Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images

Abstract. Convolutional neural networks (CNNs) have become the architecture of choice for visual recognition tasks. However, these models are perceived as black boxes since there is a lack of understanding of the learned behavior from the underlying task of interest. This lack of transparency is a serious drawback, particularly in applications involving medical screening and diagnosis since poorly understood model behavior could adversely impact subsequent clinical decision-making. Recently, researchers have begun working on this issue and several methods have been proposed to visualize and understand the behavior of these models. We highlight the advantages offered through visualizing and understanding the weights, saliencies, class activation maps, and region of interest localizations in customized CNNs applied to the challenge of classifying parasitized and uninfected cells to aid in malaria screening. We provide an explanation for the models’ classification decisions. We characterize, evaluate, and statistically validate the performance of different customized CNNs keeping every training subject’s data separate from the validation set.

[1]  Yuhang Dong,et al.  Evaluations of deep convolutional neural networks for automatic identification of malaria infected cells , 2017, 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[2]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Mildred L. Patten,et al.  One-Way Analysis of Variance (F) , 2017 .

[4]  Chandan Chakraborty,et al.  Machine learning approach for automated screening of malaria parasite using light microscopic images. , 2013, Micron.

[5]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[7]  Mahdieh Poostchi,et al.  Image analysis and machine learning for detecting malaria , 2018, Translational research : the journal of laboratory and clinical medicine.

[8]  G. R. K. Sai Subrahmanyam,et al.  Convolutional neural network‐based malaria diagnosis from focus stack of blood smear images acquired using custom‐built slide scanner , 2018, Journal of biophotonics.

[9]  Davide Chicco,et al.  Ten quick tips for machine learning in computational biology , 2017, BioData Mining.

[10]  B. Matthews Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[11]  François Chollet Deep Learning with Separable Convolutions , 2016 .

[12]  Hayit Greenspan,et al.  Chest pathology detection using deep learning with non-medical training , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[13]  R. Sivaramakrishnan,et al.  Visualizing abnormalities in chest radiographs through salient network activations in Deep Learning , 2017, 2017 IEEE Life Sciences Conference (LSC).

[14]  Harold D. Delaney,et al.  The Kruskal-Wallis Test and Stochastic Homogeneity , 1998 .

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Hilal Olgun Kucuk,et al.  Importance of using proper post hoc test with ANOVA. , 2016, International journal of cardiology.

[17]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[18]  J. Gastwirth,et al.  The impact of Levene’s test of equality of variances on statistical theory and practice , 2009, 1010.0308.

[19]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[20]  Charles Elkan,et al.  Optimal Thresholding of Classifiers to Maximize F1 Measure , 2014, ECML/PKDD.

[21]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[22]  Madhu S. Nair,et al.  Malaria Parasite Detection From Peripheral Blood Smear Images Using Deep Belief Networks , 2017, IEEE Access.

[23]  K. Mitiku,et al.  The reliability of blood film examination for malaria at the peripheral health unit , 2003 .

[24]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Kenji Suzuki,et al.  Overview of deep learning in medical imaging , 2017, Radiological Physics and Technology.

[26]  S. Bressler Large-scale cortical networks and cognition , 1995, Brain Research Reviews.

[27]  S. Daya,et al.  Issues in surgical therapy evaluation: technical skill of the surgeon , 2003 .

[28]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[29]  Joseph S. Rossi One-Way Anova from Summary Statistics , 1987 .

[30]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[31]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[32]  Honglak Lee,et al.  Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units , 2016, ICML.

[33]  Alexander Binder,et al.  Evaluating the Visualization of What a Deep Neural Network Has Learned , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[37]  Xiangji Huang,et al.  CNN-based image analysis for malaria diagnosis , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[38]  P. Royston Approximating the Shapiro-Wilk W-test for non-normality , 1992 .

[39]  David Barber,et al.  Nesterov's accelerated gradient and momentum as approximations to regularised update descent , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[40]  David M. Rubin,et al.  Automated image processing method for the diagnosis and classification of malaria on thin blood smears , 2006, Medical and Biological Engineering and Computing.