Top

Published in:

01-11-2014 | Original Article

Texture analysis on ¹⁸F-FDG PET/CT images to differentiate malignant and benign bone and soft-tissue lesions

Authors: Rui Xu, Shoji Kido, Kazuyoshi Suga, Yasushi Hirano, Rie Tachibana, Keiichiro Muramatsu, Kazuki Chagawa, Satoshi Tanaka

Published in: Annals of Nuclear Medicine | Issue 9/2014

Abstract

Objective

The purpose is to develop and evaluate the ability of the computer-aided diagnosis (CAD) methods that apply texture analysis and pattern classification to differentiate malignant and benign bone and soft-tissue lesions on 18F-fluorodeoxy-glucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images.

Methods

Subjects were 103 patients with 59 malignant and 44 benign bone and soft tissue lesions larger than 25 mm in diameter. Variable texture parameters of standardized uptake values (SUV) and CT Hounsfield unit values were three-dimensionally calculated in lesional volumes-of-interest segmented on PET/CT images. After selection of a subset of the most optimal texture parameters, a support vector machine classifier was used to automatically differentiate malignant and benign lesions. We developed three kinds of CAD method. Two of them utilized only texture parameters calculated on either CT or PET images, and the other one adopted the combined PET and CT texture parameters. Their abilities of differential diagnosis were compared with the SUV method with an optimal cut-off value of the maximum SUV.

Results

The CAD methods utilizing only optimal PET (or CT) texture parameters showed sensitivity of 83.05 % (81.35 %), specificity of 63.63 % (61.36 %), and accuracy of 74.76 % (72.82 %). Although the ability of differential diagnosis by PET or CT texture analysis alone was not significantly different from the SUV method whose sensitivity, specificity, and accuracy were 64.41, 61.36, and 63.11 % (the optimal cut-off SUV_max was 5.4 ± 0.9 in the 10-fold cross-validation test), the CAD method with the combined PET and CT optimal texture parameters (PET: entropy and coarseness, CT: entropy and correlation) exhibited significantly better performance compared with the SUV method (p = 0.0008), showing a sensitivity of 86.44 %, specificity of 77.27 %, and accuracy of 82.52 %.

Conclusions

The present CAD method using texture analysis to analyze the distribution/heterogeneity of SUV and CT values for malignant and benign bone and soft-tissue lesions improved the differential diagnosis on ¹⁸F-FDG PET/CT images.

Available only for authorised users

We define the length of the longest edge of the lesional bounding box as the diameter, because a lesion is not always circular.

We specify the developed CAD method to be the method utilizing the combination of CT and PET texture parameters in the following context.

Bischoff M, Bischoff G, Buck A, von Baer A, Pauls S, Scheffold F, et al. Integrated FDG-PET-CT: its role in the assessment of bone and soft tissue tumors. Arch Orthop Trauma Surg. 2010;130:819–27.PubMedCrossRef

Charest M, Hickeson M, Lisbona R, Novales-Diaz JA, Derbekyan V, Turcotte RE. FDG PET/CT imaging in primary osseous and soft tissue sarcomas: a retrospective review of 212 cases. Eur J Nucl Med Mol Imaging. 2009;36:1944–51.PubMedCrossRef

Piperkova E, Mikhaeil M, Mousavi A, Libes R, Viejo-Rullan F, Lin H, et al. Impact of PET and CT in PET/CT studies for staging and evaluating treatment response in bone and soft tissue sarcomas. Clin Nucl Med. 2009;34:146–50.PubMedCrossRef

Aoki J, Endo K, Watanabe H, Shinozaki T, Yanagawa T, Ahmed AR, et al. FDG-PET for evaluating musculoskeletal tumors: a review. J Orthop Sci. 2003;8:435–41.PubMedCrossRef

Schwarzbach MH, Dimitrakopoulou-Strauss A, Willeke F, Hinz U, Strauss LG, Zhang YM, et al. Clinical value of [18-F] fluorodeoxyglucose positron emission tomography imaging in soft tissue sarcomas. Ann Surg. 2000;231:380–6.PubMedCentralPubMedCrossRef

Shin DS, Shon OJ, Han DS, Choi JH, Chun KA, Cho IH. The clinical efficacy of 18F-FDG-PET/CT in benign and malignant musculoskeletal tumors. Ann Nucl Med. 2008;22:603–9.PubMedCrossRef

Suga K, Chagawa K, Seki N, Taguchi T, Matsunaga N. Feasibility and pitfall of PET/CT scan in assessment of bone and soft-tissue tumors: initial experiences and literature review [in Japanese]. Jpn J Clin Radiol. 2011;56:855–72.

