A gradient-based method for segmenting FDG-PET images: methodology and validation
- 1.5k Downloads
A new gradient-based method for segmenting FDG-PET images is described and validated.
The proposed method relies on the watershed transform and hierarchical cluster analysis. To allow a better estimation of the gradient intensity, iteratively reconstructed images were first denoised and deblurred with an edge-preserving filter and a constrained iterative deconvolution algorithm. Validation was first performed on computer-generated 3D phantoms containing spheres, then on a real cylindrical Lucite phantom containing spheres of different volumes ranging from 2.1 to 92.9 ml. Moreover, laryngeal tumours from seven patients were segmented on PET images acquired before laryngectomy by the gradient-based method and the thresholding method based on the source-to-background ratio developed by Daisne (Radiother Oncol 2003;69:247–50). For the spheres, the calculated volumes and radii were compared with the known values; for laryngeal tumours, the volumes were compared with the macroscopic specimens. Volume mismatches were also analysed.
On computer-generated phantoms, the deconvolution algorithm decreased the mis-estimate of volumes and radii. For the Lucite phantom, the gradient-based method led to a slight underestimation of sphere volumes (by 10–20%), corresponding to negligible radius differences (0.5–1.1 mm); for laryngeal tumours, the segmented volumes by the gradient-based method agreed with those delineated on the macroscopic specimens, whereas the threshold-based method overestimated the true volume by 68% (p = 0.014). Lastly, macroscopic laryngeal specimens were totally encompassed by neither the threshold-based nor the gradient-based volumes.
The gradient-based segmentation method applied on denoised and deblurred images proved to be more accurate than the source-to-background ratio method.
KeywordsPositron emission tomography Gradient-based image segmentation Threshold-based image segmentation Image enhancement Head and neck cancer
This work was supported by a grant from the Belgian FNRS (national fund for scientific research), grant number 7.4538.02. This research program was supported by grants from the European Community (BIOCARE research program #LSHC-CT-2004-505785), the Belgian Federation against Cancer (convention #SCIE 2003-23FR) and the Fonds J. Maisin of the Université Catholique de Louvain. The authors have no financial relationship with the organizations that sponsored the research. J.A. Lee is a Postdoctoral Researcher with the FNRS.
- 16.Lagendijk RL, Biemond J. Iterative identification and restoration of images. Norwell, MA: Kluwer Academic, 1991.Google Scholar
- 17.Beucher S. The watershed transformation applied to image segmentation. Scanning Microscopy International 1992;Suppl 6:299–314.Google Scholar
- 24.Geets X, Daisne JF, Tomsej M, Duprez T, Lonneux M, Gregoire V. Impact of the type of imaging modality on target volumes delineation and dose distribution in pharyngo-laryngeal squamous cell carcinoma: comparison between pre- and per-treatment studies. Radiother Oncol 2006;78:291–7.PubMedCrossRefGoogle Scholar
- 25.Vauclin S, Doyeux K, Hapdey S, Vassal M, Vera P, Gardin I. Comparison of three thresholding methods for tumor volume determination in 18F-FDG PET imaging. Eur J Nucl Med 2006;33(Suppl 2):S148.Google Scholar
- 26.Devroye L. Non-uniform random variate generation. New York: Springer, 1986.Google Scholar
- 29.Nestle U, Kremp S, Schaefer-Schuler A, Sebastian-Welsch C, Hellwig D, Rube C, 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. J Nucl Med 2005;46:1342–8.PubMedGoogle Scholar