EUVIMEDEUVIMED entdecken
Crossref

Cascaded‐TOARNet: A cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation

Wu Du, Huimin Guo, Boyang Chen, Ming Cui, Teng Zhang, Deyu Sun, He Ma

Medical Physics · 2024

DOI: 10.1002/mp.16881 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2024. Verfasst von Wu Du und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China. Hauptthemen laut MEDLINE: Organs at Risk, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate and automated segmentation of thoracic organs‐at‐risk (OARs) is critical for radiotherapy treatment planning of thoracic cancers. However, this has remained a challenging task for four major reasons: (1) thoracic OARs have diverse morphologies; (2) thoracic OARs have low contrast with the background; (3) boundaries of thoracic OARs are blurry; (4) class imbalance issue caused by small organs.

Purpose

To overcome the above challenges and achieve accurate and automated segmentation of thoracic OARs on thoracic CT.

Methods

A novel cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation, called Cascaded‐TOARNet. This cascaded framework comprises two stages: localization and segmentation. During the localization stage, TOARNet locates each organ to crop the regions of interest (ROIs). During the segmentation stage, TOARNet accurately segments the ROIs, and the segmentation results are merged into a complete result.

Results

We evaluated our proposed method and other common segmentation methods on two public datasets: the AAPM Thoracic Auto‐Segmentation Challenge dataset and the Segmentation of Thoracic Organs at Risk (SegTHOR) dataset. Our method demonstrated superior performance, achieving a mean Dice score of 92.6% on the SegTHOR dataset and 90.8% on the AAPM dataset.

Conclusions

This segmentation method holds great promise as an essential tool for enhancing the efficiency of thoracic radiotherapy planning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Organs at RiskImage Processing, Computer-AssistedHumansTomography, X-Ray ComputedRadiotherapy Planning, Computer-AssistedThoraxRadiography, ThoracicThoracic Neoplasms

Stichwörter der Autor:innen

deep learningmedical image segmentationorgans‐at‐risk (OARs)

Autor:innen und Institutionen

  • College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China.
  • Gastrointestinal and Urinary and Musculoskeletal Cancer, Cancer Hospital of Dalian University of Technology, Shenyang, Liaoning, China.
  • Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Shenyang, Liaoning, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Du, W., Guo, H., Chen, B., Cui, M., Zhang, T., Sun, D., & Ma, H. (2024). Cascaded‐TOARNet: A cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation. Medical Physics. https://doi.org/10.1002/mp.16881

Vancouver

Du W, Guo H, Chen B, Cui M, Zhang T, Sun D, et al. Cascaded‐TOARNet: A cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation. Medical Physics. 2024. doi:10.1002/mp.16881

BibTeX
@article{Du2024,
  author = {Du, Wu and Guo, Huimin and Chen, Boyang and Cui, Ming and Zhang, Teng and Sun, Deyu and Ma, He},
  title = {Cascaded‐TOARNet: A cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.16881}
}
Kostenlos starten →