Analysis of different atlas-based segmentation techniques for parotid glands

From NAMIC
Jump to: navigation, search
Home < Analysis of different atlas-based segmentation techniques for parotid glands


Key Investigators

  • MIT: Christian Wachinger, Matthew Brennan
  • MGH: Karl Fritscher, Greg Sharp

Objective

Our goal is to investigate various segmentation approaches for identifying parotid glands on head and neck CT images. The focus will be on atlas-based methods, which exploit the information from a number of previously labeled images. Several different strategies exist on how to employ this prior information to achieve the segmentation.

Plan

We will try to work out the differences in terms of parameterization and regularization of various atlas-based methods. We will further try to characterize properties of such methods for the segmentation of parotid glands, which show high structural variability. Finally, we would like to investigate, which combination of methods may be promising.

Progress

3 different segmentation approaches based on the usage of multiple atlases [1], statistical appearance models [2] and a method based on using image patches in combination with Gaussian processes [3] have been tested for their suitability to segment the parotid gland.


Available methods:

  • LF = Image-based Registration with Label Fusion
  • SAM = Statistical Appearance Models (label map registration, PCA, etc)
  • PatchClass = Patch classification with Random Forests
  • GP = Gaussian Processes for label refinement


20 test datasets (CTs) of Head-Neck region have been exchanged

The following hybrid approach has already been tested:

  • LF -> SAM


First tests using following pipelines will be carried out:

  • PatchClass -> SAM
  • LF -> GP


Further potential combinations:

  • PatchClass -> SAM -> GP
  • LF -> GP -> SAM

References

  • [1] Peroni M, Methods and Algorithms for Image Guided Adaptive Radio- and Hadron Therapy. PhD Thesis, Politecnico di Milano, 2011
  • [2] Fritscher KD, Gruenerbl A, Schubert R, 3D image segmentation using combined shape-intensity prior models. Journal of Computer Assisted Radiology and Surgery, 2007;1:341–350
  • [3] Wachinger C, Sharp G, Golland P, Contour-Driven Regression for Label Inference in Atlas-Based Segmentation, MICCAI, 2013.