Deng Xiu-Wen, Zhao Hong-Mei, Jia Le-Cheng, Li Jin-Na, Wei Zi-Quan, Yang Hang, Qu Ang, Jiang Wei-Juan, Lei Run-Hong, Sun Hai-Tao, Wang Jun-Jie, Jiang Ping
Department of Radiation Oncology, Peking University Third Hospital, Beijing, China.
Department of General Surgery, Peking University Third Hospital, Beijing, China.
Int J Radiat Oncol Biol Phys. 2025 Apr 1;121(5):1361-1371. doi: 10.1016/j.ijrobp.2024.11.104. Epub 2024 Dec 10.
This study aimed to design and evaluate a prior-knowledge-guided U-Net (PK-UNet) for automatic clinical target volume (CTV) segmentation in postmastectomy radiation therapy for breast cancer.
A total of 102 computed tomography (CT) scans from breast cancer patients who underwent postmastectomy were retrospectively collected. Of these, 80 scans were used for training with 5-fold cross-validation, and 22 scans for independent testing. The CTV included the chest wall, supraclavicular region, and axillary group III. The proposed PK-UNet method employs a 2-stage auto-segmentation process. Initially, the localization network categorizes CT slices based on the anatomic information of the CTV and generates prior knowledge labels. These outputs, along with the CT images, were fed into the final segmentation network. Quantitative evaluation was conducted using the mean Dice similarity coefficient (DSC), 95% Hausdorff distance, average surface distance, and surface DSC. A four-level objective scale evaluation was performed by 2 experienced radiation oncologists in a randomized double-blind manner.
Quantitative evaluations revealed that PK-UNet significantly outperformed state-of-the-art segmentation methods (P < .01), with a mean DSC of 0.90 ± 0.02 and a 95% Hausdorff distance of 2.82 ± 1.29 mm. The mean average surface distance of PK-UNet was 0.91 ± 0.22 mm and the surface DSC was 0.84 ± 0.07, significantly surpassing the performance of AdwU-Net (P < .01) and showing comparable results to other models. Clinical evaluation confirmed the efficacy of PK-UNet, with 81.8% of the predicted contours being acceptable for clinical application. The advantages of the auto-segmentation capability of PK-UNet were most evident in the superior and inferior slices and slices with discontinuities at the junctions of different subregions. The average manual correction time was reduced to 1.02 min, compared with 18.20 min for manual contouring leading to a 94.4% reduction in working time.
This study introduced the pioneering integration of prior medical knowledge into a deep learning framework for postmastectomy radiation therapy. This strategy addresses the challenges of CTV segmentation in postmastectomy radiation therapy and improves clinical workflow efficiency.
本研究旨在设计并评估一种基于先验知识引导的U-Net（PK-UNet），用于乳腺癌乳房切除术后放射治疗中自动临床靶区（CTV）分割。
回顾性收集了102例接受乳房切除术后的乳腺癌患者的计算机断层扫描（CT）图像。其中，80例扫描图像用于5折交叉验证训练，22例扫描图像用于独立测试。CTV包括胸壁、锁骨上区域和腋窝Ⅲ组。所提出的PK-UNet方法采用两阶段自动分割过程。首先，定位网络根据CTV的解剖信息对CT切片进行分类，并生成先验知识标签。这些输出结果与CT图像一起被输入到最终的分割网络中。使用平均Dice相似系数（DSC）、95% Hausdorff距离、平均表面距离和表面DSC进行定量评估。由2名经验丰富的放射肿瘤学家以随机双盲方式进行四级目标尺度评估。
定量评估显示，PK-UNet显著优于现有最先进的分割方法（P < 0.01），平均DSC为0.90±0.02，95% Hausdorff距离为2.82±1.29 mm。PK-UNet的平均平均表面距离为0.91±0.22 mm，表面DSC为0.84±0.07，显著超过AdwU-Net的性能（P < 0.01），与其他模型的结果相当。临床评估证实了PK-UNet的有效性，81.8%的预测轮廓可用于临床应用。PK-UNet自动分割能力的优势在上下切片以及不同子区域交界处有间断的切片中最为明显。平均手动校正时间减少到1.02分钟，而手动勾勒轮廓的时间为18.20分钟，工作时间减少了94.4%。
本研究率先将先验医学知识整合到深度学习框架中用于乳房切除术后放射治疗。该策略解决了乳房切除术后放射治疗中CTV分割的挑战，提高了临床工作流程效率。
