[论文解读] Synthetic Poisoning Attacks: The Impact of Poisoned MRI Image on U-Net Brain Tumor Segmentation

Tianhao Li, Tianyu Zeng+7 more|ArXiv.org|Feb 6, 2025

Forensic Toxicology and Drug Analysis被引用 4

一句话总结

该论文研究GAN合成的MRI数据比例上升如何污染训练集并降低U-Net脑肿瘤分割性能。

ABSTRACT

Deep learning-based medical image segmentation models, such as U-Net, rely on high-quality annotated datasets to achieve accurate predictions. However, the increasing use of generative models for synthetic data augmentation introduces potential risks, particularly in the absence of rigorous quality control. In this paper, we investigate the impact of synthetic MRI data on the robustness and segmentation accuracy of U-Net models for brain tumor segmentation. Specifically, we generate synthetic T1-contrast-enhanced (T1-Ce) MRI scans using a GAN-based model with a shared encoding-decoding framework and shortest-path regularization. To quantify the effect of synthetic data contamination, we train U-Net models on progressively "poisoned" datasets, where synthetic data proportions range from 16.67% to 83.33%. Experimental results on a real MRI validation set reveal a significant performance degradation as synthetic data increases, with Dice coefficients dropping from 0.8937 (33.33% synthetic) to 0.7474 (83.33% synthetic). Accuracy and sensitivity exhibit similar downward trends, demonstrating the detrimental effect of synthetic data on segmentation robustness. These findings underscore the importance of quality control in synthetic data integration and highlight the risks of unregulated synthetic augmentation in medical image analysis. Our study provides critical insights for the development of more reliable and trustworthy AI-driven medical imaging systems.

研究动机与目标

• 推动对医学影像分割中合成数据的稳健评估。
• 量化合成数据污染如何影响U-Net脑肿瘤分割性能。
• 识别性能显著下降的 poisoning 阈值。
• 强调医学影像中安全可信AI的含义。

提出的方法

• 使用具有共享编码-解码和最短路径正则化的GAN，从成对CT-MRI数据生成T1-Ce MRI图像。
• 通过在指定比例（16.67% 到 83.33%）混合真实与合成图像来创建污染训练数据集。
• 在真实数据上训练基线U-Net，并在每个受污染数据集上训练污染U-Net。
• 在真实MRI验证集上使用Dice、Jaccard、准确度和灵敏度评估模型。

实验结果

研究问题

• RQ1 训练数据中合成数据比例增加对U-Net脑肿瘤分割性能有何影响？
• RQ2 在何种关键比例下性能下降会变得显著？
• RQ3 Dice、Jaccard、准确度和灵敏度是否会随着合成数据污染的增加而一致下降？

主要发现

• 当合成数据比例为33.33%时Dice为0.8937，83.33%时降至0.7474。
• Jaccard和灵敏度在更高的合成数据比例下呈现类似的下降趋势。
• 尽管合成数据增加，准确度保持相对稳定。
• 较低的合成数据比例（≤33.33%）维持相对稳定的性能，而≥50%时性能显著下降。