Superior Performances of the Neural Network on the Masses Lesions Classification through Morphological Lesion Differences

Authors: U. Bottigli, R.Chiarucci, B. Golosio, G.L. Masala, P. Oliva, S.Stumbo, D.Cascio, F. Fauci, M. Glorioso, M. Iacomi, R. Magro, G. Raso

Abstract:

Purpose of this work is to develop an automatic classification system that could be useful for radiologists in the breast cancer investigation. The software has been designed in the framework of the MAGIC-5 collaboration. In an automatic classification system the suspicious regions with high probability to include a lesion are extracted from the image as regions of interest (ROIs). Each ROI is characterized by some features based generally on morphological lesion differences. A study in the space features representation is made and some classifiers are tested to distinguish the pathological regions from the healthy ones. The results provided in terms of sensitivity and specificity will be presented through the ROC (Receiver Operating Characteristic) curves. In particular the best performances are obtained with the Neural Networks in comparison with the K-Nearest Neighbours and the Support Vector Machine: The Radial Basis Function supply the best results with 0.89 ± 0.01 of area under ROC curve but similar results are obtained with the Probabilistic Neural Network and a Multi Layer Perceptron.

Keywords: Neural Networks, K-Nearest Neighbours, Support Vector Machine, Computer Aided Detection

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1055441

References:

