A New Method for Osteosarcoma Recognition Based on Bayesian Classifier

Wen Bo Huang; Yun Ji Wang

doi:10.4028/www.scientific.net/AMM.543-547.2901

Paper Titles

Research and Design of a Short Message Services Management System for Mobile Devices
p.2884

High Isolation and Compact Microstrip Diplexer for Broadband and WLAN Application
p.2888

Analysis and Testing on Terminal RRC Connection Establishment Procedure in TD-LTE System Based on TTCN-3
p.2893

Research of Double RM Code and Decode of PUCCH Format 3 in Carrier Aggregation
p.2897

A New Method for Osteosarcoma Recognition Based on Bayesian Classifier
p.2901

RETRACTED: Studying Context-Free Grammar Using Collaborative Symmetries
p.2907

Intelligent DNS for Accelerating Web Access to University with Multi-Exports
p.2911

Service Discovery Based on Self-Evolution of Domain Ontology and Cloud Migration of Web Service
p.2915

3D Reconstruction of Rock Mass Based on Point Cloud Library
p.2920

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 543-547A New Method for Osteosarcoma Recognition Based on...

A New Method for Osteosarcoma Recognition Based on Bayesian Classifier

Abstract:

In order to deal with the complexity and uncertainty in medical image diagnosis of osteosarcoma, we proposed a new method based on Bayesian network, and first applied it to recognize osteosarcoma. A new multidimensional feature vector composed of both biochemical indicator and the quantized image features is defined and used as input to the Bayesian network, so as to establish a more accurate and reliable osteosarcoma recognition probability model. Experimental results demonstrate the effective of our method, there are 50 training samples and 30 testing samples, and the accuracy is up to 86.67%, which close to the expert diagnosis.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 543-547)

Pages:

2901-2904

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.543-547.2901

Citation:

Cite this paper

Online since:

March 2014

Authors:

Wen Bo Huang*, Yun Ji Wang

Keywords:

Bayesian Classifier, Bayesian Network (BN), Feature Extraction, Fuzzy C-Means (FCM) Clustering, Osteosarcoma Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Ottaviani G, Jaffe N. The epidemiology of osteosarcoma[M]/Pediatric and Adolescent Osteosarcoma. Springer US, 2010: 3-13.

Google Scholar

[2] Van Lung H, Kim J M. A generalized spatial fuzzy c-means algorithm for medical image segmentation[C]/Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on. IEEE, 2009: 409-414.

DOI: 10.1109/fuzzy.2009.5276878

Google Scholar

[3] Li Y, Shen Y. An automatic fuzzy c-means algorithm for image segmentation[J]. Soft Computing, 2010, 14(2): 123-128.

DOI: 10.1007/s00500-009-0442-0

Google Scholar

[4] Wang X Y, Bu J. A fast and robust image segmentation using FCM with spatial information[J]. Digital Signal Processing, 2010, 20(4): 1173-1182.

DOI: 10.1016/j.dsp.2009.11.007

Google Scholar

[5] M. Rajeswari, O.M. Alia, C. Bong, D. Ramachandram, M.E. Aziz, and I.L. Shuaib, Osteosarcoma segmentation in MRI using dynamic Harmony Search based clustering, IEEE, 2010 International Conference of Soft Computing and Pattern Recognition, 2010, 423-429.

DOI: 10.1109/socpar.2010.5686624

Google Scholar

[6] Peter J. F. Lucas. Expert Knowledge and Its Role in Learning Bayesian Networks in Medicine: An Appraisal. AIME 2001, 156-166.

Google Scholar