Department of Radiology, Children's Hospital of Soochow University, Suzhou, China.
School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, 88 Keling Road, Suzhou, China.
Br J Radiol. 2022 Jul 1;95(1135):20201189. doi: 10.1259/bjr.20201189. Epub 2022 May 5.
The aim of this study was to establish an automatic classification model for chronic inflammation of the choledoch wall using deep learning with CT images in patients with pancreaticobiliary maljunction (PBM).
CT images were obtained from 76 PBM patients, including 61 cases assigned to the training set and 15 cases assigned to the testing set. The region of interest (ROI) containing the choledochal lesion was extracted and segmented using the UNet++ network. The degree of severity of inflammation in the choledochal wall was initially classified using the ResNeSt network. The final classification result was determined per decision rules. Grad-CAM was used to explain the association between the classification basis of the network and clinical diagnosis.
Segmentation of the lesion on the common bile duct wall was roughly obtained with the UNet++ segmentation model and the average value of Dice coefficient of the segmentation model in the testing set was 0.839 ± 0.150, which was verified through fivefold cross-validation. Inflammation was initially classified with ResNeSt18, which resulted in accuracy = 0.756, sensitivity = 0.611, specificity = 0.852, precision = 0.733, and area under curve (AUC) = 0.711. The final classification sensitivity was 0.8. Grad-CAM revealed similar distribution of inflammation of the choledochal wall and verified the inflammation classification.
By combining the UNet++ network and the ResNeSt network, we achieved automatic classification of chronic inflammation of the choledoch in PBM patients and verified the robustness through cross-validation performed five times. This study provided an important basis for classification of inflammation severity of the choledoch in PBM patients.
We combined the UNet++ network and the ResNeSt network to achieve automatic classification of chronic inflammation of the choledoch in PBM. These results provided an important basis for classification of choledochal inflammation in PBM and for surgical therapy.
本研究旨在利用深度学习技术对胰胆管合流异常（PBM）患者的 CT 图像进行分析，建立胆总管壁慢性炎症的自动分类模型。
纳入 76 例 PBM 患者的 CT 图像，其中 61 例作为训练集，15 例作为测试集。使用 UNet++网络提取并分割包含胆总管病变的感兴趣区（ROI）。采用 ResNeSt 网络初步对胆总管壁炎症严重程度进行分类，根据决策规则确定最终分类结果。使用 Grad-CAM 解释网络分类依据与临床诊断之间的关系。
UNet++分割模型大致获得了胆总管壁病变的分割结果，测试集分割模型的 Dice 系数平均值为 0.839±0.150，通过五折交叉验证得到验证。使用 ResNeSt18 对炎症进行初步分类，准确率=0.756，灵敏度=0.611，特异度=0.852，精确率=0.733，曲线下面积（AUC）=0.711。最终分类的灵敏度为 0.8。Grad-CAM 显示了胆总管壁炎症的相似分布，验证了炎症分类。
通过结合 UNet++网络和 ResNeSt 网络，我们实现了 PBM 患者胆总管慢性炎症的自动分类，并通过五次交叉验证验证了其稳健性。本研究为 PBM 患者胆总管炎症严重程度的分类提供了重要依据。
我们结合 UNet++网络和 ResNeSt 网络，实现了 PBM 患者胆总管慢性炎症的自动分类。这些结果为 PBM 患者胆总管炎症的分类和手术治疗提供了重要依据。
