Prior knowledge of anatomical relationships supports automatic delineation of clinical target volume for cervical cancer.
Authors
Affiliations (6)
Affiliations (6)
- School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, 100083, China.
- Perception Vision Medical Technologies Co. Ltd., Guangzhou, 510530, China.
- The Taihe Hospital of Wannan Medical College, Fuyang, 236000, China.
- iFlytek Medical Science and Technology Co., Ltd., Hefei, 230088, China.
- Perception Vision Medical Technologies Co. Ltd., Guangzhou, 510530, China. [email protected].
- Department of Radiation Oncology, The First Affiliated Hospital of Anhui Medical University, Hefei, 230022, China. [email protected].
Abstract
Deep learning has been used for automatic planning of radiotherapy targets, such as inferring the clinical target volume (CTV) for a given new patient. However, previous deep learning methods mainly focus on predicting CTV from CT images without considering the rich prior knowledge. This limits the usability of such methods and prevents them from being generalized to larger clinical scenarios. We propose an automatic CTV delineation method for cervical cancer based on prior knowledge of anatomical relationships. This prior knowledge involves the anatomical position relationship between Organ-at-risk (OAR) and CTV, and the relationship between CTV and psoas muscle. First, our model proposes a novel feature attention module to integrate the relationship between nearby OARs and CTV to improve segmentation accuracy. Second, we propose a width-driven attention network to incorporate the relative positions of psoas muscle and CTV. The effectiveness of our method is verified by conducting a large number of experiments in private datasets. Compared to the state-of-the-art models, our method has obtained the Dice of 81.33%±6.36% and HD95 of 9.39mm±7.12mm, and ASSD of 2.02mm±0.98mm, which has proved the superiority of our method in cervical cancer CTV delineation. Furthermore, experiments on subgroup analysis and multi-center datasets also verify the generalization of our method. Our study can improve the efficiency of automatic CTV delineation and help the implementation of clinical applications.