Liu Tianyu, Liu Junchi, Ma Yan, He Jiangping, Han Jincang, Ding Xiaoyang, Chen Chin-Tu
Department of Electronic Engineering, Lanzhou University of Finance and Economics, Lanzhou, 730020, China.
Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, 60616, USA.
Med Phys. 2021 Jan;48(1):264-272. doi: 10.1002/mp.14585. Epub 2020 Nov 27.
The accurate segmentation of liver and liver tumors from CT images can assist radiologists in decision-making and treatment planning. The contours of liver and liver tumors are currently obtained by manual labeling, which is time-consuming and subjective. Computer-aided segmentation methods have been widely used in the segmentation of liver and liver tumors. However, due to the diversity of shape, volume, and image intensity, the segmentation is still a difficult task. In this study, we present a Spatial Feature Fusion Convolutional Network (SFF-Net) to automatically segment liver and liver tumors from CT images.
First, we extract side-outputs at each convolutional block in SFF-Net to make full use of multiscale features. Second, skip-connections are added in the down-sampling phase, therefore, the spatial information can be efficiently transferred to later layers. Third, we present feature fusion blocks (FFBs) to merge spatial features and high-level semantic features from early layers and later layers, respectively. Finally, a fully connected 3D conditional random fields (CRFs) is applied to refine the liver and liver tumor segmentation results.
We test our method on the MICCAI 2017 Liver Tumor Segmentation (LiTS) challenge dataset. The Dice Global (DG) score, Dice per case (DC) score, Volume Overlap Error (VOE), Average Symmetric Surface Distance (ASSD), and tumor precision score are calculated to evaluate the liver and liver tumor segmentation accuracies. For the liver segmentation, DG is 0.955; DC is 0.937; VOE is 0.106; and ASSD is 3.678. For the tumor segmentation, DG is 0.746; DC is 0.592; VOE is 0.416; ASSD is 1.585 and the tumor precision score is 0.369.
The SFF-Net learns more spatial information by adding skip-connections and feature fusion blocks. The experiments validate that our method can accurately segment liver and liver tumors from CT images.
从CT图像中准确分割肝脏和肝脏肿瘤能够辅助放射科医生进行决策和治疗规划。目前肝脏和肝脏肿瘤的轮廓是通过手动标注获取的，这既耗时又主观。计算机辅助分割方法已广泛应用于肝脏和肝脏肿瘤的分割。然而，由于形状、体积和图像强度的多样性，分割仍然是一项艰巨的任务。在本研究中，我们提出了一种空间特征融合卷积网络（SFF-Net），用于从CT图像中自动分割肝脏和肝脏肿瘤。
首先，我们在SFF-Net的每个卷积块中提取侧输出，以充分利用多尺度特征。其次，在下采样阶段添加跳跃连接，因此，空间信息可以有效地传递到后续层。第三，我们提出特征融合块（FFB）分别融合来自早期层和后期层的空间特征和高级语义特征。最后，应用全连接的3D条件随机场（CRF）来细化肝脏和肝脏肿瘤的分割结果。
我们在MICCAI 2017肝脏肿瘤分割（LiTS）挑战数据集上测试了我们的方法。计算骰子全局（DG）分数、每个病例的骰子（DC）分数、体积重叠误差（VOE）、平均对称表面距离（ASSD）和肿瘤精确分数，以评估肝脏和肝脏肿瘤的分割准确性。对于肝脏分割，DG为0.955；DC为0.937；VOE为0.106；ASSD为3.678。对于肿瘤分割，DG为0.746；DC为0.592；VOE为0.416；ASSD为1.585，肿瘤精确分数为0.369。
SFF-Net通过添加跳跃连接和特征融合块学习到更多的空间信息。实验验证了我们的方法能够从CT图像中准确分割肝脏和肝脏肿瘤。
