Zheng Hao, Qian Lijun, Qin Yulei, Gu Yun, Yang Jie
Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, 800 Dongchuan RD, Minhang District, Shanghai, 200240, China.
School of Biomedical Engineering, Shanghai Jiao Tong University, 800 Dongchuan RD, Minhang District, Shanghai, 200240, China.
Med Phys. 2020 Nov;47(11):5543-5554. doi: 10.1002/mp.14303. Epub 2020 Oct 15.
Volumetric pancreas segmentation can be used in the diagnosis of pancreatic diseases, the research about diabetes and surgical planning. Since manual delineation is time-consuming and laborious, we develop a deep learning-based framework for automatic pancreas segmentation in three dimensional (3D) medical images.
A two-stage framework is designed for automatic pancreas delineation. In the localization stage, a Square Root Dice loss is developed to handle the trade-off between sensitivity and specificity. In refinement stage, a novel 2.5D slice interaction network with slice correlation module is proposed to capture the non-local cross-slice information at multiple feature levels. Also a self-supervised learning-based pre-training method, slice shuffle, is designed to encourage the inter-slice communication. To further improve the accuracy and robustness, ensemble learning and a recurrent refinement process are adopted in the segmentation flow.
The segmentation technique is validated in a public dataset (NIH Pancreas-CT) with 82 abdominal contrast-enhanced 3D CT scans. Fourfold cross-validation is performed to assess the capability and robustness of our method. The dice similarity coefficient, sensitivity, and specificity of our results are 86.21 ± 4.37%, 87.49 ± 6.38% and 85.11 ± 6.49% respectively, which is the state-of-the-art performance in this dataset.
We proposed an automatic pancreas segmentation framework and validate in an open dataset. It is found that 2.5D network benefits from multi-level slice interaction and suitable self-supervised learning method for pre-training can boost the performance of neural network. This technique could provide new image findings for the routine diagnosis of pancreatic disease.
胰腺体积分割可用于胰腺疾病的诊断、糖尿病研究及手术规划。由于手动勾勒耗时费力，我们开发了一种基于深度学习的框架，用于在三维（3D）医学图像中自动分割胰腺。
设计了一个两阶段框架用于自动勾勒胰腺。在定位阶段，开发了一种平方根骰子损失函数来处理敏感性和特异性之间的权衡。在细化阶段，提出了一种带有切片相关模块的新型2.5D切片交互网络，以在多个特征级别捕获非局部跨切片信息。还设计了一种基于自监督学习的预训练方法——切片洗牌，以促进切片间的交流。为进一步提高准确性和鲁棒性，在分割流程中采用了集成学习和循环细化过程。
在一个包含82例腹部增强3D CT扫描的公共数据集（NIH胰腺-CT）中对分割技术进行了验证。进行了四折交叉验证以评估我们方法的能力和鲁棒性。我们结果的骰子相似系数、敏感性和特异性分别为86.21±4.37%、87.49±6.38%和85.11±6.49%，这是该数据集中的最优性能。
我们提出了一个自动胰腺分割框架并在一个开放数据集中进行了验证。发现2.5D网络受益于多级切片交互，合适的自监督学习预训练方法可以提高神经网络的性能。该技术可为胰腺疾病的常规诊断提供新的影像发现。
