Automatic contouring of normal tissues with deep learning for preclinical radiation studies

G. Lappas, C.J.A. Wolfs, N. Staut, N.G. Lieuwes, R. Biemans, S.J. van Hoof, L.J. Dubois, F. Verhaegen*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Objective. Delineation of relevant normal tissues is a bottleneck in image-guided precision radiotherapy workflows for small animals. A deep learning (DL) model for automatic contouring using standardized 3D micro cone-beam CT (mu CBCT) volumes as input is proposed, to provide a fully automatic, generalizable method for normal tissue contouring in preclinical studies. Approach. A 3D U-net was trained to contour organs in the head (whole brain, left/right brain hemisphere, left/right eye) and thorax (complete lungs, left/right lung, heart, spinal cord, thorax bone) regions. As an important preprocessing step, Hounsfield units (HUs) were converted to mass density (MD) values, to remove the energy dependency of the mu CBCT scanner and improve generalizability of the DL model. Model performance was evaluated quantitatively by Dice similarity coefficient (DSC), mean surface distance (MSD), 95th percentile Hausdorff distance (HD95p), and center of mass displacement (Delta CoM). For qualitative assessment, DL-generated contours (for 40 and 80 kV images) were scored (0: unacceptable, manual re-contouring needed - 5: no adjustments needed). An uncertainty analysis using Monte Carlo dropout uncertainty was performed for delineation of the heart. Main results. The proposed DL model and accompanying preprocessing method provide high quality contours, with in general median DSC > 0.85, MSD < 0.25 mm, HD95p < 1 mm and Delta CoM < 0.5 mm. The qualitative assessment showed very few contours needed manual adaptations (40 kV: 20/155 contours, 80 kV: 3/155 contours). The uncertainty of the DL model is small (within 2%). Significance. A DL-based model dedicated to preclinical studies has been developed for multi-organ segmentation in two body sites. For the first time, a method independent of image acquisition parameters has been quantitatively evaluated, resulting in sub-millimeter performance, while qualitative assessment demonstrated the high quality of the DL-generated contours. The uncertainty analysis additionally showed that inherent model variability is low.
Original languageEnglish
Article number044001
Number of pages12
JournalPhysics in Medicine and Biology
Volume67
Issue number4
DOIs
Publication statusPublished - 21 Feb 2022

Keywords

  • deep learning
  • artificial intelligence
  • autocontouring
  • normal tissue
  • preclinical
  • AUTO-SEGMENTATION
  • AT-RISK
  • TECHNOLOGY
  • SYSTEM
  • ATLAS
  • MICE

Cite this