Data Mining Techniques in Computer-Aided Diagnosis: Non-Invasive Cancer Detection

Diagnosis can be achieved by building a model of a certain organ under surveillance and comparing it with the real time physiological measurements taken from the patient. This paper deals with the presentation of the benefits of using Data Mining techniques in the computer-aided diagnosis (CAD), focusing on the cancer detection, in order to help doctors to make optimal decisions quickly and accurately. In the field of the noninvasive diagnosis techniques, the endoscopic ultrasound elastography (EUSE) is a recent elasticity imaging technique, allowing characterizing the difference between malignant and benign tumors. Digitalizing and summarizing the main EUSE sample movies features in a vector form concern with the use of the exploratory data analysis (EDA). Neural networks are then trained on the corresponding EUSE sample movies vector input in such a way that these intelligent systems are able to offer a very precise and objective diagnosis, discriminating between benign and malignant tumors. A concrete application of these Data Mining techniques illustrates the suitability and the reliability of this methodology in CAD.

Authors:

• Florin Gorunescu

Keywords:

• Endoscopic ultrasound elastography
• exploratorydata analysis
• neural networks
• non-invasive cancer detection.

References:

[1] M. Giovannini, L. Hookey, E. Bories et al., "Endoscopic ultrasound
elastography: the first step towards virtual biopsy? Preliminary results in
49 patients," Endoscopy, vol. 38, pp. 344-348, 2006.
[2] W. Rasband, "ImageJ: image processing and analysis in JAVA",
National Institutes of Health (Available: http://rsb.info.nih.gov/ij/).
[3] A. Saftoiu., P. Vilmann, H. Hassan, and F. Gorunescu, "Analysis of
endoscopic ultrasound elastography used for characterization and
differentiation of benign and malignant lymph nodes", Ultraschall in der
Medizin (European Journal of Ultrasound), vol 27, no. 6, pp. 535-542,
2006.
[4] A. Saftoiu, C. Popescu, S. Cazacu, D. Dumitrescu, C.V. Georgescu, M.
Popescu, T. Ciurea, and F. Gorunescu, "Power Doppler Endoscopic
Ultrasound for the Differential Diagnosis between Pancreatic Cancer and
Pseudotumoral Chronic Pancreatitis", Journal of Ultrasound in
Medicine, vol. 25, no. 3, pp. 363-372, 2006.
[5] A. Saftoiu, P. Vilmann, T. Ciurea, G.L. Popescu, A. Iordache, H.
Hassan, F. Gorunescu, S. Iordache, "Dynamic analysis of endoscopic
ultrasound (EUS) elastography used for the differentiation of benign and
malignant lymph nodes", Gastrointestinal Endoscopy, vol. 66, no. 2, pp.
291-300, 2007.
[6] S. Haykin, Neural Networks. Prentice Hall International, 1999.