 最终架构CB-STM-RENet在三个公开数据集（CoV-Healthy-6k、CoV-NonCoV-10k和CoV-NonCoV-15k）上进行端到端训练。
• 通过标准指标（包括准确率、精确率和F1值）在所有数据集上评估模型性能。

实验结果

研究问题

• RQ1 具有分离-转换-合并模块的新型CNN架构能否有效学习到新冠肺炎胸部X光片中特有的区域、边缘和纹理特征？
• RQ2 通过迁移学习集成辅助通道是否能显著提升低资源医学影像任务的分类性能？
• RQ3 CB-STM-RENet在多样化、真实世界胸部X光数据集（包括严格测试集）上的表现如何，相较于最先进模型有何差异？
• RQ4 通道增强机制在多大程度上提升了新冠肺炎、非新冠肺炎与健康病例之间的特征判别能力？

主要发现

• CB-STM-RENet在CoV-NonCoV-15k数据集上实现了97%的检测准确率，该数据集因类别间相似度高而被视为严格基准。
• 该模型在CoV-NonCoV-15k数据集上记录了93%的精确率，表明其在阳性病例预测中具有极强的可靠性。
• 性能提升在CoV-NonCoV-15k数据集上最为显著，模型在准确率和精确率方面均优于现有技术。
• 基于迁移学习的辅助通道集成显著增强了模型的特征学习与判别能力。