Segmentation of multiple Organs‐at‐Risk associated with brain tumors based on coarse‐to‐fine stratified networks
Medical Physics · 2023
DOI: 10.1002/mp.16247 ↗At a glance
Journal article in Medical Physics, 2023. Written by Qianfei Zhao and 7 co-authors. Institution: School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China. Major MEDLINE topics: Neural Networks, Computer, Brain Neoplasms. Cited 5 times so far (Crossref); 38 references. Funded by: National Natural Science Foundation of China, Radiation Oncology Key Laboratory of Sichuan Province.
Abstract (original language)
Background
Delineation of Organs‐at‐Risks (OARs) is an important step in radiotherapy treatment planning. As manual delineation is time‐consuming, labor‐intensive and affected by inter‐ and intra‐observer variability, a robust and efficient automatic segmentation algorithm is highly desirable for improving the efficiency and repeatability of OAR delineation.
Purpose
Automatic segmentation of OARs in medical images is challenged by low contrast, various shapes and imbalanced sizes of different organs. We aim to overcome these challenges and develop a high‐performance method for automatic segmentation of 10 OARs required in radiotherapy planning for brain tumors.
Methods
A novel two‐stage segmentation framework is proposed, where a coarse and simultaneous localization of all the target organs is obtained in the first stage, and a fine segmentation is achieved for each organ, respectively, in the second stage. To deal with organs with various sizes and shapes, a stratified segmentation strategy is proposed, where a High‐ and Low‐Resolution Residual Network (HLRNet) that consists of a multiresolution branch and a high‐resolution branch is introduced to segment medium‐sized organs, and a High‐Resolution Residual Network (HRRNet) is used to segment small organs. In addition, a label fusion strategy is proposed to better deal with symmetric pairs of organs like the left and right cochleas and lacrimal glands.
Results
Our method was validated on the dataset of MICCAI ABCs 2020 challenge for OAR segmentation. It obtained an average Dice of 75.8% for 10 OARs, and significantly outperformed several state‐of‐the‐art models including nnU‐Net (71.6%) and FocusNet (72.4%). Our proposed HLRNet and HRRNet improved the segmentation accuracy for medium‐sized and small organs, respectively. The label fusion strategy led to higher accuracy for symmetric pairs of organs.
Conclusions
Our proposed method is effective for the segmentation of OARs of brain tumors, with a better performance than existing methods, especially on medium‐sized and small organs. It has a potential for improving the efficiency of radiotherapy planning with high segmentation accuracy.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China.
- Shanghai AI Laboratory, Shanghai, China.
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Department of Radiation Oncology, Sichuan Cancer Hospital and Institute, University of Electronic Science and Technology of China, Chengdu, China.
Funding
- National Natural Science Foundation of China
- Radiation Oncology Key Laboratory of Sichuan Province
Cite
APA
Zhao, Q., Wang, G., Lei, W., Fu, H., Qu, Y., Lu, J., Zhang, S., & Zhang, S. (2023). Segmentation of multiple Organs‐at‐Risk associated with brain tumors based on coarse‐to‐fine stratified networks. Medical Physics. https://doi.org/10.1002/mp.16247
Vancouver
Zhao Q, Wang G, Lei W, Fu H, Qu Y, Lu J, et al. Segmentation of multiple Organs‐at‐Risk associated with brain tumors based on coarse‐to‐fine stratified networks. Medical Physics. 2023. doi:10.1002/mp.16247
BibTeX
@article{Zhao2023,
author = {Zhao, Qianfei and Wang, Guotai and Lei, Wenhui and Fu, Hao and Qu, Yijie and Lu, Jiangshan and Zhang, Shichuan and Zhang, Shaoting},
title = {Segmentation of multiple Organs‐at‐Risk associated with brain tumors based on coarse‐to‐fine stratified networks},
journal = {Medical Physics},
year = {2023},
doi = {10.1002/mp.16247}
}
EUVIMED