当前位置: X-MOL 学术IEEE Trans. Med. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks.
IEEE Transactions on Medical Imaging ( IF 10.6 ) Pub Date : 2020-09-23 , DOI: 10.1109/tmi.2020.3026261
Siqi Liu , Arnaud Arindra Adiyoso Setio , Florin C. Ghesu , Eli Gibson , Sasa Grbic , Bogdan Georgescu , Dorin Comaniciu

Detecting malignant pulmonary nodules at an early stage can allow medical interventions which may increase the survival rate of lung cancer patients. Using computer vision techniques to detect nodules can improve the sensitivity and the speed of interpreting chest CT for lung cancer screening. Many studies have used CNNs to detect nodule candidates. Though such approaches have been shown to outperform the conventional image processing based methods regarding the detection accuracy, CNNs are also known to be limited to generalize on under-represented samples in the training set and prone to imperceptible noise perturbations. Such limitations can not be easily addressed by scaling up the dataset or the models. In this work, we propose to add adversarial synthetic nodules and adversarial attack samples to the training data to improve the generalization and the robustness of the lung nodule detection systems. To generate hard examples of nodules from a differentiable nodule synthesizer, we use projected gradient descent (PGD) to search the latent code within a bounded neighbourhood that would generate nodules to decrease the detector response. To make the network more robust to unanticipated noise perturbations, we use PGD to search for noise patterns that can trigger the network to give over-confident mistakes. By evaluating on two different benchmark datasets containing consensus annotations from three radiologists, we show that the proposed techniques can improve the detection performance on real CT data. To understand the limitations of both the conventional networks and the proposed augmented networks, we also perform stress-tests on the false positive reduction networks by feeding different types of artificially produced patches. We show that the augmented networks are more robust to both under-represented nodules as well as resistant to noise perturbations.

中文翻译:

不出意外:通过增强对抗性攻击,为低剂量CT扫描训练鲁棒的肺结节检测。

在早期发现恶性肺结节可以进行医学干预,从而可以提高肺癌患者的生存率。使用计算机视觉技术检测结节可以提高对胸部CT进行肺癌筛查的敏感性和解释速度。许多研究已使用CNN检测候选结节。尽管已显示出这种方法在检测准确度方面优于传统的基于图像处理的方法,但也已知CNN仅限于概括训练集中代表性不足的样本,并且容易产生不可察觉的噪声干扰。通过扩大数据集或模型不容易解决这些限制。在这项工作中 我们建议在训练数据中添加对抗性合成结节和对抗性攻击样本,以提高肺结节检测系统的通用性和鲁棒性。为了从可区分的结节合成器生成结节的硬示例,我们使用投影梯度下降(PGD)搜索有界邻域内的潜在代码,这将产生结节以降低检测器响应。为了使网络对意外的噪声干扰更加鲁棒,我们使用PGD搜索可能触发网络产生过分自信错误的噪声模式。通过评估包含来自三位放射科医生的共识注释的两个不同基准数据集,我们表明所提出的技术可以提高对实际CT数据的检测性能。为了了解常规网络和提议的增强网络的局限性,我们还通过提供不同类型的人工生产的补丁,对假阳性还原网络进行了压力测试。我们显示,增强网络对代表性不足的结节以及对噪声干扰的抵抗力都更强。
更新日期:2020-09-23
down
wechat
bug