Atlas-Based Auto-segmentation of Head and Neck CT Images

Treatment planning for high precision radiotherapy of head and neck (H&N) cancer patients requires accurate delineation of many structures and lymph node regions. Manual contouring is tedious and suffers from large inter- and intra-rater variability. To reduce manual labor, we have developed a fully automated, atlas-based method for H&N CT image segmentation that employs a novel hierarchical atlas registration approach. This registration strategy makes use of object shape information in the atlas to help improve the registration efficiency and robustness while still being able to account for large inter-subject shape differences. Validation results showed that our method provides accurate segmentation for many structures despite difficulties presented by real clinical data. Comparison of two different atlas selection strategies is also reported.

[1]  Nicholas Ayache,et al.  Non-rigid MR/US registration for tracking brain deformations , 2001, Proceedings International Workshop on Medical Imaging and Augmented Reality.

[2]  Juan Ruiz-Alzola,et al.  Fast Entropy-Based Nonrigid Registration , 2003, EUROCAST.

[3]  Stefano Bistarelli,et al.  Representing Biological Systems with Multiset Rewriting , 2003 .

[4]  K. Ang,et al.  CT-based delineation of lymph node levels and related CTVs in the node-negative neck: DAHANCA, EORTC, GORTEC, NCIC,RTOG consensus guidelines. , 2003, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[5]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[6]  William M. Wells,et al.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation , 2004, IEEE Transactions on Medical Imaging.

[7]  Rick S. Blum,et al.  Multi-sensor image fusion and its applications , 2005 .

[8]  Torsten Rohlfing,et al.  Quo Vadis, Atlas-Based Segmentation? , 2005 .

[9]  Nicholas Ayache,et al.  A Log-Euclidean Polyaffine Framework for Locally Rigid or Affine Registration , 2006, WBIR.

[10]  Linda G. Shapiro,et al.  Head and neck lymph node region delineation using a hybrid image registration method , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[11]  Nicholas Ayache,et al.  Non-parametric Diffeomorphic Image Registration with the Demons Algorithm , 2007, MICCAI.

[12]  Nicholas Ayache,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2007, 10th International Conference, Brisbane, Australia, October 29 - November 2, 2007, Proceedings, Part I , 2007, MICCAI.

[13]  O. Commowick,et al.  Atlas-based automatic segmentation (ABAS) of head and neck (H&N) structures in conformal radiotherapy (CRT): Atlas development and preliminary results in clinical context , 2007 .

[14]  Grégoire Malandain,et al.  Atlas-based delineation of lymph node levels in head and neck computed tomography images. , 2008, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[15]  Nicholas Ayache,et al.  A Fast and Log-Euclidean Polyaffine Framework for Locally Linear Registration , 2009, Journal of Mathematical Imaging and Vision.