EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Improved deep learning for automatic localisation and segmentation of rectal cancer on T2‐weighted MRI

Zaixian Zhang, Junqi Han iD, Weina Ji, Henan Lou, Zhiming Li, Yabin Hu, Mingjia Wang, Baozhu Qi, Shunli Liu

Journal of Medical Radiation Sciences · 2024

DOI: 10.1002/jmrs.794 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Radiation Sciences, 2024. Verfasst von Zaixian Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China. Hauptthemen laut MEDLINE: Adenocarcinoma, Convolutional Neural Networks, Magnetic Resonance Imaging, Rectal Neoplasms. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Youth Foundation Project Of the Affiliated Hospital of Qingdao University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The automatic segmentation approaches of rectal cancer from magnetic resonance imaging (MRI) are very valuable to relieve physicians from heavy workloads and enhance working efficiency. This study aimed to compare the segmentation accuracy of a proposed model with the other three models and the inter‐observer consistency.

Methods

A total of 65 patients with rectal cancer who underwent MRI examination were enrolled in our cohort and were randomly divided into a training cohort ( n = 45) and a validation cohort ( n = 20). Two experienced radiologists independently segmented rectal cancer lesions. A novel segmentation model (AttSEResUNet) was trained on T2WI based on ResUNet and attention mechanisms. The segmentation performance of the AttSEResUNet, U‐Net, ResUNet and U‐Net with Attention Gate (AttUNet) was compared, using Dice similarity coefficient (DSC), Hausdorff distance (HD), mean distance to agreement (MDA) and Jaccard index. The segmentation variability of automatic segmentation models and inter‐observer was also evaluated.

Results

The AttSEResUNet with post‐processing showed perfect lesion recognition rate (100%) and false recognition rate (0), and its evaluation metrics outperformed other three models for two independent readers (observer 1: DSC = 0.839 ± 0.112, HD = 9.55 ± 6.68, MDA = 0.556 ± 0.722, Jaccard index = 0.736 ± 0.150; observer 2: DSC = 0.856 ± 0.099, HD = 11.0 ± 10.1, MDA = 0.789 ± 1.07, Jaccard index = 0.673 ± 0.130). The segmentation performance of AttSEResUNet was comparable and similar to manual variability (DSC = 0.857 ± 0.115, HD = 10.0 ± 10.0, MDA = 0.704 ± 1.17, Jaccard index = 0.666 ± 0.139).

Conclusion

Comparing with other three models, the proposed AttSEResUNet model was demonstrated as a more accurate model for contouring the rectal tumours in axial T2WI images, whose variability was similar to that of inter‐observer.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AdenocarcinomaConvolutional Neural NetworksMagnetic Resonance ImagingRectal NeoplasmsImage Processing, Computer-AssistedFemaleHumansMaleMiddle AgedRetrospective StudiesDeep Learning

Stichwörter der Autor:innen

Automatic segmentationconvolutional neural networkdeep learningmagnetic resonance imagingrectal cancer

Autor:innen und Institutionen

  • Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, China.

ORCID-Profile: Junqi Han

Förderung

  • Youth Foundation Project Of the Affiliated Hospital of Qingdao University

Zitieren

APA

Zhang, Z., Han, J., Ji, W., Lou, H., Li, Z., Hu, Y., Wang, M., Qi, B., & Liu, S. (2024). Improved deep learning for automatic localisation and segmentation of rectal cancer on T2‐weighted MRI. Journal of Medical Radiation Sciences. https://doi.org/10.1002/jmrs.794

Vancouver

Zhang Z, Han J, Ji W, Lou H, Li Z, Hu Y, et al. Improved deep learning for automatic localisation and segmentation of rectal cancer on T2‐weighted MRI. Journal of Medical Radiation Sciences. 2024. doi:10.1002/jmrs.794

BibTeX
@article{Zhang2024,
  author = {Zhang, Zaixian and Han, Junqi and Ji, Weina and Lou, Henan and Li, Zhiming and Hu, Yabin and Wang, Mingjia and Qi, Baozhu and Liu, Shunli},
  title = {Improved deep learning for automatic localisation and segmentation of rectal cancer on T2‐weighted MRI},
  journal = {Journal of Medical Radiation Sciences},
  year = {2024},
  doi = {10.1002/jmrs.794}
}
Kostenlos starten →