Skip to main content
QUICK REVIEW

[论文解读] Advancing Diagnostic Precision: Leveraging Machine Learning Techniques for Accurate Detection of Covid-19, Pneumonia, and Tuberculosis in Chest X-Ray Images

Aditya Kulkarni, Guruprasad Parasnis|arXiv (Cornell University)|Oct 9, 2023
COVID-19 diagnosis using AIMedicine被引用 3
一句话总结

本文提出了一种新颖的卷积神经网络(CNN),用于通过先进的图像预处理和深度学习技术,对胸部X光片中的新冠肺炎、肺炎和结核病进行多类别检测。该方法在多个公开数据集上实现了最先进性能,AUC得分分别为0.95(新冠肺炎)、0.99(结核病)和0.98(肺炎),优于VGG19、ResNet和DenseNet等迁移学习模型。

ABSTRACT

Lung diseases such as COVID-19, tuberculosis (TB), and pneumonia continue to be serious global health concerns that affect millions of people worldwide. In medical practice, chest X-ray examinations have emerged as the norm for diagnosing diseases, particularly chest infections such as COVID-19. Paramedics and scientists are working intensively to create a reliable and precise approach for early-stage COVID-19 diagnosis in order to save lives. But with a variety of symptoms, medical diagnosis of these disorders poses special difficulties. It is essential to address their identification and timely diagnosis in order to successfully treat and prevent these illnesses. In this research, a multiclass classification approach using state-of-the-art methods for deep learning and image processing is proposed. This method takes into account the robustness and efficiency of the system in order to increase diagnostic precision of chest diseases. A comparison between a brand-new convolution neural network (CNN) and several transfer learning pre-trained models including VGG19, ResNet, DenseNet, EfficientNet, and InceptionNet is recommended. Publicly available and widely used research datasets like Shenzen, Montogomery, the multiclass Kaggle dataset and the NIH dataset were used to rigorously test the model. Recall, precision, F1-score, and Area Under Curve (AUC) score are used to evaluate and compare the performance of the proposed model. An AUC value of 0.95 for COVID-19, 0.99 for TB, and 0.98 for pneumonia is obtained using the proposed network. Recall and precision ratings of 0.95, 0.98, and 0.97, respectively, likewise met high standards.

研究动机与目标

  • 开发一种稳健的多类别深度学习模型,以实现对胸部X光片中新冠肺炎、肺炎和结核病的精确检测。
  • 通过整合直方图均衡化和去噪等先进图像预处理技术,提升诊断精度。
  • 在公开数据集上,对胸部疾病分类任务中,超越现有迁移学习模型(如VGG19、ResNet、DenseNet)的性能表现。
  • 通过在多个数据集上进行严格评估,建立自动化胸部X光分析在临床诊断中的基准。
  • 降低疾病检测中的假阳性和假阴性率,提升在真实医疗应用中的可靠性。

提出的方法

  • 设计了一种自定义卷积神经网络(CNN),采用残差连接和全局平均池化,以增强特征学习和泛化能力。
  • 图像预处理包括去噪、直方图均衡化和图像缩放,以提升输入质量与模型鲁棒性。
  • 该模型在四个公开数据集(深圳、Montgomery、NIH和包含7,395张X光片的多类别Kaggle数据集)上进行训练与评估。
  • 采用相同的评估协议,将所提出的CNN与迁移学习模型(VGG19、ResNet、DenseNet、EfficientNet、InceptionNet)进行对比。
  • 性能通过标准指标进行评估:召回率、精确率、F1得分和曲线下面积(AUC),并确定直方图均衡化为最优预处理步骤。
  • 最终模型采用Softmax分类器实现多类别输出,并通过数据增强技术进行微调,以提升泛化能力。
Figure 1: Data Pre-processing by Augmentation
Figure 1: Data Pre-processing by Augmentation

实验结果

研究问题

  • RQ1所设计的自定义CNN是否能在胸部X光片中对新冠肺炎、肺炎和结核病进行多类别检测时,优于现有的迁移学习模型?
  • RQ2直方图均衡化预处理与其它图像增强技术相比,在提升不同数据集上模型性能方面表现如何?
  • RQ3所提出模型在NIH和多类别Kaggle等基准数据集上的诊断准确率如何?
  • RQ4与传统人工诊断及先前的深度学习方法相比,该模型在减少假阳性和假阴性方面达到何种程度?
  • RQ5该模型在真实临床环境中,能否在不同成像条件和患者群体中实现良好泛化?

主要发现

  • 所提出的CNN在新冠肺炎检测中AUC达到0.95,结核病为0.99,肺炎为0.98,优于所有评估的迁移学习模型。
  • 在新冠肺炎检测中,模型召回率为0.95,精确率为0.98,F1得分为0.97,表明具有高敏感性和特异性。
  • 直方图均衡化被确定为最有效的预处理技术,在所有数据集中显著提升了模型性能。
  • 在多类别Kaggle数据集中,模型AUC达到0.98,表明其在不同疾病类别间具有强大的泛化能力。
  • 与先前研究中ResNet-50(AUC 0.77)和DenseNet-121(AUC 0.76)相比,本模型性能更优,证实其达到最先进水平。
  • 在包含7,395张X光片的多类别测试集中,模型准确率达到99.3%,敏感性为0.99,特异性为0.99,显示出极高的诊断可靠性。
Figure 2: Data Pre-processing by LTP
Figure 2: Data Pre-processing by LTP

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。