Pattern Recognition and Image Analysis

, Volume 28, Issue 1, pp 106–113 | Cite as

Normal and Abnormal Tissue Classification in Positron Emission Tomography Oncological Studies

  • A. Comelli
  • A. Stefano
  • V. Benfante
  • G. Russo
Applied Problems


Positron Emission Tomography (PET) imaging is increasingly used in radiotherapy environment as well as for staging and assessing treatment response. The ability to classify PET tissues, as normal versus abnormal tissues, is crucial for medical analysis and interpretation. For this reason, a system for classifying PET area is implemented and validated. The proposed classification is carried out using k-nearest neighbor (KNN) method with the stratified K-Fold Cross-Validation strategy to enhance the classifier reliability. A dataset of eighty oncological patients are collected for system training and validation. For every patient, lesion (abnormal tissue) and background (normal tissue around the lesion) are contoured on PET images using a semi-automatic method. Then 160 vectors are obtained to train and validate the KNN. Each vector is composed by thirty Standardized Uptake Values (SUVs) characterizing the area under investigation (lesion or background). In one case, vectors are labeled as normal or abnormal tissues by a nuclear medicine physician using a semi-automatic method; in other cases, Fuzzy C-means (FCM) and k-means are used for labelling vectors in an unsupervised manner. This study aims to evaluate the performance of the proposed classifier comparing it to the Linear Kernel Support Vector Machine (KSVM). The method accuracy is evaluated by comparison with the gold standard in terms of correct classification. Experimental results show that the KNN method achieves the highest classification accuracy using the semi-automatic labelling training (Sensitivity: 86.25%; Specificity: 90.00%; Negative Predictive Value: 88.37%; Precision: 89.81%; Accuracy: 88.12%; Error: 11.87%). In addition, the proposed method shows real-time performance; it could be applied to the field classification of PET images assisting physicians into discrimination of normal and abnormal tissue during radiation treatment planning.


