用深度学习CNN自动识别肺部X光片中的肺炎，提升医疗诊断效率。
Deep Learning CNN for Pneumonia Detection: Advancing Digital Health in Society 5.0
- 基于深度学习的CNN模型，结合图像增强与数据扩增优化特征提取。
- 准确率达91.67%，ROC-AUC为0.96，PR-AUC达0.95，性能优异。
- 适合资源有限地区快速辅助诊断，推动智能医疗发展。
肺炎是全球重大健康问题，尤其在缺乏诊断工具和医疗资源的地区导致高发病率与死亡率。本研究开发了一种基于深度学习的卷积神经网络（CNN），可自动从胸部X光片中检测肺炎。模型在标注数据集上训练，结合归一化、数据增强和图像质量增强等预处理技术，提升鲁棒性与泛化能力。测试结果显示，优化后的模型准确率达91.67%，ROC-AUC为0.96，PR-AUC达0.95，表现出优异的区分能力。结论表明，该CNN模型具备快速、稳定、可靠的诊断潜力，有助于在社会5.0背景下融合人工智能改善医疗服务与公众健康。
原文摘要 · Abstract (English)
Pneumonia is a serious global health problem, contributing to high morbidity and mortality, especially in areas with limited diagnostic tools and healthcare resources. This study develops a Convolutional Neural Network (CNN) based on deep learning to automatically detect pneumonia from chest X-ray images. The method involves training the model on labeled datasets with preprocessing techniques such as normalization, data augmentation, and image quality enhancement to improve robustness and generalization. Testing results show that the optimized model achieves 91.67% accuracy, ROC-AUC of 0.96, and PR-AUC of 0.95, demonstrating strong performance in distinguishing pneumonia from normal images. In conclusion, this CNN model has significant potential as a fast, consistent, and reliable diagnostic aid, supporting Society 5.0 by integrating artificial intelligence to improve healthcare services and public well-being.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。