EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network

Runyuan Wang iD, Xingcai Chen, Xiaoqin Zhang, Ping He, Jinfeng Ma, Huilin Cui, Ximei Cao, Yongjian Nian, Ximing Xu, Wei Wu, Yi Wu

Cancer Medicine · 2024

DOI: 10.1002/cam4.70188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancer Medicine, 2024. Verfasst von Runyuan Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Digital Medicine, College of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), C…. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Lymphatic Metastasis, Deep Learning, Lymph Nodes. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University Funded Science and Technology Innovation Capacity Improvement Project, Science-Health Joint Medical Scientific Research Project of Chongqing, National Natural Science Foundation of China under Grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To create a deep‐learning automatic segmentation model for esophageal cancer (EC), metastatic lymph nodes (MLNs) and their adjacent structures using the UperNet Swin network and computed tomography angiography (CTA) images and to improve the effectiveness and precision of EC automatic segmentation and TN stage diagnosis.

Methods

Attention U‐Net, UperNet Swin, UNet++ and UNet were used to train the EC segmentation model to automatically segment the EC, esophagus, pericardium, aorta and MLN from CTA images of 182 patients with postoperative pathologically proven EC. The Dice similarity coefficient (DSC), sensitivity, and positive predictive value (PPV) were used to assess their segmentation effectiveness. The volume of EC was calculated using the segmentation results, and the outcomes and times of automatic and human segmentation were compared. All statistical analyses were completed using SPSS 25.0 software.

Results

Among the four EC autosegmentation models, the UperNet Swin had the best autosegmentation results with a DSC of 0.7820 and the highest values of EC sensitivity and PPV. The esophagus, pericardium, aorta and MLN had DSCs of 0.7298, 0.9664, 0.9496 and 0.5091. The DSCs of the UperNet Swin were 0.6164, 0.7842, 0.8190, and 0.7259 for T1‐4 EC. The volume of EC and its adjacent structures between the ground truth and UperNet Swin model were not significantly different.

Conclusions

The UperNet Swin showed excellent efficiency in autosegmentation and volume measurement of EC, MLN and its adjacent structures in different T stage, which can help to T and N stage diagnose EC and will save clinicians time and energy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Esophageal NeoplasmsLymphatic MetastasisDeep LearningLymph NodesComputed Tomography AngiographyHumansMaleFemaleMiddle AgedAgedAdultImage Processing, Computer-AssistedNeoplasm Staging

Stichwörter der Autor:innen

3D reconstructionautomatic segmentationcomputed tomography angiography (CTA)deep learningesophageal cancer

Autor:innen und Institutionen

  • Department of Digital Medicine, College of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), Chongqing, China.
  • Department of Histology and Embryology, Shanxi Medical University, Taiyuan, China.
  • Department of Cardiac Surgery, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China.
  • Department of General Surgery, Shanxi Province Cancer Hospital/Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences/Cancer Hospital Affiliated to Shanxi Medical University, Taiyuan, China.
  • Ministry of Education Key Laboratory of Child Development and Disorders, National Clinical Research Center for Child Health and Disorders, Children's Hospital of Chongqing Medical University, Chongqing, China.
  • Department of Thoracic Surgery, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China.

ORCID-Profile: Runyuan Wang

Förderung

  • University Funded Science and Technology Innovation Capacity Improvement Project
  • Science-Health Joint Medical Scientific Research Project of Chongqing
  • National Natural Science Foundation of China under Grant
  • Chongqing Science and Technology Talent Project
  • Basic Research (Free Exploration) Project of Shanxi Province
  • Health Project of National Clinical Research Center for Child Health and Disorders (Children's Hospital of Chongqing Medical University, Chongqing, China)

Zitieren

APA

Wang, R., Chen, X., Zhang, X., He, P., Ma, J., Cui, H., Cao, X., Nian, Y., Xu, X., Wu, W., & Wu, Y. (2024). Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network. Cancer Medicine. https://doi.org/10.1002/cam4.70188

Vancouver

Wang R, Chen X, Zhang X, He P, Ma J, Cui H, et al. Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network. Cancer Medicine. 2024. doi:10.1002/cam4.70188

BibTeX
@article{Wang2024,
  author = {Wang, Runyuan and Chen, Xingcai and Zhang, Xiaoqin and He, Ping and Ma, Jinfeng and Cui, Huilin and Cao, Ximei and Nian, Yongjian and Xu, Ximing and Wu, Wei and Wu, Yi},
  title = {Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network},
  journal = {Cancer Medicine},
  year = {2024},
  doi = {10.1002/cam4.70188}
}
Kostenlos starten →