Department of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital and Institute. Sichuan Cancer Center, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China.
School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China.
Sci Data. 2024 Oct 4;11(1):1085. doi: 10.1038/s41597-024-03890-0.
The deep learning (DL)-based prediction of accurate lymph node (LN) clinical target volumes (CTVs) for nasopharyngeal carcinoma (NPC) radiotherapy (RT) remains challenging. One of the main reasons is the variability of contours despite standardization processes by expert guidelines in combination with scarce data sharing in the community. Therefore, we retrospectively generated a 262-subjects dataset from four centers to develop the DL models for LN CTVs delineation. This dataset included 440 computed tomography images from different scanning phases, disease stages and treatment strategies. Three clinical expert boards, each comprising two experts (totalling six experts), manually delineated six basic LN CTVs on separate cohorts as the ground truth according to LN involvement and clinical requirements. Several state-of-the-art segmentation algorithms were evaluated on this benchmark, showing promising results for LN CTV segmentation. In conclusion, this work built a multicenter LN CTV segmentation dataset, which may be the first dataset for automatic LN CTV delineation development and evaluation, serving as a benchmark for future research.
深度学习（DL）在预测鼻咽癌（NPC）放疗的准确淋巴结（LN）临床靶区（CTV）方面仍然具有挑战性。其中一个主要原因是，尽管有专家指南的标准化流程以及社区内数据共享的缺乏，但轮廓的可变性仍然存在。因此，我们从四个中心回顾性地生成了一个包含 262 个病例的数据集，用于开发 LNCTV 勾画的 DL 模型。该数据集包括来自不同扫描阶段、疾病阶段和治疗策略的 440 张 CT 图像。三个临床专家委员会，每个委员会由两名专家组成（共计 6 名专家），根据 LN 的受累情况和临床要求，在单独的队列上对六个基本 LNCTV 进行了手动勾画，作为金标准。在这个基准上评估了几种最先进的分割算法，它们在 LNCTV 分割方面显示出了很有前景的结果。总之，这项工作构建了一个多中心的 LNCTV 分割数据集，这可能是第一个用于自动 LNCTV 勾画开发和评估的数据集，可为未来的研究提供基准。
