Impact of consensus contours from multiple PET segmentation methods on the accuracy of functional volume delineation
- 558 Downloads
The aim of this study was to evaluate the impact of consensus algorithms on segmentation results when applied to clinical PET images. In particular, whether the use of the majority vote or STAPLE algorithm could improve the accuracy and reproducibility of the segmentation provided by the combination of three semiautomatic segmentation algorithms was investigated.
Three published segmentation methods (contrast-oriented, possibility theory and adaptive thresholding) and two consensus algorithms (majority vote and STAPLE) were implemented in a single software platform (Artiview®). Four clinical datasets including different locations (thorax, breast, abdomen) or pathologies (primary NSCLC tumours, metastasis, lymphoma) were used to evaluate accuracy and reproducibility of the consensus approach in comparison with pathology as the ground truth or CT as a ground truth surrogate.
Variability in the performance of the individual segmentation algorithms for lesions of different tumour entities reflected the variability in PET images in terms of resolution, contrast and noise. Independent of location and pathology of the lesion, however, the consensus method resulted in improved accuracy in volume segmentation compared with the worst-performing individual method in the majority of cases and was close to the best-performing method in many cases. In addition, the implementation revealed high reproducibility in the segmentation results with small changes in the respective starting conditions. There were no significant differences in the results with the STAPLE algorithm and the majority vote algorithm.
This study showed that combining different PET segmentation methods by the use of a consensus algorithm offers robustness against the variable performance of individual segmentation methods and this approach would therefore be useful in radiation oncology. It might also be relevant for other scenarios such as the merging of expert recommendations in clinical routine and trials or the multiobserver generation of contours for standardization of automatic contouring.
KeywordsPET image segmentation Consensus algorithms STAPLE Radiation oncology 18F-FDG PET Image segmentation
A. Schaefer is very grateful for the valuable support of Y.-J. Kim PhD, Department of Pathology, Saarland University Medical Centre, in preparing the pathological reference database of centre 1. U. Nestle thanks Christian Doll, MD, Department for Radiation Oncology, University Medical Center Freiburg, Freiburg, Germany, and Alin Chirindel, MD, Department of Nuclear Medicine, St. Claraspital, Basel, Switzerland, for assistance in analysing the data of centre 2.
Compliance with ethical standards
This work was partially supported by EU project E5949 SALOME under the Eurostars Program, which is supported by EUREKA and the European Community.
Conflicts of interest
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the principles of the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards.
Formal consent is not required for this type of retrospective study.
- 3.Zasadny KR, Kison PV, Francis IR, Wahl RL. FDG-PET determination of metabolically active tumor volume and comparison with CT. Clin Positron Imaging. 1998;1:123–9.Google Scholar
- 9.Erdi YE, Wessels BW, Loew MH, Erdi AK. Threshold estimation in single photon emission computed tomography and planar imaging for clinical radioimmunotherapy. Cancer Res. 1995;55(23 Suppl):S5823–6.Google Scholar
- 11.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
- 13.Schaefer A, Kremp S, Hellwig D, Rube C, Kirsch CM, Nestle U. A contrast-oriented algorithm for FDG-PET-based delineation of tumour volumes for the radiotherapy of lung cancer: derivation from phantom measurements and validation in patient data. Eur J Nucl Med Mol Imaging. 2008;35:1989–99.CrossRefPubMedGoogle Scholar
- 15.Tylski P, Bonniaud G, Decenciere E, Stawiaski J, Coulot J, Lefkopoulos D, et al. 18F-FDG PET images segmentation using morphological watershed: a phantom study. IEEE Nucl Sci Symp Conf Rec. 2006;4:2063–7.Google Scholar
- 16.Nissen I, Yaqub M, Lammertsma A, Lee J, Geets X, Boellaard R. A novel supervised watershed method for segmentation of tumors with heterogeneous tracer uptake in PET. Proceedings of the Society of Nuclear Medicine Annual Meeting, St. Louis, Mo, 7–11 June 2014. Abstract 260.Google Scholar
- 18.Zhu W, Jiang T. Automation segmentation of PET image for brain tumors. IEEE Nucl Sci Symp Conf Rec. 2003;4:2627–9.Google Scholar
- 21.Dewalle-Vignion AS, Betrouni N, Makni N, Huglo D, Rousseau J, Vermandel M. A new method based on both fuzzy set and possibility theories for tumor volume segmentation on PET images. Conf Proc IEEE Eng Med Biol Soc. 2008;2008:3122–5.Google Scholar
- 25.Shepherd T, Teras M, Beichel R, Boellaard R, Bruynooghe M, Dicken V, et al. Comparative study with new accuracy metrics for target volume contouring in PET image guided radiation therapy. IEEE Trans Med Imaging. 2012;31:2006–24. doi: 10.1109/TMI.2012.2202322.
