Advertisement

Object-oriented classification approach for bone metastasis mapping from whole-body bone scintigraphy

  • Author Footnotes
    1 ORCID: 0000-0002-6135-7850.
    Mihaela Antonina Calin
    Correspondence
    Corresponding author at: National Institute of Research and Development for Optoelectronics INOE 2000, 409 Atomistilor Street, P.O. BOX MG5, Magurele, Ilfov 077125, Romania.
    Footnotes
    1 ORCID: 0000-0002-6135-7850.
    Affiliations
    National Institute of Research and Development for Optoelectronics - INOE 2000, Magurele, Romania
    Search for articles by this author
  • Florina-Gianina Elfarra
    Affiliations
    “Saint John” Emergency Clinical Hospital, Bucharest, Romania

    University of Bucharest, Faculty of Physics, Magurele, Romania
    Search for articles by this author
  • Author Footnotes
    2 ORCID: 0000-0003-3986-0385.
    Sorin Viorel Parasca
    Footnotes
    2 ORCID: 0000-0003-3986-0385.
    Affiliations
    Carol Davila” University of Medicine and Pharmacy, Bucharest, Romania
    Search for articles by this author
  • Author Footnotes
    1 ORCID: 0000-0002-6135-7850.
    2 ORCID: 0000-0003-3986-0385.
Published:April 21, 2021DOI:https://doi.org/10.1016/j.ejmp.2021.03.040

      Highlights

      • An edge-based segmentation approach can identify objects in whole body bone scintigraphy.
      • The objects have specific textural and spatial attributes.
      • K-nearest-neighbor and support vector machine can classify previously identified objects.
      • An error matrix was used to evaluate the method’s performance.
      • The object - based classification method can detect and map metastases in whole body scintigraphy.

      Abstract

      Purpose

      Whole-body bone scintigraphy is the most widely used method for detecting bone metastases in advanced cancer. However, its interpretation depends on the experience of the radiologist. Some automatic interpretation systems have been developed in order to improve diagnostic accuracy. These systems are pixel-based and do not use spatial or textural information of groups of pixels, which could be very important for classifying images with better accuracy. This paper presents a fast method of object-oriented classification that facilitates easier interpretation of bone scintigraphy images.

      Methods

      Nine whole-body images from patients suspected with bone metastases were analyzed in this preliminary study. First, an edge-based segmentation algorithm together with the full lambda-schedule algorithm were used to identify the object in the bone scintigraphy and the textural and spatial attributes of these objects were calculated. Then, a set of objects (224 objects, ~ 46% of the total objects) were selected as training data based on visual examination of the image, and were assigned to various levels of radionuclide accumulation before performing the data classification using both k-nearest-neighbor and support vector machine classifiers. The performance of the proposed method was evaluated using as metric the statistical parameters calculated from error matrix.

      Results

      The results revealed that the proposed object-oriented classification approach using either k-nearest-neighbor or support vector machine as classification methods performed well in detecting bone metastasis in terms of overall accuracy (86.62 ± 2.163% and 86.81 ± 2.137% respectively) and kappa coefficient (0.6395 ± 0.0143 and 0.6481 ± 0.0218 respectively).

      Conclusions

      In conclusion, the described method provided encouraging results in mapping bone metastases in whole-body bone scintigraphy.

