Abstract

Aim of this study: Bone age assessment and X-ray assessment on hand radiographs is an expensive and time consuming process in radiology. This research work presents a powerful Graphical User Interface (GUI) for IRMA that gives exceptional medical image retrieval results. Methods: This study gives complete details regarding the execution of a novel Discriminative Dictionary Learning (DDL) for the purpose of matching query and input medical image samples. In order to further boost the quality of the medical images, Principal Component Analysis (PCA) based noise level estimation scheme is introduced. This helps to eliminate noises included in the medical images. Furthermore, to enhance the performance, a new relevance score scheme via Kernel Support Vector Machine (KSVM) is formulated, which efficiently make use of medical images features in order to discriminate the images accurately. This system initiated a new discriminative name called ‘pairwise similarity measurement’ for the discriminativeness of pairs of query and input medical database images and subsequently integrate it with the classification error for discriminativeness in classifier production to generate a unified objective function. Results: Experimentation results assessed the proposed DDL in IRMA framework on a numerous medical images like BAA images and X-Ray skull images and results confirm that DDL performs far better than the state-of the-art approaches significantly in terms of precision, recall, sensitivity, specificity and accuracy. Conclusion: The resulting DDL has a considerable impact on medical CBIR applications.

Keywords:

Bone Age Assessment (BAA), Content Based Image Retrieval in Medical Applications (IRMA), Discriminative Dictionary Learning (DDL), Kernel Support Vector Machine (KSVM), Principal Component Analysis (PCA),

References

1. Amaral, I.F., F. Coelho, J.F.P. da Costa and J.S. Cardoso, 2010. Hierarchical medical image annotation using SVM-based approaches. Proceeding of the 10th IEEE International Conference on in Information Technology and Applications in Biomedicine (ITAB, 2010). Corfu, pp: 1-5.
   
2. Deselaers, T., T. Weyand, D. Keysers, W. Macherey and H. Ney, 2006. FIRE in ImageCLEF 2005: Combining Content-Based Image Retrieval with Textual Information Retrieval. In: Peters, C. et al. (Eds.), Accessing Multilingual Information Repositories. Lecture Notes in Computer Science, Springer-Verlag, Berlin, Heidelberg, 4022: 652-661.
   
3. Doi, K., 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Comput. Med. Imag. Grap., 31(4-5): 198-211.
   CrossRef    PMid:17349778 PMCid:PMC1955762    
4. Gutierrez, M.A., C.S. Santos, R.A. Moreno, L.O.M. Kobayashi, S.S. Furuie, S.M. Freire, D.B. Floriano, C.S. Oliveira, M.J. João and R.C. Gismondi, 2006. Implementation of a fault-tolerant PACS over a grid architecture. Proceeding of the SPIE Medical Imaging, 2006: PACS and Imaging Informatics, 6145: 369-378.
   CrossRef    
5. Haak, D., H. Simon, J. Yu, M. Harmsen and T.M. Deserno, 2013. Bone Age Assessment using Support Vector Machine Regression. In: Meinzer, H.P. et al. (Eds.), Bildverarbeitung Für Die Medizin 2013. Informatik Aktuell, Springer-Verlag, Berlin, Heidelberg, pp: 164-169.
   CrossRef    
6. Harmsen, M., B. Fischer, H. Schramm, T. Seidl and T.M. Deserno, 2013. Support vector machine classification based on correlation prototypes applied to bone age assessment. IEEE J. Biomed. Health Inform., 17(1): 190-197.
   CrossRef    PMid:23192601    
7. Hoi, S.C.H., R. Jin, J. Zhu and M.R. Lyu, 2008. Semi-supervised SVM batch mode active learning for image retrieval. Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR, 2008). Anchorage, AK, pp: 1-7.
   CrossRef    
8. Hsu, W., L.R. Long and S. Antani, 2007. SPIRS: A framework for content-based image retrieval from large biomedical databases. Stud. Health Technol. Inform., 129: 188-192.
   PMid:17911704    
9. Lehmann, T.M., M.O. Güld, C. Thies, B. Fischer, K. Spitzer, D. Keysers, H. Ney, M. Kohnen, H. Schubert and B.B. Wein, 2003. The IRMA project: A state of the art report on content-based image retrieval in medical applications. Proceeding of the 7th Korea-Germany Joint Workshop on Advanced Medical Image Processing, pp: 161-171.
   
10. Mansourvara, M., R.G. Raj, M.A. Ismail, S.A. Kareem, S. Shanmugam, S. Wahid, R. Mahmud, R.H. Abdullah, F.H. Nasaruddin and N. Idris, 2012. Automated web based system for bone age assessment using histogram technique. Malays. J. Comput. Sci., 25(3): 107-121.
    
11. Marcos, E., C.J. Acu-a, B. Vela, J.M. Cavero and J.A. Hernández, 2007. A database for medical image management. Comput. Meth. Prog. Bio., 86(3): 255-269.
    CrossRef    PMid:17462785    
12. Müller, H., W. Müller, D.M. Squire, S. Marchand-Maillet and T. Pun, 2001. Performance evaluation in content-based image retrieval: Overview and proposals. Pattern Recogn. Lett., 22(5): 593-601.
    CrossRef    
13. Müller, H., N. Michoux, D. Bandon and A. Geissbuhler, 2004. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions. Int. J. Med. Inform., 73(1): 1-23.
    CrossRef    PMid:15036075    
14. Müller, H., P.A. Do Hoang, A. Depeursinge, P. Hoffmeyer, R. Stern, C. Lovis and A. Geissbuhler, 2007. Content-based image retrieval from a database of fracture images. Proceeding of the SPIE 6516 Medical Imaging 2007: PACS and Imaging Informatics.
    CrossRef    
15. Samuelson, F. and D.G. Brown, 2011. Application of Cover's theorem to the evaluation of the performance of CI observers. Proceeding of the International Joint Conference on Neural Networks (IJCNN, 2011). San Jose, CA, pp: 1020-1026.
    CrossRef    
16. Übeyli, E.D., 2007. Comparison of different classification algorithms in clinical decision-making. Expert Syst., 24(1): 17-31.
    CrossRef    
17. Yildiz, M., A. Guvenis, E. Guven, D. Talat and M. Haktan, 2011. Implementation and statistical evaluation of a web-based software for bone age assessment. J. Med. Syst., 35(6): 1485-1489.
    CrossRef    PMid:20703769    
18. Zaproudina, N., O.O. Hänninen and O. Airaksinen, 2007. Effectiveness of traditional bone setting in chronic neck pain: Randomized clinical trial. J. Manip. Physiol. Ther., 30(6): 432-437.
    CrossRef    PMid:17693333    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.