Automatic multi-organ segmentation using learning-based segmentation and level set optimization

Med Image Comput Comput Assist Interv. 2011;14(Pt 3):338-45. doi: 10.1007/978-3-642-23626-6_42.

Abstract

We present a novel generic segmentation system for the fully automatic multi-organ segmentation from CT medical images. Thereby we combine the advantages of learning-based approaches on point cloud-based shape representation, such a speed, robustness, point correspondences, with those of PDE-optimization-based level set approaches, such as high accuracy and the straightforward prevention of segment overlaps. In a benchmark on 10-100 annotated datasets for the liver, the lungs, and the kidneys we show that the proposed system yields segmentation accuracies of 1.17-2.89 mm average surface errors. Thereby the level set segmentation (which is initialized by the learning-based segmentations) contributes with an 20%-40% increase in accuracy.

MeSH terms

  • Algorithms
  • Artificial Intelligence
  • Databases, Factual
  • Humans
  • Imaging, Three-Dimensional / methods*
  • Kidney / pathology
  • Learning
  • Liver / pathology
  • Lung / pathology
  • Models, Anatomic
  • Models, Statistical
  • Pattern Recognition, Automated / methods*
  • Principal Component Analysis
  • Reproducibility of Results
  • Software
  • Tomography, X-Ray Computed / methods*