Iris nevus diagnosis: convolutional neural network and deep belief network

This work presents the diagnosis of iris nevus using a convolutional neural network (CNN) and deep belief network (DBN). Iris nevus is a pigmented growth (tumor) found in the front of the eye or around the pupil. It is seen that racial and environmental factors affect the iris color (e.g., blue, hazel, brown) of patients; hence, pigmented growths may be masked in the eye background or iris. In this work, some image processing techniques are applied to images to reinforce areas of interests in them, after which the considered classi ers are trained. We describe the automated diagnosis of iris nevus using neural network-based systems for the classi cation of eye images as nevus affected" and unaffected". Recognition rates of 93.35% and 93.67% were achieved for the CNN and DBN, respectively. Hence, the systems described in this work can be used satisfactorily for diagnosis or to reinforce the con dence in manual-visual diagnosis by medical experts.

PDF

___

[1] Shields CL, Kaliki S, Hutchinson A, Nickerson S, Patel J, Kancherla S, Peshtani A, Nakhoda S, Kocher K, Kolbus E et al. Iris nevus growth into melanoma: analysis of 1611 consecutive eyes. Ophthalmology 2013; 120: 766-772.
[2] Oyedotun OK, Olaniyi EO, Helwan A, Khashman A. Decision support models for iris nevus diagnosis considering potential malignancy. International Journal of Scienti c & Engineering Research 2014; 5: 419-426.
[3] Li W, Jia F, Hu Q. Automatic segmentation of liver tumor in CT images with deep convolutional neural networks. Journal of Computer and Communications 2015; 3: 146-151.
[4] Syafeeza AR, Khalil-Hani M, Liew SS, Bakhteri R. Convolutional neural networks with fused layers applied to face recognition. International Journal of Computational Intelligence and Applications 2015; 14: 1550014.
[5] Dieleman S, Willett KW, Dambre J. Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon Not R Astron Soc 2015; 450: 1441-1459.
[6] Lawrence S, Giles CL, Tsoi AC, Back AD. Face recognition: a convolutional neural network approach. IEEE T Neural Networ 1997: 98-113.
[7] Doorn J. Analysis of deep convolutional neural network architectures. In: 21st Twente Student Conference on IT; 23 June 2014; Enschede, the Netherlands. pp. 3-5.
[8] Nagi J, Ducatelle F, Di Caro G, Ciresan D, Meier U, Giusti A, Nagi F, Schmidhuber J, Gambardella LM. Max- pooling convolutional neural networks for vision based hand gesture recognition. In: IEEE International Conference on Signal and Image Processing Applications; 16{18 November 2011; Kuala Lumpur, Malaysia. New York, NY, USA: IEEE. pp. 343-349.
[9] Bouvrie J. Notes on Convolutional Neural Networks. Cambridge, MA, USA: Center for Biological and Computational Learning of Massachusetts Institute of Technology, 2006.
[10] Masci J, Meier U, Ciresan DC, Schmidhuber J. Stacked convolutional auto-encoders for hierarchical feature extrac- tion. Lect Notes Comp Sci 2011; 6791: 52-59.
[11] Ciresan DC, Meier U, Masci U, Gambardella LM, Schmidhuber J. Flexible, high performance convolutional neural networks for image classi cation. In: Proceedings of the 22nd International Joint Conference on Arti cial Intelli- gence; 16{22 July 2011; Barcelona, Spain. pp. 1238-1243.
[12] Scherer D, Muller A, Behnke S. Evaluation of pooling operations in convolutional architectures for object recognition. In: 20th International Conference on Arti cial Neural Networks; 15{18 September 2010; Thessaloniki, Greece. pp. 1-6.
[13] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. P IEEE 1998; 8: 2278-2324.
[14] Yu D, Wang H, Chen P, Wei Z. Mixed pooling for convolutional neural networks. In: 9th International Conference on Rough Sets and Knowledge Technology; 24{26 October 2014; Shanghai, China. pp. 364-375.
[15] Oyedotun OK, Olaniyi EO, Khashman A. Deep learning in character recognition considering pattern invariance constraints. International Journal of Intelligent Systems and Applications 2015; 7: 1-10.
[16] Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput 2006; 18: 1527-1554.
[17] Deng L. An overview of deep-structured learning for information processing. In: Asia-Paci c Signal and Information Processing Association Annual Summit and Conference; 9{12 December 2014; Chiang Mai, Thailand: pp. 2-4.