5. Conclusions and further research

methods, there exists an optimal coefficient such that the classification accuracy reaches its

Figure 8. Classification accuracies as a function of the interpolation coefficient k in Eqs. (1) and (2), when we trained the LeNet-5 using the augmented datasets and tested the classifier using the original dataset. The augmented datasets are

dataset 3 with spatial domain interpolation and dataset 4 with feature domain interpolation, respectively.

170 Machine Learning - Advanced Techniques and Emerging Applications

It can be seen in Figure 9 that by using the classifier trained on the original dataset, we might get very low (below 80%) classification accuracy on the input images in the augmented dataset (obtained using interpolation in the spatial domain). This highlights the importance of using data augmentation in order to attain a more balanced estimation of the generalization ability of the classifier. This generalization ability seems to depend heavily on the varying new image samples that were interpolated using a different interpolation (mixing) coefficient from the original dataset (e.g., when k ¼ 0:7, the accuracy can reach about 99%). Figure 9 also shows that Dataset 4 (feature domain interpolation) seems to be a less challenging dataset than Dataset 3 (spatial domain interpolation), in that all accuracies are above 95%, possibly suggesting that mixing images using their features extracted by the stacked autoencoder would generate less diverse images than directly mixing images in the spatial

maximum.

domain.

Malaria is a widespread disease that has claimed millions of lives all over the world. Automation of the diagnosis process will provide accurate diagnosis of the disease, which will benefit health-care to resource-scarce areas. We showed that the deep convolutional network based on LeNet-5 was capable of achieving very high classification accuracies for automated malaria diagnosis, by automatically learn the features from the input image data. We briefly described the workflow of classification of the red blood cell images, and discussed in details the data augmentation methods we proposed to deal with the issue with training deep convolutional neural networks with a small dataset. We then compared the classification accuracies associated with training, validating, and testing with various combinations of the original dataset and the significantly augmented datasets, which were obtained using direct interpolation in the spatial domain, as well as indirect interpolation using automatically extracted features provided by stacked autoencoders. This comparative study indicated that data augmentation in the feature domain seemed to be more robust in terms of preserving the high classification accuracies. We plan to expand the existing dataset by including more pathologist-curated cell images and further evaluate the effectiveness of the proposed data augmentation methods.

[10] Consortium for Open Medical Image Computing. ISBI Challenge on Cancer Metastasis Detection in Lymph Node. Available: http://grand-challenge.org/site/camelyon16/data/

Classification of Malaria-Infected Cells Using Deep Convolutional Neural Networks

http://dx.doi.org/10.5772/intechopen.72426

173

[11] Microsoft Corporation. Deep Zoom. Available: https://msdn.microsoft.com/en-us/library/

[12] Delahunt CB, Mehanian C, Hu L, McGuire SK, Champlin CR, Horning MP, et al. Automated microscopy and machine learning for expert-level malaria field diagnosis. In: Global Humanitarian Technology Conference (GHTC). 2015 IEEE; 2015. pp. 393-399 [13] Muralidharan V, Dong Y, Pan WD. Comparison of feature selection techniques for machine learning based automatic malarial cell recognition in wholeslide images. In: Proc. of IEEE International Conference on Biomedical and Health Informatics. Las Vegas,

[14] Park HS, Rinehart MT, Walzer KA, Chi JTA, Wax A. Automated detection of P. falciparum using machine learning algorithms with quantitative phase images of unstained cells. PLoS

[15] Sanchez CS. Deep Learning for Identifying Malaria Parasites in Images. MSc Thesis.

[16] Quinn JA, Nakasi R, Mugagga PKB, Byanyima P, Lubega W, Andama A. Deep convolutional neural networks for microscopy-based point of care diagnostics. CoRR. 2016;

[17] Muralidharan V, Dong Y, Pan WD. A comparison of feature selection methods for machine learning based automatic malarial cell recognition in wholeslide images. In: 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI);

[18] Mamoshina P, Vieira A, Putin E, Zhavoronkov A. Applications of deep learning in biomedicine. Molecular Pharmaceutics. 2016;13(5):1445-1454. PMID: 27007977. Available

[19] Leung MKK, Delong A, Alipanahi B, Frey BJ. Machine learning in genomic medicine: A review of computational problems and data sets. Proceedings of the IEEE. 2016 Jan;104(1):

[20] Min S, Lee B, Yoon S. Deep learning in bioinformatics. Briefings in Bioinformatics. 2017 Sep

[21] Greenspan H, van Ginneken B, Summers RM. Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique. IEEE Transactions

[22] Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging. 2016 May;35(5):1285-1298

cc645050(VS.95).aspx

One. 2016;11(9):e0163045

2016. pp. 216-219

176-197

1;18(5):851-869

Edinburgh, UK: University of Edinburgh; 2015

from:. DOI: 10.1021/acs.molpharmaceut.5b00982

on Medical Imaging. 2016 May;35(5):1153–1159

abs/1608.02989. Available from: http://arxiv.org/abs/1608.02989

NV; 2016
