School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
Department of Radiology, Changhai Hospital, The Naval Military Medical University, Shanghai, China.
J Xray Sci Technol. 2023;31(3):655-668. doi: 10.3233/XST-230011.
Automatic segmentation of the pancreas and its tumor region is a prerequisite for computer-aided diagnosis.
In this study, we focus on the segmentation of pancreatic cysts in abdominal computed tomography (CT) scan, which is challenging and has the clinical auxiliary diagnostic significance due to the variability of location and shape of pancreatic cysts.
We propose a convolutional neural network architecture for segmentation of pancreatic cysts, which is called pyramid attention and pooling on convolutional neural network (PAPNet). In PAPNet, we propose a new atrous pyramid attention module to extract high-level features at different scales, and a spatial pyramid pooling module to fuse contextual spatial information, which effectively improves the segmentation performance.
The model was trained and tested using 1,346 CT slice images obtained from 107 patients with the pathologically confirmed pancreatic cancer. The mean dice similarity coefficient (DSC) and mean Jaccard index (JI) achieved using the 5-fold cross-validation method are 84.53% and 75.81%, respectively.
The experimental results demonstrate that the proposed new method in this study enables to achieve effective results of pancreatic cyst segmentation.
胰腺及其肿瘤区域的自动分割是计算机辅助诊断的前提。
本研究专注于腹部计算机断层扫描（CT）扫描中胰腺囊肿的分割，由于胰腺囊肿位置和形状的可变性，胰腺囊肿的分割具有挑战性，且具有临床辅助诊断意义。
我们提出了一种用于胰腺囊肿分割的卷积神经网络架构，称为金字塔注意力和卷积神经网络池化（PAPNet）。在 PAPNet 中，我们提出了一个新的空洞金字塔注意力模块，用于在不同尺度上提取高级特征，以及一个空间金字塔池化模块，用于融合上下文空间信息，这有效地提高了分割性能。
该模型使用来自 107 名经病理证实为胰腺癌患者的 1346 张 CT 切片图像进行了训练和测试。使用 5 倍交叉验证方法获得的平均骰子相似系数（DSC）和平均 Jaccard 指数（JI）分别为 84.53%和 75.81%。
实验结果表明，本研究提出的新方法能够实现胰腺囊肿分割的有效结果。
