Automatic delineation of organ at risk in cervical cancer radiotherapy based on ensemble learning.
10.11817/j.issn.1672-7347.2022.220101
- Author:
Tingting CHENG
1
;
Zijian ZHANG
2
;
Xin YANG
3
;
Shanfu LU
3
;
Dongdong QIAN
3
;
Xianliang WANG
4
;
Hong ZHU
5
Author Information
1. Department of Oncology, Xiangya Hospital, Central South University, Changsha 410008. chengtingting@csu.edu.cn.
2. Department of Oncology, Xiangya Hospital, Central South University, Changsha 410008. wanzzj@csu.edu.cn.
3. Guangzhou Perception Vision Medical Technologies Limited Company, Guangzhou 510530.
4. Department of Radiotherapy Center, Sichuan Cancer Hospital, Chengdu 610041, China.
5. Department of Oncology, Xiangya Hospital, Central South University, Changsha 410008.
- Publication Type:Journal Article
- Keywords:
automatic delineation;
cervical cancer radiotherapy;
deep learning;
ensemble learning;
organs at risk
- MeSH:
Female;
Humans;
Image Processing, Computer-Assisted/methods*;
Machine Learning;
Organs at Risk/radiation effects*;
Radiotherapy Planning, Computer-Assisted/methods*;
Uterine Cervical Neoplasms/radiotherapy*
- From:
Journal of Central South University(Medical Sciences)
2022;47(8):1058-1064
- CountryChina
- Language:English
-
Abstract:
OBJECTIVES:The automatic delineation of organs at risk (OARs) can help doctors make radiotherapy plans efficiently and accurately, and effectively improve the accuracy of radiotherapy and the therapeutic effect. Therefore, this study aims to propose an automatic delineation method for OARs in cervical cancer scenarios of both after-loading and external irradiation. At the same time, the similarity of OARs structure between different scenes is used to improve the segmentation accuracy of OARs in difficult segmentations.
METHODS:Our ensemble model adopted the strategy of ensemble learning. The model obtained from the pre-training based on the after-loading and external irradiation was introduced into the integrated model as a feature extraction module. The data in different scenes were trained alternately, and the personalized features of the OARs within the model and the common features of the OARs between scenes were introduced. Computer tomography (CT) images for 84 cases of after-loading and 46 cases of external irradiation were collected as the train data set. Five-fold cross-validation was adopted to split training sets and test sets. The five-fold average dice similarity coefficient (DSC) served as the figure-of-merit in evaluating the segmentation model.
RESULTS:The DSCs of the OARs (the rectum and bladder in the after-loading images and the bladder in the external irradiation images) were higher than 0.7. Compared with using an independent residual U-net (convolutional networks for biomedical image segmentation) model [residual U-net (Res-Unet)] delineate OARs, the proposed model can effectively improve the segmentation performance of difficult OARs (the sigmoid in the after-loading CT images and the rectum in the external irradiation images), and the DSCs were increased by more than 3%.
CONCLUSIONS:Comparing to the dedicated models, our ensemble model achieves the comparable result in segmentation of OARs for different treatment options in cervical cancer radiotherapy, which may be shorten time for doctors to sketch OARs and improve doctor's work efficiency.
