混合视觉Transformer-生成对抗网络属性中和器用于缓解胸部X光诊断中的偏见
Hybrid Vision Transformer_GAN Attribute Neutralizer for Mitigating Bias in Chest X_Ray Diagnosis
AI总结：
本研究通过替换U-Net卷积编码器为视觉Transformer，减少胸部X光诊断中的性别偏见，同时保持诊断准确性。
摘要：
胸部X光分类器中的偏见经常源于与性别和年龄相关的捷径，导致对少数族裔亚组的系统性误诊。先前的像素空间属性中和器依赖于卷积编码器，在临床可接受的编辑强度下只能减少但无法完全消除这种属性泄漏。本研究评估了在属性中和框架中用视觉Transformer主干替代U-Net卷积编码器是否能减少人口属性泄漏同时保持诊断准确性。在ChestX-ray14数据集上训练了一个数据高效的图像Transformer小（DeiT-S）中和器。其生成的编辑图像在十一级编辑强度下被独立AI裁判评估属性泄漏，并用卷积神经网络（ConvNet）进行疾病预测。在中等编辑强度（alpha=0.5）下，视觉Transformer（ViT）中和器将患者性别识别的面积下曲线（AUC）降至约0.80，大约低于原始框架的卷积U-Net编码器10个百分点，尽管仅训练了半数的epoch。同时，15种发现的宏接收者操作特征面积下曲线（ROC AUC）保持在未编辑基准的五个百分点以内，最差的亚组AUC仍接近0.70。这些结果表明，全局自注意力视觉模型可以在不牺牲临床效用的情况下进一步抑制属性泄漏，表明朝着更公平的胸部X光AI的可行路径。
英文摘要：
Bias in chest X-ray classifiers frequently stems from sex- and age-related shortcuts, leading to systematic underdiagnosis of minority subgroups. Previous pixel-space attribute neutralizers, which rely on convolutional encoders, lessen but do not fully remove this attribute leakage at clinically usable edit strengths. This study evaluates whether substituting the U-Net convolutional encoder with a Vision Transformer backbone in the Attribute-Neutral Framework can reduce demographic attribute leakage while preserving diagnostic accuracy. A data-efficient Image Transformer Small (DeiT-S) neutralizer was trained on the ChestX-ray14 dataset. Its edited images, generated across eleven edit-intensity levels, were evaluated with an independent AI judge for attribute leakage and with a convolutional neural network (ConvNet) for disease prediction. At a moderate edit level (alpha = 0.5), the Vision Transformer (ViT) neutralizer reduces patient sex-recognition area under the curve (AUC) to approximately 0.80, about 10 percentage points below the original framework's convolutional U-Net encoder, despite being trained for only half as many epochs. Meanwhile, macro receiver operating characteristic area under the curve (ROC AUC) across 15 findings stays within five percentage points of the unedited baseline, and the worst-case subgroup AUC remains near 0.70. These results indicate that global self-attention vision models can further suppress attribute leakage without sacrificing clinical utility, suggesting a practical route toward fairer chest X-ray AI.
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。
