用Transformer和动态混合增强提升肺部感染严重度预测精度
Lung Infection Severity Prediction Using Transformers with Conditional TransMix Augmentation and Cross-Attention
- 设计双分支Transformer架构，融合跨注意力与特征聚合捕捉多尺度信息
- 在两个公开数据集上准确率超越现有模型，最高达94.3%
- 适合医疗AI研究者及临床辅助诊断系统开发者参考
肺部感染（尤其是肺炎）具有快速恶化风险，尤其在大流行期间。基于医学影像的精准严重度预测对支持及时临床决策、优化患者预后至关重要。本文提出一种适用于胸部CT与X光片的新方法：(i) QCross-Att-PVT，一种结合并行编码器、跨门控注意力机制与特征聚合器的Transformer架构，用于捕获丰富的多尺度特征；(ii) Conditional Online TransMix，一种定制化的数据增强策略，通过训练中生成混合标签图像块来缓解数据集不平衡问题。在两个基准数据集RALO CXR与Per-COVID-19 CT上的评估显示，该方法持续优于多个前沿深度学习模型。结果凸显了数据增强与门控注意力在提升模型鲁棒性与预测准确性中的关键作用。本方法为临床诊断、疾病监测与个性化治疗规划提供了可靠且可适配的工具。代码已开源：https://github.com/bouthainas/QCross-Att-PVT。
原文摘要 · Abstract (English)
Lung infections, particularly pneumonia, pose serious health risks that can escalate rapidly, especially during pandemics. Accurate AI-based severity prediction from medical imaging is essential to support timely clinical decisions and optimize patient outcomes. In this work, we present a novel method applicable to both CT scans and chest X-rays for assessing lung infection severity. Our contributions are twofold: (i) QCross-Att-PVT, a Transformer-based architecture that integrates parallel encoders, a cross-gated attention mechanism, and a feature aggregator to capture rich multi-scale features; and (ii) Conditional Online TransMix, a custom data augmentation strategy designed to address dataset imbalance by generating mixed-label image patches during training. Evaluated on two benchmark datasets, RALO CXR and Per-COVID-19 CT, our method consistently outperforms several state-of-the-art deep learning models. The results emphasize the critical role of data augmentation and gated attention in improving both robustness and predictive accuracy. This approach offers a reliable, adaptable tool to support clinical diagnosis, disease monitoring, and personalized treatment planning. The source code of this work is available at https://github.com/bouthainas/QCross-Att-PVT.
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。