arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.16610cs.CVcs.AI
收藏

AdverX-Ray: 通过频率敏感的对抗性VAE确保X射线完整性

AdverX-Ray: Ensuring X-Ray Integrity Through Frequency-Sensitive Adversarial VAEs

Eindhoven University of Technology(埃因霍温理工大学);Philips IGT(飞利浦医疗影像技术部门)

Francisco Caetano, Christiaan Viviers, Lena Filatova, Peter H. N. de With, Fons van der Sommen

AI总结:

AdverX-Ray通过频率敏感的对抗性VAE检测X射线图像的协变量偏移,提升医学影像质量评估与诊断准确性。

摘要:

确保医学影像的质量和完整性对于维持深度学习基于的计算机辅助诊断和计算机辅助检测(CAD)系统中的诊断准确性至关重要。协变量偏移是由于不同的成像设备或设置导致的数据分布的细微变化,可以严重降低模型性能,类似于对抗性攻击的影响。因此,在使用CAD模型之前,有必要有一个轻量且快速的方法来评估这些图像的质量。AdverX-Ray通过作为图像质量评估层来解决这一需求,旨在有效检测协变量偏移。该对抗性变分自编码器优先考虑判别器的作用,利用生成器的次优输出作为负样本,以微调判别器识别高频伪影的能力。由对抗性网络生成的图像往往表现出严重的高频伪影,引导判别器过度关注这些组件。这使判别器成为这种方法的理想选择。在特定机器型号的X射线图像的拼接上进行训练,AdverX-Ray可以评估扫描是否符合训练分布,或者是否在同一机器上以不同设置捕捉的扫描。与各种OOD检测方法的广泛比较表明,AdverX-Ray显著优于现有技术,仅使用64个随机拼接,就实现了96.2%的平均AUROC。其轻量且快速的架构使其适用于实时应用,提高医学影像系统的可靠性。代码和预训练模型已公开。

英文摘要:

Ensuring the quality and integrity of medical images is crucial for maintaining diagnostic accuracy in deep learning-based Computer-Aided Diagnosis and Computer-Aided Detection (CAD) systems. Covariate shifts are subtle variations in the data distribution caused by different imaging devices or settings and can severely degrade model performance, similar to the effects of adversarial attacks. Therefore, it is vital to have a lightweight and fast method to assess the quality of these images prior to using CAD models. AdverX-Ray addresses this need by serving as an image-quality assessment layer, designed to detect covariate shifts effectively. This Adversarial Variational Autoencoder prioritizes the discriminator's role, using the suboptimal outputs of the generator as negative samples to fine-tune the discriminator's ability to identify high-frequency artifacts. Images generated by adversarial networks often exhibit severe high-frequency artifacts, guiding the discriminator to focus excessively on these components. This makes the discriminator ideal for this approach. Trained on patches from X-ray images of specific machine models, AdverX-Ray can evaluate whether a scan matches the training distribution, or if a scan from the same machine is captured under different settings. Extensive comparisons with various OOD detection methods show that AdverX-Ray significantly outperforms existing techniques, achieving a 96.2% average AUROC using only 64 random patches from an X-ray. Its lightweight and fast architecture makes it suitable for real-time applications, enhancing the reliability of medical imaging systems. The code and pretrained models are publicly available.

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。

↑