Dimitrakopoulou-Strauss A, Strauss LG, Heichel T, Wu H, Burger C, Bernd L, et al. The role of quantitative 18F-FDG PET studies for the differentiation of malignant and benign bone lesions. J Nucl Med. 2002;43:510–8.PubMed

Tixier F, Le Rest CC, Hatt M, Albarghach N, Pradier O, Metges JP, et al. Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J Nucl Med. 2011;52:369–78.PubMedCentralPubMedCrossRef

10.

Tixier F, Hatt M, Le Rest CC, Le Pogam A, Corcos L, Visvikis D. Reproducibility of tumor uptake heterogeneity characterization through texture feature analysis in 18F-FDG PET. J Nucl Med. 2012;53:693–700.PubMedCentralPubMedCrossRef

11.

Cook GJ, Yip C, Siddique M, Goh V, Chicklore S, Roy A, et al. Are pretreatment ¹⁸F-FDG PET tumor textural features in non-small cell lung cancer associated with response and survival after chemoradiotherapy? J Nucl Med. 2013;54:19–26.PubMedCrossRef

12.

Chicklore S, Goh V, Siddique M, Roy A, Marsden PK, Cook GJ. Quantifying tumour heterogeneity in ¹⁸F-FDG PET/CT imaging by texture analysis. Eur J Nucl Med Mol Imaging. 2013;40:133–40.PubMedCrossRef

13.

Davnall F, Yip CS, Ljungqvist G, Selmi M, Ng F, Sanghera B, et al. Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? Insights Imaging. 2012;3:573–89.PubMedCentralPubMedCrossRef

14.

Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;3:610–21.CrossRef

15.

Kurani AS, Xu DH, Furst J, Raicu DS. Co-occurrence matrices for volumetric data. In: Proceedings of 7th IASTED international conference on computer graphics and imaging; 2004.

16.

Amadasun M, King R. Textural features corresponding to textural properties. IEEE Trans Syst Man Cybern. 1989;19:1264–74.CrossRef

17.

Kido S, Kuriyama K, Higashiyama M, Kasugai T, Kuroda C. Fractal analysis of small peripheral pulmonary nodules in thin-section CT: evaluation of the lung-nodule interfaces. J Comput Assist Tomogr. 2002;26:573–8.PubMedCrossRef

18.

Chen W, Giger ML, Li H, Bick U, Newstead GM. Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance breast image data. J Magn Reson Imaging. 2007;58:562–71.

19.

Brooks FJ, Grigsby PW. The effect of small tumor volumes on studies of intratumoral heterogeneity of tracer uptake. J Nucl Med. 2014;55:37–42.PubMedCrossRef

20.

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.PubMed

21.

Tylski P, Stute S, Grotus N, Doyeux K, Hapdey S, Gardin I, et al. Comparative assessment of methods for estimating tumor volume and standardized uptake value in 18F-FDG PET. J Nucl Med. 2010;51:268–76.PubMedCrossRef

22.

Vapnik VN. The nature of statistical learning theory. 2nd ed. New York: Springer; 1999.

23.

Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2011;2:27:1–27.CrossRef

24.

Japkowicz N, Shah M. Evaluating learning algorithms: a classification perspective. Cambridge: Cambridge University Press; 2011.CrossRef

25.

Fawceet T. An introduction to ROC analysis. Pattern Recogn Lett. 2006;27:861–74.CrossRef

26.

Shannon CE. A Mathematical Theory of communication. Bell Syst Tech J. 1948;27(379–423):623–56.CrossRef

27.

Meyer D, Leisch F, Hornik K. The support vector machine under test. Neurocomputing. 2003;55:169–86.CrossRef

Title: Texture analysis on 18F-FDG PET/CT images to differentiate malignant and benign bone and soft-tissue lesions
Authors: Rui Xu
Shoji Kido
Kazuyoshi Suga
Yasushi Hirano
Rie Tachibana
Keiichiro Muramatsu
Kazuki Chagawa
Satoshi Tanaka
Publication date: 01-11-2014
Publisher: Springer Japan
Published in: Annals of Nuclear Medicine / Issue 9/2014
Print ISSN: 0914-7187
Electronic ISSN: 1864-6433
DOI: https://doi.org/10.1007/s12149-014-0895-9

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Texture analysis on ¹⁸F-FDG PET/CT images to differentiate malignant and benign bone and soft-tissue lesions

Abstract

Objective

Methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objective

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 9/2014

Evaluation of variability of phase indices of the left ventricle in the course of time

Quantification of myocardial blood flow using 201Tl SPECT and population-based input function

Use of 99mTc-anti-TNF-α scintigraphy in a patient with non-radiographic axial spondyloarthritis

Preparation of 99mTc carbonyl DTPA-bevacizumab and its bioevaluation in a melanoma model

Association between survival and maximum standardized uptake value of liver metastases detected by 18-fluoro-2-deoxy-d-glucose positron emission tomography-computed tomography in patients with adenocarcinoma of unknown primary origin

Synthesis, characterization and in vivo evaluation of [62Zn]–benzo-δ-sultam complex as a possible pet imaging agent