Fuzzy versus hard hidden Markov chains segmentation for volume determination and quantitation in noisy PET images

Accurate volume contouring in PET is crucial for quantitation in numerous oncology applications. The objective of our study was to compare the performance of two algorithms for automatic lesion volume delineation that permit noise modelling and have not previously been applied to PET data; namely the hidden Markov chains (HMC) model and a novel version: fuzzy HMC. Both models take into account noise, voxel's intensity and spatial correlation, in order to classify a voxel as "background" or "functional volume". In comparison to HMC which only models uncertainty, the novelty of the fuzzy model consists of the inclusion of an estimation of imprecision. The performance of both models was compared using realistic simulated images. Results demonstrate that FHMC performs better than HMC in both activity concentration accuracy as well as functional volume determination under different imaging conditions

[1]  C. L. Le Rest,et al.  Validation of a Monte Carlo simulation of the Philips Allegro/GEMINI PET systems using GATE , 2006, Physics in medicine and biology.

[2]  S M Larson,et al.  Segmentation of lung lesion volume by adaptive positron emission tomography image thresholding , 1997, Cancer.

[3]  C. Rübe,et al.  Comparison of different methods for delineation of 18F-FDG PET-positive tissue for target volume definition in radiotherapy of patients with non-Small cell lung cancer. , 2005, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[4]  Tianzi Jiang,et al.  Automation segmentation of PET image for brain tumors , 2003, 2003 IEEE Nuclear Science Symposium. Conference Record (IEEE Cat. No.03CH37515).

[5]  Andrew J. Reader,et al.  Regularized one-pass list-mode EM algorithm for high resolution 3D PET image reconstruction into large arrays , 2001, 2001 IEEE Nuclear Science Symposium Conference Record (Cat. No.01CH37310).

[6]  Steve R. Gunn,et al.  Markov Random Field Models for Segmentation of PET Images , 2001, IPMI.

[7]  Adriaan A. Lammertsma,et al.  Effects of ROI definition and reconstruction method on quantitative outcome and applicability in a response monitoring trial , 2005, European Journal of Nuclear Medicine and Molecular Imaging.

[8]  W. Pieczynski.  Modèles de Markov en traitement d'images , 2003 .

[9]  Yves Bizais,et al.  Simulation of the Allegro PET system using GATE , 2004, SPIE Medical Imaging.

[10]  G. J. Klein,et al.  Automated 3-D segmentation of respiratory-gated PET transmission images , 1997 .

[11]  D. Visvikis,et al.  Evaluation of respiratory motion effects in comparison with other parameters affecting PET image quality , 2004, IEEE Symposium Conference Record Nuclear Science 2004..

[12]  D. Visvikis,et al.  The role of PET/CT scanning in radiotherapy planning. , 2006, The British journal of radiology.

[13]  D. Visvikis,et al.  Generating resolution-enhanced images for correction of partial volume effects in emission tomography: a multiresolution approach , 2005, IEEE Nuclear Science Symposium Conference Record, 2005.