EUVIMEDEUVIMED entdecken
Crossref

Deep learning‐based internal gross target volume definition in 4D CT images of lung cancer patients

Yuanyuan Ma, Jingfang Mao, Xinguo Liu, Zhongying Dai, Hui Zhang, Xinyang Zhang, Qiang Li

Medical Physics · 2023-04 · 50 (4) · 2303-2316

DOI: 10.1002/mp.16106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 25.11.2022. Verfasst von Yuanyuan Ma und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China. Hauptthemen laut MEDLINE: Deep Learning, Lung Neoplasms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: National Natural Science Foundation of China, West Light Foundation of the Chinese Academy of Sciences, Natural Science Foundation of Gansu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Contouring of internal gross target volume (iGTV) is an essential part of treatment planning in radiotherapy to mitigate the impact of intra‐fractional target motion. However, it is usually time‐consuming and easily subjected to intra‐observer and inter‐observer variability. So far, few studies have been explored to directly predict iGTV by deep learning technique, because the iGTV contains not only the gross target volume (GTV) but also the motion information of the GTV.

Purpose

This work was an exploratory study to present a deep learning‐based framework to segment iGTV rapidly and accurately in 4D CT images for lung cancers.

Methods

Five models, including 3D UNet, mmUNet with point‐wise add merging approach (mmUNet‐add), mmUNet with concatenate fusion strategy (mmUNet‐cat), gruUNet with point‐wise add fusion approach (gruUNet‐add), and gruUNet with concatenate method (gruUNet‐cat), were adopted for iGTV segmentation. All the models originated from the 3D UNet network, with multi‐channel multi‐path and convolutional gated recurrent unit (GRU) added in the mmUNet and gruUNet networks, respectively. Seventy patients with lung cancers were collected and 55 cases were randomly selected as the training set, and 15 cases as the testing set. In addition, the segmentation results of the five models were compared with the ground truths qualitatively and quantitatively.

Results

In terms of Dice Similarity Coefficient (DSC), the proposed four networks (mmUNet‐add, mmUNet‐cat, gruUNet‐add, and gruUNet‐cat) increased the DSC score of 3D UNet from 0.6945 to 0.7342, 0.7253, 0.7405, and 0.7365, respectively. However, the differences were not statistically significant ( p > 0.05). After a simple post‐processing to remove the small isolated connected regions, the mean 95th percentile Hausdorff distances (HD_95s) of the 3D UNet, mmUNet‐add, mmUNet‐cat, gruUNet‐add, and gruUNet‐cat networks were 19.70, 15.75, 15.84, 15.61, and 15.83 mm, respectively, corresponding to 25.35, 25.96, 25.11, 28.23, and 24.47 mm before the post‐processing. With regard to runtime, significant elapsed time growths (about 70s and 230s) were observed both in the mmUNet and gruUNet architectures due to the increasing parameters. But the mmUNet structure showed less growth.

Conclusion

Our study demonstrated the ability of the deep learning technique to predict iGTVs directly. With the introduction of multi‐channel multi‐path and convolutional GRU, the segmentation accuracy was improved under certain conditions with a reduced segmentation efficiency and a further research topic when the 3D UNet network would lead to poor performance is elicited. Less efficiency degradation was observed in the mmUNet structure. Besides, the element‐wise add fusing strategy was favorable to increase DSC, whereas HD_95 benefited from the concentrate merging approach. Nevertheless, the segmentation accuracy by deep learning still remains to be improved.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLung NeoplasmsHumansFour-Dimensional Computed TomographyRadiotherapy Planning, Computer-AssistedTumor BurdenImage Processing, Computer-Assisted

Stichwörter der Autor:innen

deep learninginternal gross target volumeintra-fractional target motionlung cancer

Autor:innen und Institutionen

  • Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou, China.
  • Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou, China.
  • Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Gansu Province, Lanzhou, China.
  • Putian Lanhai Nuclear Medicine Research Center, Putian, China.
  • Department of Radiation Oncology, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital, Shanghai, China.
  • Shanghai Key Laboratory of Radiation Oncology, Shanghai, China.

Förderung

  • National Natural Science Foundation of China
  • West Light Foundation of the Chinese Academy of Sciences
  • Natural Science Foundation of Gansu Province

Zitieren

APA

Ma, Y., Mao, J., Liu, X., Dai, Z., Zhang, H., Zhang, X., & Li, Q. (2023). Deep learning‐based internal gross target volume definition in 4D CT images of lung cancer patients. Medical Physics, 50(4), 2303-2316. https://doi.org/10.1002/mp.16106

Vancouver

Ma Y, Mao J, Liu X, Dai Z, Zhang H, Zhang X, et al. Deep learning‐based internal gross target volume definition in 4D CT images of lung cancer patients. Medical Physics. 2023;50(4):2303-2316. doi:10.1002/mp.16106

BibTeX
@article{Ma2023,
  author = {Ma, Yuanyuan and Mao, Jingfang and Liu, Xinguo and Dai, Zhongying and Zhang, Hui and Zhang, Xinyang and Li, Qiang},
  title = {Deep learning‐based internal gross target volume definition in 4D CT images of lung cancer patients},
  journal = {Medical Physics},
  year = {2023},
  volume = {50},
  number = {4},
  pages = {2303--2316},
  doi = {10.1002/mp.16106}
}
Kostenlos starten →