[论文解读] Chest X-ray Image Phase Features for Improved Diagnosis of COVID-19 Using Convolutional Neural Network
本文提出一种多特征卷积神经网络(CNN),通过融合原始与局部相位增强的胸部X光(CXR)图像,以提升新冠肺炎诊断效果。通过增强图像相位特征以突出细微的病理模式,该模型在包含8,851例正常、6,045例肺炎和3,323例新冠肺炎扫描的大型数据集上实现了95.57%的准确率,新冠肺炎检测的F1-score达到99%。
Recently, the outbreak of the novel Coronavirus disease 2019 (COVID-19) pandemic has seriously endangered human health and life. Due to limited availability of test kits, the need for auxiliary diagnostic approach has increased. Recent research has shown radiography of COVID-19 patient, such as CT and X-ray, contains salient information about the COVID-19 virus and could be used as an alternative diagnosis method. Chest X-ray (CXR) due to its faster imaging time, wide availability, low cost and portability gains much attention and becomes very promising. Computational methods with high accuracy and robustness are required for rapid triaging of patients and aiding radiologist in the interpretation of the collected data. In this study, we design a novel multi-feature convolutional neural network (CNN) architecture for multi-class improved classification of COVID-19 from CXR images. CXR images are enhanced using a local phase-based image enhancement method. The enhanced images, together with the original CXR data, are used as an input to our proposed CNN architecture. Using ablation studies, we show the effectiveness of the enhanced images in improving the diagnostic accuracy. We provide quantitative evaluation on two datasets and qualitative results for visual inspection. Quantitative evaluation is performed on data consisting of 8,851 normal (healthy), 6,045 pneumonia, and 3,323 Covid-19 CXR scans. In Dataset-1, our model achieves 95.57\% average accuracy for a three classes classification, 99\% precision, recall, and F1-scores for COVID-19 cases. For Dataset-2, we have obtained 94.44\% average accuracy, and 95\% precision, recall, and F1-scores for detection of COVID-19. Our proposed multi-feature guided CNN achieves improved results compared to single-feature CNN proving the importance of the local phase-based CXR image enhancement (https://github.com/endiqq/Fus-CNNs_COVID-19).
研究动机与目标
- 解决因早期影像特征细微而导致基于CXR的新冠肺炎诊断敏感性和特异性较低的问题。
- 降低放射科医生对CXR扫描影像解读中的组间与组内差异性。
- 通过整合基于局部相位增强的图像特征,提升深度学习模型的诊断准确性。
- 开发一种稳健且可泛化的模型,利用广泛可用、低成本的CXR影像对疑似新冠肺炎病例进行分诊。
- 证明多特征融合(原始+增强CXR)相较于单特征CNN在分类正常、肺炎和新冠肺炎病例方面的优越性。
提出的方法
- 应用基于局部相位的图像增强方法,以增强CXR图像中细微的纹理和结构细节,提升新冠肺炎相关渗出影的可见度。
- 将原始图像和增强图像作为多通道输入送入自定义CNN架构,实现特征层面的融合。
- 实施早期、中期和晚期融合策略,以比较特征交互机制并优化性能。
- 在两个大型公开数据集上进行模型训练:一个包含18,229张扫描图像(8,851例正常、6,045例肺炎、3,323例新冠肺炎),另一个包含10,400张扫描图像。
- 采用5折交叉验证和消融研究,以分离图像增强对诊断性能的贡献。
- 使用标准指标评估模型性能:准确率、精确率、召回率和F1-score,并报告统计显著性。
实验结果
研究问题
- RQ1基于局部相位的图像增强是否能显著提升CNN在将CXR图像分类为正常、肺炎和新冠肺炎类别时的诊断性能?
- RQ2与单特征CNN相比,原始与增强CXR图像的多特征融合在分类准确率和鲁棒性方面表现如何?
- RQ3结合原始与增强CXR输入特征的最优融合策略(早期、中期或晚期)是什么?
- RQ4所提出的方法是否在大型真实世界CXR数据集上实现了新冠肺炎检测的最先进性能?
- RQ5图像增强在多大程度上减少了假阳性结果,并提升了对早期或轻症新冠肺炎病例的检测能力?
主要发现
- 所提出的多特征CNN在数据集-1上实现了95.57%的平均准确率,新冠肺炎类别的精确率、召回率和F1-score均为99%。
- 在数据集-2上,模型实现了94.44%的平均准确率和95%的新冠肺炎F1-score,表明其在不同数据划分下均具有鲁棒性。
- 消融研究证实,图像增强显著提升了诊断准确率,证明了基于相位特征增强的价值。
- 在大多数架构中,晚期融合策略优于早期和中期融合,尤其在EfficientNetB4和Xception模型中,准确率最高达94.01%。
- 采用Xception架构的晚期融合模型在数据集-2上实现了最高的F1-score(94.01%),表明其在精确率与召回率之间具有极佳的平衡。
- 所提出方法在准确率和数据集规模方面均优于现有最先进模型,尤其在更大、更多样化的数据集上表现更优。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。