Wu Zhe, Wang Dong, Xu Cheng, Peng Shengxian, Deng Lihua, Liu Mujun, Wu Yi
Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), Chongqing, China.
Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, China.
J Appl Clin Med Phys. 2025 Jan;26(1):e14553. doi: 10.1002/acm2.14553. Epub 2024 Oct 14.
To explore the accuracy and feasibility of a proposed deep learning (DL) algorithm for clinical target volume (CTV) delineation in cervical cancer radiotherapy and evaluate whether it can perform well in external cervical cancer and endometrial cancer cases for generalization validation.
A total of 332 patients were enrolled in this study. A state-of-the-art network called ResCANet, which added the cascade multi-scale convolution in the skip connections to eliminate semantic differences between different feature layers based on ResNet-UNet. The atrous spatial pyramid pooling in the deepest feature layer combined the semantic information of different receptive fields without losing information. A total of 236 cervical cancer cases were randomly grouped into 5-fold cross-training (n = 189) and validation (n = 47) cohorts. External validations were performed in a separate cohort of 54 cervical cancer and 42 endometrial cancer cases. The performances of the proposed network were evaluated by dice similarity coefficient (DSC), sensitivity (SEN), positive predictive value (PPV), 95% Hausdorff distance (95HD), and oncologist clinical score when comparing them with manual delineation in validation cohorts.
In internal validation cohorts, the mean DSC, SEN, PPV, 95HD for ResCANet achieved 74.8%, 81.5%, 73.5%, and 10.5 mm. In external independent validation cohorts, ResCANet achieved 73.4%, 72.9%, 75.3%, 12.5 mm for cervical cancer cases and 77.1%, 81.1%, 75.5%, 10.3 mm for endometrial cancer cases, respectively. The clinical assessment score showed that minor and no revisions (delineation time was shortened to within 30 min) accounted for about 85% of all cases in DL-aided automatic delineation.
We demonstrated the problem of model generalizability for DL-based automatic delineation. The proposed network can improve the performance of automatic delineation for cervical cancer and shorten manual delineation time at no expense to quality. The network showed excellent clinical viability, which can also be even generalized for endometrial cancer with excellent performance.
探讨一种用于宫颈癌放疗中临床靶区（CTV）勾画的深度学习（DL）算法的准确性和可行性，并评估其在子宫颈癌和子宫内膜癌病例中的泛化验证性能。
本研究共纳入332例患者。使用一种名为ResCANet的先进网络，该网络在跳跃连接中添加了级联多尺度卷积，以消除基于ResNet-UNet的不同特征层之间的语义差异。最深特征层中的空洞空间金字塔池化在不丢失信息的情况下合并了不同感受野的语义信息。将236例宫颈癌病例随机分为5折交叉训练组（n = 189）和验证组（n = 47）。在由54例宫颈癌和42例子宫内膜癌病例组成的单独队列中进行外部验证。在验证队列中，将所提网络的性能与手动勾画进行比较，通过骰子相似系数（DSC）、灵敏度（SEN）、阳性预测值（PPV）、95%豪斯多夫距离（95HD）和肿瘤学家临床评分进行评估。
在内部验证队列中，ResCANet的平均DSC、SEN、PPV、95HD分别达到74.8%、81.5%、73.5%和10.5毫米。在外部独立验证队列中，对于宫颈癌病例，ResCANet的DSC、SEN、PPV、95HD分别为73.4%、72.9%、75.3%、12.5毫米；对于子宫内膜癌病例，分别为77.1%、81.1%、75.5%、10.3毫米。临床评估评分显示，在深度学习辅助自动勾画中，少量修改和无需修改（勾画时间缩短至30分钟以内）的病例约占所有病例的85%。
我们证明了基于深度学习的自动勾画的模型泛化性问题。所提网络可以提高宫颈癌自动勾画的性能，并在不影响质量的情况下缩短手动勾画时间。该网络显示出优异的临床可行性，甚至在子宫内膜癌中也具有出色的泛化性能。
