Comparison of Several ANN Architectures on the Thyroid Diseases Grades Diagnosis

Nowadays, with advancement of technology and science and expansion of computer usage in high-tech calculations, especially in the field of medicine, intelligence systems and in particular ANN are becoming of significant importance in automatic diagnosis and prognoses of different diseases. In this article, we have used several ANN architectures (namely RBF, PNN, LVQ) and SVMs, diagnosing thyroid diseases. As the degree of disease development is a critical parameter in medical treatment, we design those networks to classify the grade of diseases, too. The performance of each of them has studied and the best method is selected for each of classification tasks. The overall accuracy of diagnosis system is near 99%.

[1]  Massimo Buscema,et al.  Artificial neural networks in the recognition of the presence of thyroid disease in patients with atrophic body gastritis. , 2008, World journal of gastroenterology.

[2]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[3]  Carine Maenhaut,et al.  The phylogeny, ontogeny, anatomy and regulation of the iodine metabolizing thyroid , 2005 .

[4]  Tulay Yildirim,et al.  Diagnosis of thyroid disease using artificial neural network methods , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[5]  E. El-Darzi,et al.  Statistical Comparison of a Probabilistic Neural Network Approach in Hepatic Cancer Diagnosis , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

[6]  M Yearworth,et al.  Artificial neural networks in diagnosis of thyroid function from in vitro laboratory tests. , 1993, Clinical chemistry.

[7]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[8]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[9]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.