False‐positive reduction is one of the most crucial components in an automated lymph nodes (LNs) detection task in volumetric computed tomography (CT) scans, which is a highly sought goal for cancer diagnosis and early treatment. In this article, treating the three‐dimensional (3D) LN detection task as object detection on sequence problem, we propose a novel spatio‐temporal context‐based recurrent visual attention model (STRAM) for the LNs false positive reduction. We firstly extract the deep spatial features maps for two‐dimensional LN patches from pre‐trained Inception‐V3 model. A new Gaussian kernel‐based spatial attention method is then presented to extract the most discriminating spatial features for the corresponding center slices. Additionally, to combine the temporal information between 3D CT slices, we devise a novel “Siamese” mixture density networks which can learn to adaptively focus on the most relevant parts of the CT slices. Considering the lesion areas always locate around the centroid of the 3D CT scans, a hard constraint is imposed on the predicted attention locations with batch normalization technique and the Siamese architecture. The proposed model is a fully differentiable unit that can be optimized end‐to‐end by using stochastic gradient descent. The effectiveness of our method is verified on LN dataset: 388 mediastinal LNs labeled by radiologists in 90 patient CT scans, and 595 abdominal LNs in 86 patient CT scans. Our method demonstrates sensitivities of about 87%/82% at 3 FP/vol. and 93%/89% at 6 FP/vol. for mediastinum and abdomen, respectively, which compares favorably to previous methods.

中文翻译：

---

用于淋巴结检测的基于时空上下文的循环视觉注意模型

减少假阳性是体积计算机断层扫描 (CT) 扫描中自动淋巴结 (LN) 检测任务中最重要的组成部分之一，这是癌症诊断和早期治疗的一个备受追捧的目标。在本文中，将三维 (3D) LN 检测任务视为序列问题上的对象检测，我们提出了一种新的基于时空上下文的循环视觉注意模型 (STRAM)，用于减少 LN 假阳性。我们首先从预训练的 Inception-V3 模型中提取二维 LN 块的深度空间特征图。然后提出了一种新的基于高斯核的空间注意方法来提取相应中心切片的最具辨别力的空间特征。此外，为了结合 3D CT 切片之间的时间信息，我们设计了一种新颖的“连体”混合密度网络，它可以学习自适应地关注 CT 切片中最相关的部分。考虑到病变区域始终位于 3D CT 扫描的质心周围，因此使用批量归一化技术和 Siamese 架构对预测的注意力位置施加了硬约束。所提出的模型是一个完全可微的单元，可以通过使用随机梯度下降进行端到端的优化。我们的方法的有效性在 LN 数据集上得到了验证：放射科医生在 90 次患者 CT 扫描中标记了 388 个纵隔 LN，在 86 次患者 CT 扫描中标记了 595 个腹部 LN。我们的方法在 3 FP/vol 下显示出约 87%/82% 的灵敏度。和 93%/89% 在 6 FP/vol。分别用于纵隔和腹部，与以前的方法相比具有优势。