Wu Zhe, Lu Liming, Xu Cheng, Wang Dong, Zeng Bin, Liu Mujun
Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing 400038, China; Department of Radiation Oncology, Zigong First People's Hospital, Sichuan 643000, China.
Department of Radiotherapy, Tongling People's Hospital, Anhui 244002, China.
Radiother Oncol. 2025 Mar;204:110699. doi: 10.1016/j.radonc.2024.110699. Epub 2024 Dec 27.
Accurate segmentation of the clinical target volume (CTV) is essential to deliver an effective radiation dose to tumor tissues in cervical cancer radiotherapy. Also, although automated CTV segmentation can reduce oncologists' workload, challenges persist due to the microscopic spread of tumor cells undetectable in CT imaging, low-intensity contrast between organs, and inter-observer variability. This study aims to develop and validate a multi-task feature fusion network (MTF-Net) that uses distance-based information to enhance CTV segmentation accuracy.
We developed a dual-branch, end-to-end MTF-Net designed to address the challenges in cervical cancer CTV segmentation. The MTF-Net architecture consists of a shared encoder and two parallel decoders, one generating a distance location information map (D) and the other producing CTV segmentation masks. To enhance segmentation accuracy, we introduced a distance information attention fusion module that integrates features from the Dimg into the CTV segmentation process, thus optimizing target delineation. The datasets for this study were from three centers. Data from two centers were used for model training and internal validation, and that of the third center was used as an independent dataset for external testing. To benchmark performance, we also compared MTF-Net to commercial segmentation software in a clinical setting.
MTF-Net achieved an average dice score of 84.67% on internal and 77.51% on external testing datasets. Compared with commercial software, MTF-Net demonstrated superior performance across several metrics, including Dice score, positive predictive value, and 95% Hausdorff distance, with the exception of sensitivity.
This study indicates that MTF-Net outperforms existing state-of-the-art segmentation methods and commercial software, demonstrating its potential effectiveness for clinical applications in cervical cancer radiotherapy planning.
在宫颈癌放射治疗中，准确分割临床靶区（CTV）对于向肿瘤组织提供有效的辐射剂量至关重要。此外，尽管自动CTV分割可以减轻肿瘤学家的工作量，但由于CT成像中无法检测到的肿瘤细胞的微观扩散、器官之间的低强度对比度以及观察者间的变异性，挑战依然存在。本研究旨在开发并验证一种使用基于距离的信息来提高CTV分割准确性的多任务特征融合网络（MTF-Net）。
我们开发了一种双分支、端到端的MTF-Net，旨在解决宫颈癌CTV分割中的挑战。MTF-Net架构由一个共享编码器和两个并行解码器组成，一个生成距离位置信息图（D），另一个生成CTV分割掩码。为了提高分割准确性，我们引入了一个距离信息注意力融合模块，该模块将来自Dimg的特征整合到CTV分割过程中，从而优化靶区勾画。本研究的数据集来自三个中心。来自两个中心的数据用于模型训练和内部验证，第三个中心的数据用作独立的外部测试数据集。为了评估性能，我们还在临床环境中将MTF-Net与商业分割软件进行了比较。
MTF-Net在内部测试数据集上的平均骰子系数得分为84.67%，在外部测试数据集上为77.51%。与商业软件相比，MTF-Net在包括骰子系数、阳性预测值和95%豪斯多夫距离等多个指标上表现出卓越的性能，但敏感性除外。
本研究表明MTF-Net优于现有的最先进分割方法和商业软件，证明了其在宫颈癌放射治疗计划临床应用中的潜在有效性。
