Deep Learning-Based Segmentation of Head and Neck Organs-at-Risk with Clinical Partially Labeled Data Articles uri icon

publication date

  • November 2022

start page

  • 1

end page

  • 15

issue

  • 11, 1661

volume

  • 24

International Standard Serial Number (ISSN)

  • 1099-4300

abstract

  • Radiotherapy is one of the main treatments for localized head and neck (HN) cancer. To design a personalized treatment with reduced radio-induced toxicity, accurate delineation of organs at risk (OAR) is a crucial step. Manual delineation is time- and labor-consuming, as well as observer-dependent. Deep learning (DL) based segmentation has proven to overcome some of these limitations, but requires large databases of homogeneously contoured image sets for robust training. However, these are not easily obtained from the standard clinical protocols as the OARs delineated may vary depending on the patient¿s tumor site and specific treatment plan. This results in incomplete or partially labeled data. This paper presents a solution to train a robust DL-based automated segmentation tool exploiting a clinical partially labeled dataset. We propose a two-step workflow for OAR segmentation: first, we developed longitudinal OAR-specific 3D segmentation models for pseudo-contour generation, completing the missing contours for some patients; with all OAR available, we trained a multi-class 3D convolutional neural network (nnU-Net) for final OAR segmentation. Results obtained in 44 independent datasets showed superior performance of the proposed methodology for the segmentation of fifteen OARs, with an average Dice score coefficient and surface Dice similarity coefficient of 80.59% and 88.74%. We demonstrated that the model can be straightforwardly integrated into the clinical workflow for standard and adaptive radiotherapy.

subjects

  • Biology and Biomedicine
  • Materials science and engineering
  • Mechanical Engineering

keywords

  • dl; automated segmentation; head and neck radiotherapy; organs-at-risk; partially; labeled; longitudinal data