A Novel T-CAD Framework to Support Medical Image Analysis and Reconstruction
The current medical imaging devices allow to obtain high resolution digital images with a complex informative content expressed by the textural skin that covers organs and tissues (hereinafter objects). These textural information can be exploited to develop a descriptive mathematical model of the objects by which to support heterogeneous activities within the medical field.
This paper describes our developed framework based on the texture analysis by which to mathematically model every object contained in the layout of the total body NMR images. By every specific model, the framework automatically also defines a connected application which supports, on the related object, different fixed targets, such as: segmentation, mass detection, reconstruction, and so on.
KeywordsFramework CAD medical image texture analysis pattern recognition feature extraction segmentation classification
- 1.Avola, D., Cinque, L.: Encephalic NMR Image Analysis by Textural Interpretation. In: Avanzi, R.M., Keliher, L., Sica, F. (eds.) Proceedings of the 2008 ACM Symposium on Applied Computing, SAC 2008. LNCS, March 16–20, pp. 1338–1342. ACM Press, New York (2009)Google Scholar
- 3.Avola, D., Cinque, L., Di Girolamo, M.: Texture Based Approches to Support Medical Image Analysis. Internal Technical Report in Medical Image Proessing. DSI - Sapienza University of Rome, ITR-MIP 2010, Int. Res. on Medical Imaging (2010)Google Scholar
- 5.Li, Q., Shi, Z.: Texture Image Retrieval Using Compact Texton Co-Occurrence Matrix Descriptor. In: Proceedings of the 11th ACM International Conference on Multimedia Information Retrieval, MIR 2010, March 29-31, pp. 83–90. ACM Press, Philadelphia (2010)Google Scholar
- 6.Histace, A., Matuszewski, B., Zhang, Y.: Segmentation of Myocardial Boundaries in Tagged Cardiac MRI Using Active Contours: A Gradient-Based Approach Integrating Texture Analysis. International Journal of Biomedical Imaging, IJBI 2009, 1–8 (2009)Google Scholar
- 7.Niranjan, J., Michael, B.: Non-Parametric Mixture Model Based Evolution of Level Sets and Application to Medical Image. International Journal of Computer Vision, IJCV 2010 1(88), 52–68 (2010)Google Scholar
- 8.Wu, J., Poehlman, S., Noseworthy, M.D., Kamath, M.V.: Texture Feature Based Automated Seeded Region Growing in Abdominal MRI Segmentation. Journal in Biomed. Sc. and Eng., JBiSE 2009 2, 1–8 (2009)Google Scholar
- 9.Schmid, J., Kim, J., Magnenat-Thalmann, N.: Robust Statistical Shape Models for MRI Bone Segmentation in Presence of Small Field of View. International Journal of Medical Image Analysis, IJMIA 2011 15(1), 155–168 (2011)Google Scholar
- 10.Tesar, L., Smutek, D., Shimizu, A., Kobatake, H.: Medical Image Segmentation Using Co-Occurrence Matrix Based Texture Features Calculated on Weighted Region. In: Proceedings of the 3rd Conference on IASTED International Conference: Advances in Computer Science and Technology, ACST 2007, pp. 243–248. ACTA Press, Phuket (2007)Google Scholar