External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation With Limited Data.
External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation With Limited Data.
复制标题
DOI：
10.1109/tmi.2021.3139637
复制
发表时间：
2022-06
影响因子：
10.6
通讯作者：
中科院分区：
文献类型：
--
作者：
脾脏是腹部钝性创伤中最常受损的实体器官之一。基于多期计算机断层扫描（CT）开发的脾脏血管损伤自动分割系统能够增强严重程度分级，从而改善临床决策支持和结果预测。然而，由于以下原因，脾脏血管损伤的准确分割具有挑战性：1）脾脏血管损伤在形状、质地、大小和整体外观上可能差异很大；2）数据采集是一个复杂且昂贵的过程，需要数据科学家和放射科医生付出大量努力，这通常使得大规模标注良好的数据难以获取。
鉴于这些挑战，我们在此设计了一种用于多期脾脏血管损伤分割的新框架，特别是在数据有限的情况下。一方面，我们提议利用外部数据挖掘伪脾脏掩模作为空间注意力（称为外部注意力），以指导脾脏血管损伤的分割。另一方面，我们开发了一个合成期增强模块，该模块基于生成对抗网络，通过充分利用不同期之间的关系来扩充内部数据。通过在训练过程中联合施加外部注意力并扩充内部数据表示，我们提出的方法优于其他竞争方法，并且在平均骰子相似系数（DSC）方面比流行的DeepLab - v3 +基线显著提高了7%以上，这证实了其有效性。
The spleen is one of the most commonly injured solid organs in blunt abdominal trauma. The development of automatic segmentation systems from multi-phase CT for splenic vascular injury can augment severity grading for improving clinical decision support and outcome prediction. However, accurate segmentation of splenic vascular injury is challenging for the following reasons: 1) Splenic vascular injury can be highly variant in shape, texture, size, and overall appearance; and 2) Data acquisition is a complex and expensive procedure that requires intensive efforts from both data scientists and radiologists, which makes large-scale well-annotated datasets hard to acquire in general. In light of these challenges, we hereby design a novel framework for multi-phase splenic vascular injury segmentation, especially with limited data. On the one hand, we propose to leverage external data to mine pseudo splenic masks as the spatial attention, dubbed external attention, for guiding the segmentation of splenic vascular injury. On the other hand, we develop a synthetic phase augmentation module, which builds upon generative adversarial networks, for populating the internal data by fully leveraging the relation between different phases. By jointly enforcing external attention and populating internal data representation during training, our proposed method outperforms other competing methods and substantially improves the popular DeepLab-v3+ baseline by more than 7% in terms of average DSC, which confirms its effectiveness.