Hu Dingdu, Jian Junming, Li Yongai, Gao Xin
School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China.
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China.
Quant Imaging Med Surg. 2023 Mar 1;13(3):1464-1477. doi: 10.21037/qims-22-494. Epub 2023 Feb 9.
Epithelial ovarian cancer (EOC) segmentation is an indispensable step in assessing the extent of disease and guiding the treatment plan that follows. Currently, manual segmentation is the most commonly used method, despite it being tedious, time-consuming and subject to inter- and intra-observer variability. This study aims to assess the feasibility of deep learning methods in the automatic segmentation of EOC on T2-weighted magnetic resonance images.
A total of 339 EOC patients from eight different clinical centers were enrolled and divided into 4 groups: training set (n=154), validation set (n=25), internal test set (n=50) and external test set (n=110). Six common-used algorithms, including convolutional neural networks (CNNs) (U-Net, DeepLabv3, U-Net++ and PSPNet) and transformers (TransUnet and Swin-Unet), were used to conduct automatic segmentations. The performances of these automatic segmentation methods were evaluated by means of dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), precision and recall.
All the results look promising, which demonstrates the feasibility of using deep learning for EOC segmentation. Overall, CNNs and transformers showed similar performances in both internal and external test sets. Among all the models, U-Net++ performed best with a DSC, HD, ASSD, precision and recall of 0.851, 25.3, 1.75, 0.838, 0.882 and 0.740, 42.5, 4.21, 0.825, 0.725 in internal and external test sets, respectively.
Fully automated segmentation of EOC is possible with deep learning. The segmentation performance is related to the International Federation of Gynecology and Obstetrics (FIGO) stages and histological types of EOC.
上皮性卵巢癌（EOC）分割是评估疾病范围和指导后续治疗方案的不可或缺的步骤。目前，手动分割是最常用的方法，尽管它繁琐、耗时且存在观察者间和观察者内的变异性。本研究旨在评估深度学习方法在T2加权磁共振图像上自动分割EOC的可行性。
共纳入来自八个不同临床中心的339例EOC患者，并分为4组：训练集（n = 154）、验证集（n = 25）、内部测试集（n = 50）和外部测试集（n = 110）。使用六种常用算法，包括卷积神经网络（CNN）（U-Net、DeepLabv3、U-Net++和PSPNet）和变换器（TransUnet和Swin-Unet）进行自动分割。通过骰子相似系数（DSC）、豪斯多夫距离（HD）、平均对称表面距离（ASSD）、精确率和召回率评估这些自动分割方法的性能。
所有结果看起来都很有前景，这证明了使用深度学习进行EOC分割的可行性。总体而言，CNN和变换器在内部和外部测试集中表现出相似的性能。在所有模型中，U-Net++表现最佳，在内部和外部测试集中的DSC、HD、ASSD、精确率和召回率分别为0.851、25.3、1.75、0.838、0.882和0.740、42.5、4.21、0.825、0.725。
使用深度学习可以实现EOC的全自动分割。分割性能与国际妇产科联合会（FIGO）分期和EOC的组织学类型有关。