      Graphical abstract

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Physica Medica: European Journal of Medical Physics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Van den Wyngaert T.
        • Strobel K.
        • Kampen W.U.
        • Kuwert T.
        • van der Bruggen W.
        • Mohan H.K.
        • et al.
        The EANM practice guidelines for bone scintigraphy.
        Eur J Nucl Med Mol Imaging. 2016; 43: 1723-1738https://doi.org/10.1007/s00259-016-3415-4
        • Sadik M.
        • Hamadeh I.
        • Nordblom P.
        • Suurkula M.
        • Hoglund P.
        • Ohlsson M.
        • et al.
        Computer-assisted interpretation of planar whole-body bone scans.
        J Nucl Med. 2008; 49: 1958-1965https://doi.org/10.2967/jnumed.108.055061
        • Nakajima K.
        • Nakajima Y.
        • Horikoshi H.
        • Ueno M.
        • Wakabayashi H.
        • Shiga T.
        • et al.
        Enhanced diagnostic accuracy for quantitative bone scan using an artificial neural network system: A Japanese multi-center database project.
        EJNMMI Res. 2013; 3: 83https://doi.org/10.1186/2191-219X-3-83
        • Elfarra F.-G.
        • Calin M.A.
        • Parasca S.V.
        Computer-aided detection of bone metastasis in bone scintigraphy images using parallelepiped classification method.
        Ann Nucl Med. 2019; 33: 866-874https://doi.org/10.1007/s12149-019-01399-w
        • Aslantas A.
        • Dandil E.
        • Saǧlam S.
        • Çakiroǧlu M.
        CADBOSS: A computer-aided diagnosis system for whole-body bone scintigraphy scans.
        J Cancer Res Ther. 2016; 12: 787https://doi.org/10.4103/0973-1482.150422
        • Pu X.
        • Tang G.
        • Cai K.
        • Huang Y.
        • Ping M.
        • Peng Z.
        • et al.
        A parallel deep learning network framework for whole-body bone scan image analysis.
        Ann Oncol. 2019; 30: ix182https://doi.org/10.1093/annonc/mdz423
        • Papandrianos N.
        • Papageorgiou E.
        • Anagnostis A.
        • Feleki A.
        A Deep-Learning Approach for Diagnosis of Metastatic Breast Cancer in Bones from Whole-Body Scans.
        Appl Sci. 2020; 10: 997https://doi.org/10.3390/app10030997
        • Liu D.
        • Xia F.
        Assessing object-based classification: advantages and limitations.
        Remote Sens Lett. 2010; 1: 187-194https://doi.org/10.1080/01431161003743173
        • Kettig R.L.
        • Landgrebe D.A.
        Classification of Multispectral Image Data by Extraction and.
        Classification of Homogeneous Objects. 1976;
        • Blaschke T.
        Object based image analysis for remote sensing.
        ISPRS J Photogramm Remote Sens. 2010; 65: 2-16https://doi.org/10.1016/j.isprsjprs.2009.06.004
        • Gamarra M.
        • Zurek E.
        • San-Juan H.
        Study of Image Analysis Algorithms for Segmentation, Feature Extraction and Classification of Cells.
        J Inf Syst Eng Manag. 2017; 2: 20
        • Rodellar J.
        • Alférez S.
        • Acevedo A.
        • Molina A.
        • Merino A.
        Image processing and machine learning in the morphological analysis of blood cells.
        Int J Lab Hematol. 2018; 40: 46-53https://doi.org/10.1111/ijlh.12818
        • Asodekar B.
        • Gore P.S.
        Brain Tumor Classification Using Shape Analysis of MRI Images.
        SSRN Electron J. 2019; https://doi.org/10.2139/ssrn.3425335
      1. Venkatesh, Leo MJ. MRI brain image segmentation and detection using K-NN classification. J. Phys. Conf. Ser., vol. 1362, Institute of Physics Publishing; 2019, p. 12073. https://doi.org/10.1088/1742-6596/1362/1/012073.

