融合DenseNet与Swin Transformer提升胸片多标签分类准确率
CheX-DS: Improving Chest X-ray Image Classification with Ensemble Learning Based on DenseNet and Swin Transformer
- 用集成学习结合CNN与Transformer，兼顾局部与全局特征
- 在NIH ChestX-ray14上达到83.76%平均AUC，优于已有方法
- 适合医疗影像分析、长尾分布多标签分类任务的研究者
胸部疾病自动诊断是热门且具挑战性的任务。当前多数方法依赖卷积神经网络（CNN），侧重局部特征而忽略全局信息。近期自注意力机制在计算机视觉中表现优异。本文提出一种名为CheX-DS的模型，用于处理医学胸片中的长尾多标签数据。该模型基于优秀的医学图像CNN模型DenseNet和新兴的Swin Transformer，采用集成深度学习技术融合二者，发挥CNN与Transformer各自优势。其损失函数结合加权二元交叉熵与非对称损失，有效缓解数据不平衡问题。在NIH ChestX-ray14数据集上评估，模型平均AUC达83.76%，显著优于以往研究。
原文摘要 · Abstract (English)
The automatic diagnosis of chest diseases is a popular and challenging task. Most current methods are based on convolutional neural networks (CNNs), which focus on local features while neglecting global features. Recently, self-attention mechanisms have been introduced into the field of computer vision, demonstrating superior performance. Therefore, this paper proposes an effective model, CheX-DS, for classifying long-tail multi-label data in the medical field of chest X-rays. The model is based on the excellent CNN model DenseNet for medical imaging and the newly popular Swin Transformer model, utilizing ensemble deep learning techniques to combine the two models and leverage the advantages of both CNNs and Transformers. The loss function of CheX-DS combines weighted binary cross-entropy loss with asymmetric loss, effectively addressing the issue of data imbalance. The NIH ChestX-ray14 dataset is selected to evaluate the model's effectiveness. The model outperforms previous studies with an excellent average AUC score of 83.76\%, demonstrating its superior performance.
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。