An approach to classification of data with highly localized unmarked features using neural networks

Rafał Wojciech Grzeszczuk

Abstract


To face the increasing demand on quality healthcare, cutting edge automation technology is being applied in such demanding areas as medical imaging. This paper proposes a novel approach to classification problems on datasets with sparse, highly localized features. It is based on the use of saliency map in amplification of features. Unlike previous efforts, this approach does not use any prior information about feature localization. We present an experimental study based on Diabetic Retinopathy classification problem, in which our method has shown to achieve over 20\% higher accuracy in solving a two-class Diabetic Retinopathy classification problem  than a naive approach based solely on residual neural networks. The dataset consists of 35120 images of various quality, inconsistent resolution and aspect ratio.

Keywords


saliency map; feature extraction; localized features

Full Text:

PDF

References


Leon Bottou. Stochastic learning. In Advanced lectures on machine learning,

pages 146-168. Springer, 2004.

Jacob Cohen. A coeffcient of agreement for nominal scales. Educational and

psychological measurement, 20(1):37-46, 1960.

Corinna Cortes and Vladimir Vapnik. Support vector machine. Machine learning,

(3):273-297, 1995.

B Aruna Devi and M Pallikonda Rajasekaran. Performance evaluation of mri

pancreas image classication using articial neural network (ann). In Smart

Intelligent Computing and Applications, pages 671-681. Springer, 2019.

EyePACS. Public diabetic retinopathy dataset. www.kaggle.com/c/diabetic-

retinopathy-detection, 2015.

Mrinal Haloi. Improved microaneurysm detection using deep neural networks.

arXiv preprint arXiv:1505.04424, 2015.

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Spatial pyramid pool-

ing in deep convolutional networks for visual recognition. In European Conference

on Computer Vision, pages 346-361. Springer, 2014.

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning

for image recognition. In Proceedings of the IEEE conference on computer vision

and pattern recognition, pages 770-778, 2016.

Nikola K Kasabov. Neucube: A spiking neural network architecture for mapping,

learning and understanding of spatio-temporal brain data. Neural Networks,

:62-76, 2014.

Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. The cifar-10 dataset. online:

http://www.cs.toronto.edu/kriz/cifar. html, 2014.

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classication

with deep convolutional neural networks. In Advances in neural information

processing systems, pages 1097-1105, 2012.

Jinsa Kuruvilla and K Gunavathi. Lung cancer classication using neural net-

works for ct images. Computer methods and programs in biomedicine, 113(1):202-

, 2014.

Gilbert Lim, Mong-Li Lee, Wynne Hsu, and Tien Yin Wong. Transformed rep-

resentations for convolutional neural networks in diabetic retinopathy screening.

In AAAI Workshop: Modern Articial Intelligence for Health Analytics, 2014.

Martina Melinscak, Pavle Prentasic, and Sven Loncaric. Retinal vessel segmenta-

tion using deep neural networks. In VISAPP 2015 (10th International Conference

on Computer Vision Theory and Applications), 2015.

Mohd Fauzi Othman and Mohd Arianan Mohd Basri. Probabilistic neural net-

work for brain tumor classication. In Intelligent Systems, Modelling and Simu-

lation (ISMS), 2011 Second International Conference on, pages 136-138. IEEE,

Robert W Rodieck. The vertebrate retina: principles of structure and function.

Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Net-

works for Biomedical Image Segmentation, pages 234-241. Springer International

Publishing, Cham, 2015.

Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. Deep inside convolu-

tional networks: Visualising image classication models and saliency maps. arXiv

preprint arXiv:1312.6034, 2013.

Jonathan Tompson, Ross Goroshin, Arjun Jain, Yann LeCun, and Christoph

Bregler. Efficient object localization using convolutional networks. In The IEEE

Conference on Computer Vision and Pattern Recognition (CVPR), June 2015.

Gulshan V, Peng L, Coram M, and et al. Development and validation of a

deep learning algorithm for detection of diabetic retinopathy in retinal fundus

photographs. JAMA, 316(22):2402-2410, 2016.

CP Wilkinson, Frederick L Ferris, Ronald E Klein, Paul P Lee, Carl David

Agardh, Matthew Davis, Diana Dills, Anselm Kampik, R Pararajasegaram,

Juan T Verdaguer, et al. Proposed international clinical diabetic retinopathy

and diabetic macular edema disease severity scales. Ophthalmology, 110(9):1677-

, 2003.

Wong Li Yun, U. Rajendra Acharya, Y.V. Venkatesh, Caroline Chee, Lim Choo

Min, and E.Y.K. Ng. Identication of different stages of diabetic retinopathy

using retinal optical images. Information Sciences, 178(1):106 - 121, 2008.




DOI: https://doi.org/10.7494/csci.2019.20.3.3343

Refbacks

  • There are currently no refbacks.