[1] Smith R.A., "Epidemiology of breast cancer", in "A categorical course in physics. Imaging considerations and medical physics responsibilities", Madison, Wisconsin, Medical Physics Publishing, 1991.
[2] Peto R., Boreham J., Clarke m., Davies c., Deral V, correspondence "UK and USA Breast cancer deaths down 25% in year 2000 at ages 20-69 years", LANCET 2000, 355, (9217) pp. 1822-1823, 2000.
[3] Bird R., Wallace T., Yankaskas B., “Analysis of cancer missed at screening mammography", Radiology 1992: 184; pp.613-617, 1992.
[4] Haus A.G. and Yaffe M. (editors), "A categorical course in physics. Technical aspects in breast imaging". Radiological Society of North America, Presented at the 79th Scientific Assembly and Annual Meeting of RSNA, 1993.
[5] Feig S.A. , Yaffe M. , "Digital mammography, computer aided diagnosis and telemammography", Radiol. Clin. N. Am. 33, 1205-1230, 1995.
[6] Keddache S., Thilander-Klang A., Lanhede B. , "Storage phosphor and film screen mammography: performance with different mammographic techniques" Eur. Radiol. 9, 591-597, 1999.
[7] Schmidt R.A., Nishikawa R.M. , "Clinical use of digital mammography: the presents and the perspects", Digit. Imaging 8/1 suppl. 74-79, 1995.
[8] Karssemejer N., "A stochastic method for automated detection of microcalcifications in digital mammograms" in Information processing in medical imaging, Springer-Verlag New York, 227-238, 1991.
[9] Karssmejer N. , "Reading screening mammograms with the help of neural networks", Nederlands Tijdschriff geneeskd, 143/45, 2232-2236, 1999.
[10] 10.C.J. Viborny, M.L. Giger, "Computer vision and artificial intelligence in mammography", AJR 162, 699-708, 1994.
[11] Bottigli U, Delogu P, Fantacci ME, Fauci F, Golosio B, Lauria A, Palmiero R, Raso G, Stumbo S, Tangaro S Search of Microcalcification clusters with the CALMA CAD station. The International Society for Optical Engineering (SPIE) 4684: 1301-1310, 2002
[12] F. Fauci, S. Bagnasco, R. Bellotti, D. Cascio, S. C. Cheran, F. De Carlo, G. De Nunzio, M. E. Fantacci, G. Forni, A. Lauria, E.Lopez Torres, R. Magro, G. L. Masala, P.Oliva, M. Quarta, G. Raso, A. Retico, S.Tangaro, Mammogram Segmentation by Contour Searching and Massive Lesion Classification with Neural Network, Proc. IEEE Medical Imaging Conference, October 16-22 2004, Rome, Italy; M2- 373/1-5, 2004.
[13] S. Haykin “Neural Networks - A comprehensive foundation", second edition, Prentice Hall, 1999.
[14] Massimo Buscema & Semeion Group, “Reti Neurali artificiali e sistemi sociali complessi", volume 1 Teoria e modelli 1409.1, Franco Angeli, 1999.
[15] S. Serpico, G. Vernazza, “Teorie e tecniche del riconoscimento", CUSL “Il gabbiano", 1997.
[16] O. Duda, P. E. Hart, D. G. Stark, “Pattern Classification“, second edition, A Wiley-Interscience Publication John Wiley & Sons, 2001.
[17] S. J. Russel, P.Norvig, “Artificial Intelligence. A modern approach", UTET, 1998.
[18] V. N. Vapnik. “Statistical Learning Theory. Wiley", New York , 1998.
[19] M. Pontil, A. Verri “Properties of Support Vector Machines", Neural Computation, Vol. 10, pp 955-974, 1998.
[20] N. Cristianini, J. Shave-Taylor. “An Introduction to Support Vector Machine"(and other kernel-based learning methods). Cambridge University Press 2000.
[21] SVM_light software is available in the following location : ftp://ftp-ai.cs.unidortmund.de/pub/Users/thorsten/svm_light/current/ svm_light.tar.gz
[22] T. Joachims, Text Categorization with Support Vector Machines: Learning with Many Relevant Features, Proc. 10th European Conf. Machine Learning (ECML), Springer-Verlag, 1998.
[23] T. Mitchell “Machine Learning" , McGraw-Hill 1997.
[24] Timp S., Karssemeijer N., A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography, Medical Physics: 31; 958-971, 2004.
[25] Baydush A.H., Catarious D.M., Abbey C.K., Floyd C.E., Computer aided detection of masses in mammography using subregion Hotelling observers, Medical Physics: 30; 1781-1787, 2003.
[26] Tourassi G.D., Vargas-Voracek R., Catarious D.M. Jr, Floyd C.E. Jr, Computer-assisted detection of mammographic masses: A template matching scheme based on mutual information, Medical Physics: 30 (8); 2123-2130, 2003.
[27] Antonie M.L., Zaiane O.R., Coman A., Application of data mining techniques for medical image classification, Proc. of II Int. Work. On Multimedia Data Mining, USA, 2001.
[28] Vyborny CJ., Giger ML., Computer vision and artificial intelligence in mammography, AJR: 162; 699-708, 1994.
[29] Lai S., Li X., Bischof W., On techniques for detecting circumscribed masses in mammograms", IEEE Transaction on Medical Imaging: 8(4); 377-386, 1989.
[30] Aapo Hyv┬¿arinen, Erkki Oja, “Indipendent Component Analysis: Algorithms and Applications", Neural Networks Research Centre, Helsinki University of Technology, Finland, “Neural Networks", 13 (4- 5):411-430, 2000.
[31] Hanley JA, McNeil B, The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology: 143; 29-36, 1982.
[32] Hanley JA, McNeil B, A method of comparing the areas under receiver operating characteristic curves derived from the same cases, Radiology: 148; 839-843, 1983.
[33] U. Bottigli, B. Golosio, G. L. Masala, P. Oliva, S. Stumbo, D. Cascio, F. Fauci, R. Magro, G. Raso, R. Bellotti, F. De Carlo, S.Tangaro, I. De Mitri, G. De Nunzio, M. Quarta, A. Preite Martinez, P. Cerello, S. C. Cheran, E.Lopez Torres “Dissimilarity Application for Medical Imaging Classification" on proceedings of The 9th World Multi-Conference on Systemics, Cybernetics and Informatics WMSCI 2005, Orlando 10-13 July 2005, vol III pag 258-262, 2005.
[34] G. Masala, B. Golosio, D. Cascio, F. Fauci, S. Tangaro, M. Quarta, S. Cheran, E. L. Torres, “Classifiers trained on dissimilarity representation of medical pattern: a comparative study" on Nuovo Cimento C, Vol. 028, Issue 06, pp 905-912 , 2005.