Your browser doesn't support javascript.
loading
Improved deep learning for automatic localisation and segmentation of rectal cancer on T2-weighted MRI.
Zhang, Zaixian; Han, Junqi; Ji, Weina; Lou, Henan; Li, Zhiming; Hu, Yabin; Wang, Mingjia; Qi, Baozhu; Liu, Shunli.
Afiliación
  • Zhang Z; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Han J; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Ji W; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Lou H; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Li Z; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Hu Y; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Wang M; College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, China.
  • Qi B; College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, China.
  • Liu S; Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
J Med Radiat Sci ; 2024 Apr 24.
Article en En | MEDLINE | ID: mdl-38654675
ABSTRACT

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.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Med Radiat Sci Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Med Radiat Sci Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Estados Unidos