儿童肺炎从胸部X光片检测：迁移学习与定制CNNs的比较研究
Pediatric Pneumonia Detection from Chest X-Rays:A Comparative Study of Transfer Learning and Custom CNNs
AI总结：
本研究通过比较迁移学习与定制CNNs在儿童肺炎检测中的性能，发现微调迁移模型在准确率、F1分数和AUC上均优于从头训练模型，具有在资源有限地区应用的潜力。
摘要：
肺炎是五岁以下儿童的主要死亡原因，每年有超过70万例死亡。从胸部X光片进行准确诊断受到放射科医生可用性和变异性的限制。本研究比较了从头训练的定制CNNs与迁移学习（ResNet50、DenseNet121、EfficientNet-B0）在儿童肺炎检测中的表现，评估了冻结骨干和微调模式。方法：使用5216张儿童胸部X光片数据集，按80/10/10的比例分为训练、验证和测试集。七个模型被训练和评估，使用准确率、F1分数和AUC进行评估。Grad-CAM可视化提供了可解释性。结果：微调的ResNet50取得了最佳表现：99.43%的准确率，99.61%的F1分数，99.93%的AUC，仅3次误分类。微调模型在平均上比冻结骨干模型高出5.5个百分点。Grad-CAM确认了临床相关的肺部区域引导了预测。结论：迁移学习与微调在儿童肺炎检测中显著优于从头训练的CNNs，显示出几乎完美的准确率。该系统在资源有限的环境中具有强大的筛查潜力。未来的工作应验证这些发现在多中心和成人数据集上的有效性。
英文摘要：
Pneumonia is a leading cause of mortality in children under five, with over 700,000 deaths annually. Accurate diagnosis from chest X-rays is limited by radiologist availability and variability. Objective: This study compares custom CNNs trained from scratch with transfer learning (ResNet50, DenseNet121, EfficientNet-B0) for pediatric pneumonia detection, evaluating frozen-backbone and fine-tuning regimes. Methods: A dataset of 5,216 pediatric chest X-rays was split 80/10/10 for training, validation, and testing. Seven models were trained and assessed using accuracy, F1-score, and AUC. Grad-CAM visualizations provided explainability. Results: Fine-tuned ResNet50 achieved the best performance: 99.43\% accuracy, 99.61\% F1-score, and 99.93\% AUC, with only 3 misclassifications. Fine-tuning outperformed frozen-backbone models by 5.5 percentage points on average. Grad-CAM confirmed clinically relevant lung regions guided predictions. Conclusions: Transfer learning with fine-tuning substantially outperforms CNNs trained from scratch for pediatric pneumonia detection, showing near-perfect accuracy. This system has strong potential as a screening tool in resource-limited settings. Future work should validate these findings on multi-center and adult datasets. Keywords: Pneumonia detection, deep learning, transfer learning, CNN, chest X-ray, pediatric diagnosis, ResNet, DenseNet, EfficientNet, Grad-CAM.
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。
