arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.16622eess.IVcs.CV
收藏

使用ViT和CNN架构从胸部X射线图像诊断COVID-19严重程度

Diagnosing COVID-19 Severity from Chest X-Ray Images Using ViT and CNN Architectures

Luis Lara, Lucia Eve Berger, Rajesh Raju

AI总结:

本研究利用ViT和CNN架构,通过迁移学习从胸部X射线图像预测COVID-19严重程度,DenseNet161在分类任务中达80%准确率,ViT在回归任务中误差最低。

摘要:

COVID-19疫情给医疗资源带来了压力,并引发了关于机器学习如何减轻医生负担并有助于诊断的讨论。胸部X射线(CXR)用于诊断COVID-19,但很少有研究从CXR预测患者病情的严重程度。在本研究中,我们通过合并三个来源构建了一个大型COVID严重程度数据集,并研究了使用ImageNet和CXR预训练模型以及视觉变换器(ViTs)的迁移学习在严重程度回归和分类任务中的有效性。一个预训练的DenseNet161模型在三类严重程度预测问题上表现最佳,总体准确率达到80%,在轻度、中度和重度病例上分别达到77.3%、83.9%和70%。ViT在回归任务中表现最好,与放射科医生预测的严重程度评分相比,平均绝对误差为0.5676。该项目的源代码已公开可用。

英文摘要:

The COVID-19 pandemic strained healthcare resources and prompted discussion about how machine learning can alleviate physician burdens and contribute to diagnosis. Chest x-rays (CXRs) are used for diagnosis of COVID-19, but few studies predict the severity of a patient's condition from CXRs. In this study, we produce a large COVID severity dataset by merging three sources and investigate the efficacy of transfer learning using ImageNet- and CXR-pretrained models and vision transformers (ViTs) in both severity regression and classification tasks. A pretrained DenseNet161 model performed the best on the three class severity prediction problem, reaching 80% accuracy overall and 77.3%, 83.9%, and 70% on mild, moderate and severe cases, respectively. The ViT had the best regression results, with a mean absolute error of 0.5676 compared to radiologist-predicted severity scores. The project's source code is publicly available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