Approach to classifying data with highly localized unmarked features using neural networks

• Autorzy: Grzeszczuk Rafał

Identyfikatory

DOI

10.7494/csci.2019.20.3.3343

• Języki publikacji: EN

Abstrakty

EN

To face the increasing demand of quality healthcare, cutting-edge automation technology is being applied in demanding areas such 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 a saliency map in the amplification of features. Unlike previous efforts, this approach does not use any prior information about feature localization. We present an experimental study based on the Diabetic Retinopathy classification problem, in which our method has shown to achieve an 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 35,120 images of various qualities, inconsistent resolutions, and aspect ratios.

Słowa kluczowe

EN

classification; neural networks; medical image analysis

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2019
• Tom: Vol. 20 (3)
• Strony: 329--342
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Grzeszczuk Rafał

• AGH University of Science and Technology, Department of Computer Science, Krakow, Poland

Bibliografia

• [1] Bottou L.: Stochastic learning. In: Advanced lectures on machine learning, Springer, pp. 146-168, 2004.
• [2] Cohen J.: A coefficient of agreement for nominal scales, Educational and psychological measurement, vol. 20(1), pp. 37-46, 1960.
• [3] Cortes C., Vapnik V.: Support vector machine, Machine learning, vol. 20(3), pp. 273-297, 1995.
• [4] Devi B.A., Rajasekaran M.P.: Performance evaluation of MRI pancreas image classification using artifficial neural network (ANN). In: Smart Intelligent Computing and Applications, Springer, pp. 671-681, 2019.
• [5] EyePACS: Public diabetic retinopathy dataset, 2015 www.kaggle.com/c/diabe tic-retinopathy-detection.
• [6] Gulshan V., Peng L., Coram M., et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, JAMA, vol. 316(22), pp. 2402-2410, 2016. https://doi.org/10.100 1/jama.2016.17216.
• [7] Haloi M.: Improved microaneurysm detection using deep neural networks. In: arXiv preprint arXiv:1505.04424, 2015.
• [8] He K., Zhang X., Ren S., Sun J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: European Conference on Computer Vision, Springer, pp. 346-361, 2014.
• [9] He K., Zhang X., Ren S., Sun J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016.
• [10] Kasabov N.K.: NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data, Neural Networks, vol. 52, pp. 62-76, 2014
• [11] Krizhevsky A., Nair V., Hinton G.: The CIFAR-10 dataset, 2014. http://www. cs.toronto.edu/kriz/cifar.html.
• [12] Krizhevsky A., Sutskever I., Hinton G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097-1105, 2012.
• [13] Kuruvilla J., Gunavathi K.: Lung cancer classification using neural networks for CT images, Computer Methods and Programs in Biomedicine, vol. 113(1), pp. 202-209, 2014.
• [14] Lim G., Lee M.L., Hsu W., Wong T.Y.: Transformed Representations for Convolutional Neural Networks in Diabetic Retinopathy Screening. In: AAAI Work- shop: Modern Artifficial Intelligence for Health Analytics, 2014.
• [15] Melinscak M., Prentasic P., Loncaric S.: Retinal vessel segmentation using deep neural networks. In: VISAPP 2015 (10th International Conference on Computer Vision Theory and Applications), 2015.
• [16] Othman M.F., Basri M.A.M.: Probabilistic neural network for brain tumor classification. In: Intelligent Systems, Modelling and Simulation (ISMS), 2011 Second International Conference on, pp. 136-138. IEEE, 2011.
• [17] Rodieck R.W.: The vertebrate retina: principles of structure and function. In: , 1973.
• [18] Ronneberger O., Fischer P., Brox T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, Springer International Publishing, Cham, pp. 234-241, 2015. http://dx.doi.org/10.1007/978-3-319-24574-4 28.
• [19] Simonyan K., Vedaldi A., Zisserman A.: Deep inside convolutional networks: Visualising image classification models and saliency maps. In: arXiv preprint arXiv:1312.6034, 2013.
• [20] Tompson J., Goroshin R., Jain A., LeCun Y., Bregler C.: Efficient Object Localization Using Convolutional Networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
• [21] Wilkinson C., Ferris F.L., Klein R.E., Lee P.P., Agardh C.D., Davis M., Dills D., Kampik A., Pararajasegaram R., Verdaguer J.T., et al.: Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales, Ophthalmology, vol. 110(9), pp. 1677-1682, 2003.
• [22] Yun W.L., Acharya U.R., Venkatesh Y., Chee C., Min L.C., Ng E.: Identification of different stages of diabetic retinopathy using retinal optical images, Information Sciences, vol. 178(1), pp. 106-121, 2008. https://doi.org/10.1016/j.in s.2007.07.020.