        • Minarik D.
        • Enqvist O.
        • Trägårdh E.
        Denoising of scintillation camera images using a deep convolutional neural network: A Monte Carlo simulation approach.
        J Nucl Med. 2020; 61: 298-303https://doi.org/10.2967/jnumed.119.226613
        • Park C.R.
        • Lee Y.
        Fast non-local means noise reduction algorithm with acceleration function for improvement of image quality in gamma camera system: A phantom study.
        Nucl Eng Technol. 2019; 51: 719-722https://doi.org/10.1016/j.net.2018.12.013
        • Gupta G.
        Algorithm for Image Processing Using Improved Median Filter and Comparison of Mean, Median and Improved Median Filter.
        Int J Soft Comput Eng. 2011; 1: 304-311
        • N S, S V.
        Image Segmentation By Using Thresholding Techniques For Medical Images.
        Comput Sci Eng An Int J. 2016;6:1–13.; https://doi.org/10.5121/cseij.2016.6101
        • Pan Z.
        • Lu J.
        A Bayes-based region-growing algorithm for medical image segmentation.
        Comput Sci Eng. 2007; 9: 32-38https://doi.org/10.1109/MCSE.2007.67
        • Naik D.
        • Shah P.
        A Review on Image Segmentation Clustering Algorithms.
        Int J Comput Sci Inf Technol. 2014; 5: 3289-3293
        • Sharma N.
        • Ray A.
        • Shukla K.
        • Sharma S.
        • Pradhan S.
        • Srivastva A.
        • et al.
        Automated medical image segmentation techniques.
        J Med Phys. 2010; 35: 3https://doi.org/10.4103/0971-6203.58777
      2. Robinson, D.J., Redding, N.J., Crisp DJ. Implementation of a fast algorithm for segmenting SAR imagery. 2002.

        • Mumford D.
        • Shah J.
        Boundary detection by minimizing functionals. IEEE Conf. Comput. Vis.
        Pattern Recognit. 1985; : 22-26
        • Veljanovski T.
        • Kanjir U.
        • Oštir K.
        Object-based image analysis of remote sensing data.
        Geod Vestn. 2011; 55: 641-664
        • Cover T.M.
        • Hart P.E.
        Nearest Neighbor Pattern Classification.
        IEEE Trans Inf Theory. 1967; 13: 21-27https://doi.org/10.1109/TIT.1967.1053964
      3. Vapnik VN. The Nature of Statistical Learning Theory. Springer New York; 1995. https://doi.org/10.1007/978-1-4757-2440-0.

        • Qian Y.
        • Zhou W.
        • Yan J.
        • Li W.
        • Han L.
        Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery.
        Remote Sens. 2014; 7: 153-168https://doi.org/10.3390/rs70100153
        • Tzotsos A.
        • Argialas D.
        Support vector machine classification for object-based image analysis.
        Lect Notes Geoinf Cartogr. 2008; : 663-677https://doi.org/10.1007/978-3-540-77058-9_36
        • LA Vapnik L.
        Pattern recognition using generalized portrait method.
        Autom Remote Control. 1963;
      4. Boser BE, Guyon IM, Vapnik VN. Training algorithm for optimal margin classifiers. Proc. Fifth Annu. ACM Work. Comput. Learn. Theory, New York, New York, USA: Publ by ACM; 1992, p. 144–52. https://doi.org/10.1145/130385.130401.

        • Fleiss J.L.
        Statistical methods for rates and proportions.
        2nd ed. John Wiley, New York1981
        • Wang Z.
        • Wen X.
        • Lu Y.
        • Yao Y.
        • Zhao H.
        Exploiting machine learning for predicting skeletal-related events in cancer patients with bone metastases.
        Oncotarget. 2016; 7: 12612-12622
        • Castillejo-González I.L.
        • López-Granados F.
        • García-Ferrer A.
        • Peña-Barragán J.M.
        • Jurado-Expósito M.
        • de la Orden M.S.
        • et al.
        Object- and pixel-based analysis for mapping crops and their agro-environmental associated measures using QuickBird imagery.
        Comput Electron Agric. 2009; 68: 207-215https://doi.org/10.1016/j.compag.2009.06.004
        • d’Oleire-Oltmanns S.
        • Coenradie B.
        • Kleinschmit B.
        An Object-Based Classification Approach for Mapping Migrant Housing in the Mega-Urban Area of the Pearl River Delta (China).
        Remote Sens. 2011; 3: 1710-1723https://doi.org/10.3390/rs3081710