- 26.Østergaard LR, Larsen OV. Applying voting to segmentation of MR images. In: Amin A, Dori D, Pudil P, Freeman H, editors. Advances in pattern recognition. Berlin: Springer; 1998. p. 795–804.Google Scholar
- 33.Doll C, Parcq C, Modzelewski R, Dewalle-Vignion AS, Christ U, Loquin K, et al. PET-based target volume delineation in radiation therapy planning: are different implementations of the same automatic delineation method really equal? Proceedings of the Annual Congress of the European Association of Nuclear Medicine (EANM'13), October 2013, Lyon, France. Vol. 40 (2 suppl), p. S244 Google Scholar
- 34.Schaefer A, Nestle U, Kremp S, Hellwig D, Grgic A, Buchholz HG, et al. Multi-centre calibration of an adaptive thresholding method for PET-based delineation of tumour volumes in radiotherapy planning of lung cancer. Nuklearmedizin. 2012;51:101–10. doi: 10.3413/Nukmed-0452-11-12.CrossRefPubMedGoogle Scholar
- 37.Dewalle-Vignion AS, Betrouni N, Baillet C, Vermandel M. Is STAPLE algorithm confident to assess segmentation methods in PET imaging? Phys Med Biol. 2015. In press.Google Scholar
- 44.Steenbakkers RJ, Duppen JC, Fitton I, Deurloo KE, Zijp L, Uitterhoeve AL, et al. Observer variation in target volume delineation of lung cancer related to radiation oncologist-computer interaction: a ‘Big Brother’ evaluation. Radiother Oncol. 2005;77:182–90. doi: 10.1016/j.radonc.2005.09.017.CrossRefPubMedGoogle Scholar
- 45.Erasmus JJ, Gladish GW, Broemeling L, Sabloff BS, Truong MT, Herbst RS, et al. Interobserver and intraobserver variability in measurement of non-small-cell carcinoma lung lesions: implications for assessment of tumor response. J Clin Oncol. 2003;21:2574–82. doi: 10.1200/JCO.2003.01.144.CrossRefPubMedGoogle Scholar
- 46.McGurk RJ. Consensus segmentation for positron emission tomography: development and applications in radiation therapy. Duke University. 2013.Google Scholar
- 50.Hatt M, Cheze le Rest C, Descourt P, Dekker A, De Ruysscher D, Oellers M, et al. Accurate automatic delineation of heterogeneous functional volumes in positron emission tomography for oncology applications. Int J Radiat Oncol Biol Phys. 2010;77:301–8. doi: 10.1016/j.ijrobp.2009.08.018.CrossRefPubMedGoogle Scholar
- 51.Papadimitroulas P, Loudos G, Le Maitre A, Hatt M, Tixier F, Efthimiou N, et al. Investigation of realistic PET simulations incorporating tumor patient’s specificity using anthropomorphic models: creation of an oncology database. Med Phys. 2013;40:112506. doi: 10.1118/1.4826162.CrossRefPubMedGoogle Scholar