arXiv 2404.005492024-03-31eess.IVcs.CV

Pneumonia App：一款利用可解释卷积神经网络（CNN）实现高效儿科肺炎诊断的移动应用

Pneumonia App: a mobile application for efficient pediatric pneumonia diagnosis using explainable convolutional neural networks (CNN)

Zhejiang Key Laboratory of Imaging and Interventional Medicine, Zhejiang Engineering Research Center of Interventional Medicine Engineering and Biotechnology, The Fifth Affiliated Hospital of Wenzhou Medical University（温州医科大学附属第五医院）；Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院清华-伯克利深圳学院）；Institute of Biopharmaceutical and Health Engineering, Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院生物医药与健康工程研究院）；Key Lab for Industrial Biocatalysis, Ministry of Education, Department of Chemical Engineering, Tsinghua University（清华大学化学工程系工业生物催化教育部重点实验室）；State Key Laboratory of Urban Water Resources and Environment, School of Civil & Environmental Engineering, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）土木与环境工程学院城市水资源与水环境国家重点实验室）；Department of Radiology, The University of Hong Kong - Shenzhen Hospital（香港大学深圳医院放射科）

Jiaming Deng, Zhenglin Chen, Minjiang Chen, Lulu Xu, Jiaqi Yang, Zhendong Luo, Peiwu Qin

备注：: 27 Pages,7 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出PneumoniaAPP移动应用，利用在3345张胸部X光图像上训练的可解释CNN实现0-12岁儿童肺炎支原体肺炎的快速检测，测试准确率达88.20%，支原体类别准确率达97.64%，并支持肺部阴影定位以辅助医生诊断。

摘要：

肺炎支原体肺炎（MPP）在儿科医疗中带来了显著的诊断挑战，尤其是在中国等该病高发地区。我们推出了PneumoniaAPP，这是一款利用深度学习技术进行快速MPP检测的移动应用。我们的方法基于卷积神经网络（CNN），该网络在一个包含3345张胸部X光（CXR）图像的综合数据集上训练，其中833张CXR图像显示MPP，并额外使用来自公共数据集的样本进行了扩充。该CNN模型在测试数据集上实现了所有类别88.20%的准确率和0.9218的AUROC，其中支原体类别的准确率达到97.64%。此外，我们将可解释性技术集成到PneumoniaAPP中，以帮助呼吸科医生进行肺部阴影定位。我们的贡献超越了现有研究，针对儿科MPP，重点关注0-12岁年龄组，并优先考虑在移动设备上的部署。这项工作标志着儿科肺炎诊断的重大进步，提供了一种可靠且易用的工具，以减轻医疗环境中的诊断负担。

英文摘要：

Mycoplasma pneumoniae pneumonia (MPP) poses significant diagnostic challenges in pediatric healthcare, especially in regions like China where it's prevalent. We introduce PneumoniaAPP, a mobile application leveraging deep learning techniques for rapid MPP detection. Our approach capitalizes on convolutional neural networks (CNNs) trained on a comprehensive dataset comprising 3345 chest X-ray (CXR) images, which includes 833 CXR images revealing MPP and additionally augmented with samples from a public dataset. The CNN model achieved an accuracy of 88.20% and an AUROC of 0.9218 across all classes, with a specific accuracy of 97.64% for the mycoplasma class, as demonstrated on the testing dataset. Furthermore, we integrated explainability techniques into PneumoniaAPP to aid respiratory physicians in lung opacity localization. Our contribution extends beyond existing research by targeting pediatric MPP, emphasizing the age group of 0-12 years, and prioritizing deployment on mobile devices. This work signifies a significant advancement in pediatric pneumonia diagnosis, offering a reliable and accessible tool to alleviate diagnostic burdens in healthcare settings.

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。