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
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 accessOne-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 PhysicsAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- 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
- Computer-assisted interpretation of planar whole-body bone scans.J Nucl Med. 2008; 49: 1958-1965https://doi.org/10.2967/jnumed.108.055061
- 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
- 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
- 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
- A parallel deep learning network framework for whole-body bone scan image analysis.Ann Oncol. 2019; 30: ix182https://doi.org/10.1093/annonc/mdz423
- 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
- Assessing object-based classification: advantages and limitations.Remote Sens Lett. 2010; 1: 187-194https://doi.org/10.1080/01431161003743173
- Classification of Multispectral Image Data by Extraction and.Classification of Homogeneous Objects. 1976;
- 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
- Study of Image Analysis Algorithms for Segmentation, Feature Extraction and Classification of Cells.J Inf Syst Eng Manag. 2017; 2: 20
- 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
- Brain Tumor Classification Using Shape Analysis of MRI Images.SSRN Electron J. 2019; https://doi.org/10.2139/ssrn.3425335
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.
- 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
- 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
- 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
- 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
- A Bayes-based region-growing algorithm for medical image segmentation.Comput Sci Eng. 2007; 9: 32-38https://doi.org/10.1109/MCSE.2007.67
- A Review on Image Segmentation Clustering Algorithms.Int J Comput Sci Inf Technol. 2014; 5: 3289-3293
- Automated medical image segmentation techniques.J Med Phys. 2010; 35: 3https://doi.org/10.4103/0971-6203.58777
Robinson, D.J., Redding, N.J., Crisp DJ. Implementation of a fast algorithm for segmenting SAR imagery. 2002.
- Boundary detection by minimizing functionals. IEEE Conf. Comput. Vis.Pattern Recognit. 1985; : 22-26
- Object-based image analysis of remote sensing data.Geod Vestn. 2011; 55: 641-664
- Nearest Neighbor Pattern Classification.IEEE Trans Inf Theory. 1967; 13: 21-27https://doi.org/10.1109/TIT.1967.1053964
Vapnik VN. The Nature of Statistical Learning Theory. Springer New York; 1995. https://doi.org/10.1007/978-1-4757-2440-0.
- 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
- 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
- Pattern recognition using generalized portrait method.Autom Remote Control. 1963;
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.
- Statistical methods for rates and proportions.2nd ed. John Wiley, New York1981
- Exploiting machine learning for predicting skeletal-related events in cancer patients with bone metastases.Oncotarget. 2016; 7: 12612-12622
- 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
- 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
Article info
Publication history
Published online: April 21, 2021
Accepted:
March 30,
2021
Received in revised form:
March 12,
2021
Received:
December 18,
2020
Identification
Copyright
© 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.
