Performance study of augmentation techniques for HEp2 CNN classification

Computers have been playing an important role in the medical field. More specifically in the field of computer aided diagnoses. Moreover, making computers and human work together, in the medical field, not only makes it easy for medical experts to do their tasks, but also makes their work more accurate. That is the main motivation of the growing utilization of advanced computer techniques such as machine learning and artificial intelligence in the medical field. In this proposed work, we use the recent machine learning framework that is implemented in the latest MATLAB[1] version to classify HEp2 cell images. Which is one of the difficult classification tasks for a computer due to the low resolution, amount of details, and also to how similar the different classes are from each other. We make an intense study for pre-augmentation and real-time augmentation that is built-in the latest MATLAB version. In this work we use Convolutional Neural Network (CNN) with some of the state of the art techniques that proved significant improvements over older classical architectures. The proposed work has achieved 98.29% validation accuracy in only 10 epochs of training.

[1]  LinLin Shen,et al.  A Deep Residual Inception Network for HEp-2 Cell Classification , 2017, DLMIA/ML-CDS@MICCAI.

[2]  D. Hubel,et al.  Receptive fields of single neurones in the cat's striate cortex , 1959, The Journal of physiology.

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[6]  Lei Wang,et al.  HEp-2 Cell Image Classification with Convolutional Neural Networks , 2014 .

[7]  LinLin Shen,et al.  Deep convolutional neural network based HEp-2 cell classification , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

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

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

[10]  Lei Wang,et al.  HEp-2 Cell Image Classification With Deep Convolutional Neural Networks , 2015, IEEE Journal of Biomedical and Health Informatics.

[11]  Alessia Saggese,et al.  Pattern recognition in stained HEp-2 cells: Where are we now? , 2014, Pattern Recognit..

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

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

[14]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Shan Suthaharan,et al.  Support Vector Machine , 2016 .

[16]  Demis Hassabis,et al.  Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm , 2017, ArXiv.

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

[18]  William Stafford Noble,et al.  Support vector machine , 2013 .

[19]  Juho Kannala,et al.  Human Epithelial Type 2 cell classification with convolutional neural networks , 2015, 2015 IEEE 15th International Conference on Bioinformatics and Bioengineering (BIBE).

[20]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

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

[22]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[23]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[24]  Yongkang Wong,et al.  Automatic Classification of Human Epithelial Type 2 Cell Indirect Immunofluorescence Images using Cell Pyramid Matching , 2014 .

[25]  Matti Pietikäinen,et al.  Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2000, ECCV.

[26]  Mario Vento,et al.  Benchmarking HEp-2 Cells Classification Methods , 2013, IEEE Transactions on Medical Imaging.

[27]  P. Schur,et al.  ANA screening: an old test with new recommendations , 2010, Annals of the rheumatic diseases.