A Fuzzy Locally Adaptive Bayesian Segmentation Approach for Volume Determination in PET

Accurate volume estimation in positron emission tomography (PET) is crucial for different oncology applications. The objective of our study was to develop a new fuzzy locally adaptive Bayesian (FLAB) segmentation for automatic lesion volume delineation. FLAB was compared with a threshold approach as well as the previously proposed fuzzy hidden Markov chains (FHMC) and the fuzzy C-Means (FCM) algorithms. The performance of the algorithms was assessed on acquired datasets of the IEC phantom, covering a range of spherical lesion sizes (10-37 mm), contrast ratios (4:1 and 8:1), noise levels (1, 2, and 5 min acquisitions), and voxel sizes (8 and 64 mm3). In addition, the performance of the FLAB model was assessed on realistic nonuniform and nonspherical volumes simulated from patient lesions. Results show that FLAB performs better than the other methodologies, particularly for smaller objects. The volume error was 5%-15% for the different sphere sizes (down to 13 mm), contrast and image qualities considered, with a high reproducibility (variation < 4%). By comparison, the thresholding results were greatly dependent on image contrast and noise, whereas FCM results were less dependent on noise but consistently failed to segment lesions < 2 cm. In addition, FLAB performed consistently better for lesions < 2 cm in comparison to the FHMC algorithm. Finally the FLAB model provided errors less than 10% for nonspherical lesions with inhomogeneous activity distributions. Future developments will concentrate on an extension of FLAB in order to allow the segmentation of separate activity distribution regions within the same functional volume as well as a robustness study with respect to different scanners and reconstruction algorithms.

[1]  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.

[2]  D Visvikis,et al.  Fuzzy hidden Markov chains segmentation for volume determination and quantitation in PET. , 2007, Physics in medicine and biology.

[3]  Alain Hillion,et al.  Estimation of fuzzy Gaussian mixture and unsupervised statistical image segmentation , 1997, IEEE Trans. Image Process..

[4]  D. Visvikis,et al.  PET functional volume segmentation: a robustness study , 2008, 2008 IEEE Nuclear Science Symposium Conference Record.

[6]  Y. Erdi,et al.  FDG-PET standardized uptake values in normal anatomical structures using iterative reconstruction segmented attenuation correction and filtered back-projection , 2001, European Journal of Nuclear Medicine.

[7]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

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

[9]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

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

[11]  Benjamin M. W. Tsui,et al.  Modeling respiratory mechanics in the MCAT and spline-based MCAT phantoms , 1999 .

[12]  J. MacQueen Some methods for classification and analysis of multivariate observations , 1967 .

[13]  Sei-ichiro Kamata,et al.  A new algorithm for N-dimensional Hilbert scanning , 1999, IEEE Trans. Image Process..

[14]  Milton C. Chew Distributions in Statistics: Continuous Univariate Distributions-1 and 2 , 1971 .

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

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

[17]  G. Celeux,et al.  L'algorithme SEM: un algorithme d'apprentissage probabiliste: pour la reconnaissance de mélange de densités , 1986 .

[18]  Dimitris Visvikis,et al.  Partial volume correction in PET based on functional volumes , 2008 .

[19]  Christophe Collet,et al.  Fuzzy versus hard hidden Markov chains segmentation for volume determination and quantitation in noisy PET images , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[20]  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.

[21]  W. R. Buckland,et al.  Distributions in Statistics: Continuous Multivariate Distributions , 1973 .

[22]  J. C. Dunn,et al.  A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters , 1973 .

[23]  P. R. Fisk,et al.  Distributions in Statistics: Continuous Multivariate Distributions , 1971 .

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

[25]  Abdelwaheb Marzouki,et al.  Estimation of generalized mixtures and its application in image segmentation , 1997, IEEE Trans. Image Process..

[26]  Stefan Eberl,et al.  Automatic 3D temporal kinetics segmentation of dynamic emission tomography image using adaptive region growing cluster analysis , 2002, 2002 IEEE Nuclear Science Symposium Conference Record.

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

[28]  Wojciech Pieczynski,et al.  Parameter Estimation in Hidden Fuzzy Markov Random Fields and Image Segmentation , 1997, CVGIP Graph. Model. Image Process..

[29]  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.

[30]  Richard E. Carson,et al.  The watershed algorithm: a method to segment noisy PET transmission images , 1998, 1998 IEEE Nuclear Science Symposium Conference Record. 1998 IEEE Nuclear Science Symposium and Medical Imaging Conference (Cat. No.98CH36255).