Gil Medical Center, Department of Biomedical Engineering, Gachon University College of Medicine, Incheon 21565, Korea.
HIRA Research Institute, Health Insurance Review & Assessment Service (HIRA), Wonju-si 26465, Korea.
Sensors (Basel). 2021 Dec 30;22(1):245. doi: 10.3390/s22010245.
The automatic segmentation of the pancreatic cyst lesion (PCL) is essential for the automated diagnosis of pancreatic cyst lesions on endoscopic ultrasonography (EUS) images. In this study, we proposed a deep-learning approach for PCL segmentation on EUS images. We employed the Attention U-Net model for automatic PCL segmentation. The Attention U-Net was compared with the Basic U-Net, Residual U-Net, and U-Net++ models. The Attention U-Net showed a better dice similarity coefficient (DSC) and intersection over union (IoU) scores than the other models on the internal test. Although the Basic U-Net showed a higher DSC and IoU scores on the external test than the Attention U-Net, there was no statistically significant difference. On the internal test of the cross-over study, the Attention U-Net showed the highest DSC and IoU scores. However, there was no significant difference between the Attention U-Net and Residual U-Net or between the Attention U-Net and U-Net++. On the external test of the cross-over study, all models showed no significant difference from each other. To the best of our knowledge, this is the first study implementing segmentation of PCL on EUS images using a deep-learning approach. Our experimental results show that a deep-learning approach can be applied successfully for PCL segmentation on EUS images.
胰腺囊性病变（PCL）的自动分割对于内镜超声（EUS）图像上胰腺囊性病变的自动诊断至关重要。在本研究中，我们提出了一种基于深度学习的 EUS 图像 PCL 分割方法。我们采用了 Attention U-Net 模型进行自动 PCL 分割。将 Attention U-Net 与 Basic U-Net、Residual U-Net 和 U-Net++模型进行了比较。在内部测试中，Attention U-Net 的 Dice 相似系数（DSC）和交并比（IoU）得分均优于其他模型。虽然 Basic U-Net 在外部测试中的 DSC 和 IoU 得分高于 Attention U-Net，但差异无统计学意义。在交叉研究的内部测试中，Attention U-Net 的 DSC 和 IoU 得分最高。然而，Attention U-Net 与 Residual U-Net 或 Attention U-Net 与 U-Net++之间没有显著差异。在交叉研究的外部测试中，所有模型之间没有显著差异。据我们所知，这是首次使用深度学习方法对 EUS 图像上的 PCL 进行分割的研究。我们的实验结果表明，深度学习方法可成功应用于 EUS 图像上的 PCL 分割。
