TRCGL-Net：基于生成式数据增强和标签共现建模的长尾多标签胸部X光分类框架
TRCGL-Net: A Long-Tailed Multi-Label Chest X-Ray Classification Framework with Generative Data Augmentation and Label Co-Occurrence Modeling
AI总结：
针对胸部X光多标签分类中的长尾分布问题，提出TRCGL-Net，利用可学习文本引导扩散模型生成尾部类样本、通道重加权和类别注意力机制增强特征，以及基于标签共现的图卷积网络建模类别关系，在PadChest数据集上尾部类mAP达0.4904。
摘要：
胸部X光多标签分类是智能医学影像诊断中的核心任务。然而，真实临床数据常呈现极端长尾分布，导致尾部类罕见疾病性能下降。该问题不仅由数据稀缺驱动，还受两个内在因素影响：1) 复杂解剖背景下尾部类病变表征的衰减；2) 头部类在建模标签共现关系中的主导地位。为应对这些挑战，我们提出TRCGL-Net。首先，采用可学习文本引导的条件扩散模型，在疾病语义约束下生成高质量尾部类胸部X光图像样本，提升罕见疾病模式的数据多样性和真实性，同时缓解类别不平衡并保持病理一致性。其次，引入通道重加权机制，通过强调疾病相关特征通道进行特征重校准，从而提升长尾分布下的特征判别性。进一步应用类别感知注意力机制生成类别特定注意力图，使模型能够定位疾病相关区域并关注细粒度病变区域。最后，引入基于标签共现的图卷积网络，建立类别间的信息传播机制。在PadChest数据集上的实验表明，所提方法实现了尾部类mAP为0.4904，总体mAP为0.4408，mAUC为0.8989，优于现有最先进方法。TRCGL-Net有效提升了长尾分布下罕见疾病的识别性能，并减轻了胸部X光多标签分类中极端类别不平衡的影响。
英文摘要：
Chest X-ray multi-label classification is a core task in intelligent medical imaging diagnosis. However, real clinical data often exhibit extreme long-tailed distributions, leading to degraded performance on rare diseases in tail classes. This issue is not only driven by data scarcity but also by two intrinsic factors:1) attenuation of tail-class lesion representations under complex anatomical backgrounds, and 2) dominance of head classes in modeling label co-occurrence relationships. To address these challenges, we propose TRCGL-Net. First, a learnable text-guided conditional diffusion model is employed to generate high-quality tail-class chest X-ray image samples under disease semantic constraints, improving data diversity and realism of rare disease patterns while alleviating class imbalance and preserving pathology-consistent semantics.Second, a channel reweighting mechanism is introduced to perform feature recalibration by emphasizing disease-relevant feature channels, thereby improving feature discriminability under long-tailed distributions.A class-aware attention mechanism is further applied to generate class-specific attention maps, enabling the model to localize disease-relevant regions and focus on fine-grained lesion areas.Finally, a graph convolution network based on label co occurrence is introduced to establish an information propagation mechanism among categories. Experiments on the PadChest dataset show that the proposed method achieves a tail-class mAP of 0.4904, an overall mAP of 0.4408, and an mAUC of 0.8989, outperforming state-of-the-art methods. TRCGL-Net effectively improves recognition performance for rare diseases under long-tailed distributions and mitigates the impact of extreme class imbalance in chest X-ray multi-label classification.
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。
