Clinical application and improvement of a CNN-based autosegmentation model for clinical target volumes in cervical cancer radiotherapy.
Clinical application and improvement of a CNN-based autosegmentation model for clinical target volumes in cervical cancer radiotherapy.
复制标题
DOI：
10.1002/acm2.13440
复制
发表时间：
2021-11
影响因子：
2.1
通讯作者：
Pei X
中科院分区：
文献类型：
--
作者：
Chang Y;Wang Z;Peng Z;Zhou J;Pi Y;Xu XG;Pei X
临床靶区（CTV）自动分割是宫颈癌放射治疗的理想方法。数据异质性和观察者间变异性（IOV）限制了这些方法的临床适应性。提出了自适应方法来提高基于CNN的宫颈癌CTV轮廓自动分割的适应性。这项研究包括400例宫颈癌治疗计划与CTV划定的放射肿瘤学家从三家医院。数据集分为5个子数据集（每个子数据集80例）。数据集1、2和3中的病例分别由医生A、B和C描述。数据集4和5中的病例由多名医生描述。数据集1分为训练（50例），验证（10例）和测试（20例）队列，并用于构建预训练模型。数据集2-5被视为宿主数据集，以评估预训练模型的准确性。在自适应过程中，通过逐渐添加更多从主机数据集中选择的训练案例，对预训练模型进行微调以衡量改进。使用相应的测试用例评估每个主机数据集上自动分割模型的准确性。采用Dice相似系数（DSC）和95%Hausdorff距离（HD_95）评价方法的准确性。在适应性改善之前和之后，主机数据集上的平均DSC值分别为0.818与0.882、0.763与0.810、0.727与0.772和0.679与0.789，分别改善了7.82%、6.16%、6.19%和16.05%。平均HD_95值分别为11.143 mm与6.853 mm、22.402 mm与14.076 mm、28.145 mm与16.437 mm和33.034 mm与16.441 mm，分别改善了37.94%、37.17%、41.60%和50.23%。该方法提高了基于CNN的自动分割模型在应用于主机数据集时的适应性。
Clinical target volume (CTV) autosegmentation for cervical cancer is desirable for radiation therapy. Data heterogeneity and interobserver variability (IOV) limit the clinical adaptability of such methods. The adaptive method is proposed to improve the adaptability of CNN‐based autosegmentation of CTV contours in cervical cancer. This study included 400 cervical cancer treatment planning cases with CTV delineated by radiation oncologists from three hospitals. The datasets were divided into five subdatasets (80 cases each). The cases in datasets 1, 2, and 3 were delineated by physicians A, B, and C, respectively. The cases in datasets 4 and 5 were delineated by multiple physicians. Dataset 1 was divided into training (50 cases), validation (10 cases), and testing (20 cases) cohorts, and they were used to construct the pretrained model. Datasets 2–5 were regarded as host datasets to evaluate the accuracy of the pretrained model. In the adaptive process, the pretrained model was fine‐tuned to measure improvements by gradually adding more training cases selected from the host datasets. The accuracy of the autosegmentation model on each host dataset was evaluated using the corresponding test cases. The Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD_95) were used to evaluate the accuracy. Before and after adaptive improvements, the average DSC values on the host datasets were 0.818 versus 0.882, 0.763 versus 0.810, 0.727 versus 0.772, and 0.679 versus 0.789, which are improvements of 7.82%, 6.16%, 6.19%, and 16.05%, respectively. The average HD_95 values were 11.143 mm versus 6.853 mm, 22.402 mm versus 14.076 mm, 28.145 mm versus 16.437 mm, and 33.034 mm versus 16.441 mm, which are improvements of 37.94%, 37.17%, 41.60%, and 50.23%, respectively. The proposed method improved the adaptability of the CNN‐based autosegmentation model when applied to host datasets.
登录
查看更多内容
影响因子：
3.8
作者：
Peng, Zhao;Fang, Xi;Xu, X. George
通讯作者：
Xu, X. George
影响因子：
3.5
作者：
Qin W;Wu J;Han F;Yuan Y;Zhao W;Ibragimov B;Gu J;Xing L
通讯作者：
Xing L
DOI：
10.1016/j.ijrobp.2009.06.012
发表时间：
2010-07-01
影响因子：
7
作者：
Tsuji, Stuart Y.;Hwang, Andrew;Xia, Ping
通讯作者：
Xia, Ping
使用深度扩张卷积神经网络自动分割直肠癌计划 CT 中的临床靶区和危险器官
影响因子：
3.8
作者：
Men, Kuo;Dai, Jianrong;Li, Yexiong
通讯作者：
Li, Yexiong
MS-Net：利用异构 MRI 数据改善前列腺分割的多站点网络
影响因子：
10.6
作者：
Liu, Quande;Dou, Qi;Heng, Pheng Ann
通讯作者：
Heng, Pheng Ann