tissue classification K-nearest neighbor Kernel support vector machine Fuzzy C-Means K-Fold cross-validation positron emission tomography 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    K. L. Newbold, M. Partridge, G. Cook, B. Sharma, P. Rhys-Evans, K. J. Harrington, and C. M. Nutting, “Evaluation of the role of 18fdg-pet/ct in radiotherapy target definition in patients with head and neck cancer,” Acta Oncol. 47, 1229–1236 (2008).CrossRefGoogle Scholar
  2. 2.
    L. K. Shankar, J. M. Hoffman, S. Bacharach, M. M. Graham, J. Karp, A. A. Lammertsma, S. Larson, D. A. Mankoff, B. A. Siegel, A. Van den Abbeele, et al., “Consensus recommendations for the use of 18ffdg pet as an indicator of therapeutic response in patients in national cancer institute trials,” J. Nucl. Med. 47, 1059–1066 (2006).Google Scholar
  3. 3.
    L. Rundo, A. Stefano, C. Militello, G. Russo, M. G. Sabini, C. D’Arrigo, F. Marletta, M. Ippolito, G. Mauri, S. Vitabile, et al., “A fully automatic approach for multimodal pet and mr image segmentation in gamma knife treatment planning,” Comput. Methods Programs Biomed. 144, 77–96 (2017).CrossRefGoogle Scholar
  4. 4.
    S. M. Larson, Y. Erdi, T. Akhurst, M. Mazumdar, H. A. Macapinlac, R. D. Finn, C. Casilla, M. Fazzari, N. Srivastava, H. W. D. Yeung, et al., “Tumor treatment response based on visual and quantitative changes in global tumor glycolysis using pet-fdg imaging: the visual response score and the change in total lesion glycolysis,” Clin. Positron Imag. 2, 159–171 (1999).CrossRefGoogle Scholar
  5. 5.
    A. Stefano, S. Vitabile, G. Russo, M. Ippolito, M. G. Sabini, D. Sardina, O. Gambino, R. Pirrone, E. Ardizzone, and M. C. Gilardi, “An enhanced random walk algorithm for delineation of head and neck cancers in pet studies,” Med. Biol. Eng. Comput. 55 (6), 897–908 (2016).CrossRefGoogle Scholar
  6. 6.
    D. Hellwig, T. P. Graeter, D. Ukena, A. Groeschel, G. W. Sybrecht, H.-J. Schaefers, and C.-M. Kirsch, “18f-fdg pet for mediastinal staging of lung cancer: which suv threshold makes sense,” J. Nucl. Med. 48, 1761–1766 (2007).CrossRefGoogle Scholar
  7. 7.
    R. L. Wahl, H. Jacene, Y. Kasamon, and M. A. Lodge, “From recist to percist: evolving considerations for pet response criteria in solid tumors,” J. Nucl. Med. 50, 122S–150S (2009).CrossRefGoogle Scholar
  8. 8.
    N. C. Nguyen, A. Kaushik, M. K. Wolverson, and M. M. Osman, “Is there a common suv threshold in oncological fdg pet/ct, at least for some common indications a retrospective study,” Acta Oncol. 50, 670–677 (2011).CrossRefGoogle Scholar
  9. 9.
    C. Ballangan, X. Wang, S. Eberl, M. Fulham, and D. Feng, “Automated lung tumor segmentation for whole body pet volume based on novel downhill region growing,” Proc. SPIE Med. Imag. 7623, 76233O–76233O (2010).CrossRefGoogle Scholar
  10. 10.
    A. Stefano, S. Vitabile, G. Russo, M. Ippolito, F. Marletta, C. D’arrigo, D. D’urso, O. Gambino, R. Pirrone, E. Ardizzone, et al., “A fully automatic method for biological target volume segmentation of brain metastases,” Int. J. Imag. Syst. Technol. 26, 29–37 (2016).CrossRefGoogle Scholar
  11. 11.
    B. Wu, P.-L. Khong, and T. Chan, “Automatic detection and classification of nasopharyngeal carcinoma on pet/ct with support vector machine,” Int. J. Comput. Assisted Radiol. Surgery 7, 635–646 (2012).CrossRefGoogle Scholar
  12. 12.
    Hongkai Wang, Zongwei Zhou, Yingci Li, Zhonghua Chen, Peiou Lu, Wenzhi Wang, Wanyu Liu, and Lijuan Yu, “Comparison of machine learning methods for classifying mediastinal lymph node metastasis of nonsmall cell lung cancer from 18 f-fdg pet/ct images,” EJNMMI Res. 7, 11 (2017).CrossRefGoogle Scholar
  13. 13.
    C. Lartizien, M. Rogez, E. Niaf, and F. Ricard, “Computer- aided staging of lymphoma patients with fdg pet/ct imaging based on textural information,” IEEE J. Biomed. Health Inf. 18, 946–955 (2014).CrossRefGoogle Scholar
  14. 14.
    H. Yu, C. Caldwell, K. Mah, and D. Mozeg, “Coregistered fdg pet/ct-based textural characterization of head and neck cancer for radiation treatment planning,” IEEE Trans. Med. Imag. 28, 374–383 (2009).CrossRefGoogle Scholar
  15. 15.
    Lei Bi, Jinman Kim, Lingfeng Wen, Dagan Feng, and M. Fulham, “Automated thresholded region classification using a robust feature selection method for pet-ct,” in Proc. 12th IEEE Int. Symp. on Biomedical Imaging (ISBI) (IEEE, 2015), pp. 1435–1438.Google Scholar
  16. 16.
    M. A. Nogueira, P. H. Abreu, P. Martins, P. Machado, H. Duarte, and J. Santos, “An artificial neural networks approach for assessment treatment response in oncological patients using pet/ct images,” BMC Med. Imag. 17, 13 (2017).CrossRefGoogle Scholar
  17. 17.
    R. Boellaard, R. Delgado-Bolton, W. J. G. Oyen, F. Giammarile, K. Tatsch, W. Eschner, F. J. Verzijlbergen, S. F. Barrington, L. C. Pike, W. A. Weber, et al., “Fdg pet/ct: Eanm procedure guidelines for tumour imaging: version 2.0,” Europ. J. Nucl. Med. Mol. Imag. 42, 328–354 (2015).CrossRefGoogle Scholar
  18. 18.
    S. Armand, E. Watelain, E. Roux, M. Mercier, and F.-X. Lepoutre, “Linking clinical measurements and kinematic gait patterns of toe-walking using fuzzy decision trees,” Gait Posture 25, 475–484 (2007).CrossRefGoogle Scholar
  19. 19.
    L. Agnello, A. Comelli, E. Ardizzone, and S. Vitabile, “Unsupervised tissue classification of brain mr images for voxel-based morphometry analysis,” Int. J. Imag. Syst. Technol. 26, 136–150 (2016).CrossRefGoogle Scholar
  20. 20.
    M. Soret, S. L. Bacharach, and I. Buvat, “Partial-volume effect in pet tumor imaging,” J. Nucl. Med. 48, 932–945 (2007).CrossRefGoogle Scholar
  21. 21.
    F. Gallivanone, A. Stefano, E. Grosso, C. Canevari, L. Gianolli, C. Messa, M. C. Gilardi, and I. Castiglioni, “Pve correction in pet-ct wholebody oncological studies from pve-affected images,” IEEE Trans. Nucl. Sci. 58, 736–747 (2011).CrossRefGoogle Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  • A. Comelli
    • 1
    • 2
    • 4
  • A. Stefano
    • 2
  • V. Benfante
    • 3
  • G. Russo
    • 2
  1. 1.Department of Industrial and Digital Innovation (DIID)University of Palermo (PA)PalermoItaly
  2. 2.Institute of Molecular Bioimaging and PhysiologyNational Research Council (IBFM-CNR)Cefalù (PA)Italy
  3. 3.Institute of Biomedicine and Molecular Immunology “Alberto Monroy,”National Research Council (IBIM-CNR)Palermo (PA)Italy
  4. 4.Department of Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations