Abstract
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.
Abstract (translated)
肺炎是五岁以下儿童死亡的主要原因之一，每年导致超过70万例死亡。放射科医生的可用性和诊断的一致性限制了胸部X光片上准确诊断肺炎的能力。本研究旨在比较从零开始训练的自定义卷积神经网络（CNN）与迁移学习方法（包括ResNet50、DenseNet121和EfficientNet-B0）在儿童肺炎检测中的表现，同时评估固定骨干模型和微调策略的效果。 **方法：** 使用包含5,216张儿科胸部X光片的数据集进行研究。数据集按照80%用于训练，10%用于验证，剩余的10%用于测试的比例进行了分割。共训练并评估了七种不同模型（包括三种迁移学习模型及其固定和微调版本），使用准确率、F1分数以及AUC指标进行性能评价，并通过Grad-CAM可视化技术提供了模型预测过程中的解释性。 **结果：** 在所有模型中，经过微调的ResNet50表现最佳，其精确率为99.43%，F1评分为99.61%，AUC值为99.93%，仅出现三次误分类情况。相较于固定骨干模型，使用微调策略平均提高了5.5个百分点的表现。Grad-CAM可视化技术确认了临床相关的肺区域确实指导了预测过程。 **结论：** 与从零开始训练的CNN相比，采用迁移学习并结合微调策略的方法在儿童肺炎检测中表现出显著更优的效果，并达到了近乎完美的精确度。这表明该系统有可能成为资源受限环境中的一种有效的筛查工具。未来的工作应该使用多中心及成人数据集对这些发现进行验证。 **关键词：** 肺炎检测、深度学习、迁移学习、CNN、胸部X光片、儿科诊断、ResNet、DenseNet、EfficientNet、Grad-CAM
URL
https://arxiv.org/abs/2601.00837
