A Peripheral Blood WBC Classification with ConvolutionalNeural Network
Chen Chang1, Cheng Shaojie2, Li Weibin2 ,Chen Min2*
1Institute of Information Science and Technology,University of Science and Technology of China,Hefei 230022, China; 2The PLA Institute of Laboratory Medicine,Fuzhou General Hospital,Fuzhou 350025, China
Abstract：The automatic classification of white blood cell (WBC) image is essential because it helps to enhance the efficiency of clinical diagnosis and treatment. However, the classification accuracy is still need to be boost for adapting to practical applications. In this paper, we proposed an automatic classification method based on the convolution neural network (CNN). We tentatively fed our training dataset into AlexNet and LeNet using a widely used deep learning platform Caffe. Five classes of WBCs images collected by a CellaVision DM96 in peripheral blood smears were adopted as the training dataset. These manual labeled images were apportioned into three groups (training, validation and testing) randomly to construct the original dataset according to the proportion of 7：2∶1. With the augmentation methods, such as rotation and mirror, we expanded the original dataset. Stochastic gradient descent algorithm was adopted as the optimizing method for training CNNs. The experimental results demonstrated that the network structure of AlexNet was unsuitable to achieve the ideal classification accuracy which more than 95%. While the network structure of LeNet had achieved the expected target. However, the more massive and more time consuming of LeNet suggested us to further optimize the connection of layers to derive a new network with lightweight structure, named as CCNet. The model size, time for training, and time for evaluation of CCNet were only 1/1000, 1/3, and 1/30 compared with LeNet, respectively. The best classification accuracy of CCNet and LeNet for five classification of WBCs was 99.69% and 99.18% with 979 WBC images, higher than those of the previous reports. It demonstrated that CNNs especially CCNet had clear advantages than previous works both in classification accuracy and speed.
 Chabot-Richards DS,George TI. White blood cell counts- Reference methodology[J].Clin Lab Med,2015,35(1):11-24.
 Kim SJ, Kim Y, Shin S,et al.Comparison study of the rates of manual peripheral blood smear review from 3 automated hematology analyzers, UnicelDxH 800, ADVIA 2120i, and XE 2100 using international consensus group guidelines[J].Arch Pathol Lab Med, 2012,136(11): 1408-1413.
 Bain BJ.Diagnosis from the blood smear[J]. N Engl J Med, 2005; 353(5):498-507.
 Rabizadeh E,Pickholtz I,Barak M,et al.Acute leukemia detection rate by automated blood count parameters and peripheral smear review[J].Int J Lab Hem,2014,37(1):44-49.
 Da Costa L.Digital image analysis of blood cells[J]. Clin Lab Med, 2014,35(1):105-122.
 Mohammed EA,Mohamed MM,Far BH,et al.Peripheral blood smear image analysis:A comprehensive review[J].J Pathol Inform,2014,5(1):9.
 Sadeghian F,Seman Z,Ramli AR,et al.A Framework for white blood cell segmentationin microscopic blood images using digital image processing[J].Biol Proced Online, 2009,11(1):196-206.
 Ko BC,Gim JW,Nam JY.Automatic white blood cell segmentation using stepwise merging rules and gradient vector flow snake[J]. Micron,2011, 42(7):695-705.
 Mohapatra S,Patra D,Kumar K.Fast leukocyte image segmentation using shadowsets[J].Int J Comput Biol Drug Des, 2012,5(1):49-65.
 Pore YN,Kalshetty YR. Review on blood cell image segmentation and counting[J].International Journal of Application or Innovation in Engineering & Management,2014,3(11):369-372.
 Saraswat M,Arya KV.Automated microscopic image analysis for leukocytes identification:A survey[J]. Micron,2014;65:20-33.
 Su Muchun, Cheng Chunyen, Wang Pachun. Neural-network-based approach to white blood cell classification[J].Scientific World Journal,2014:796371.
 LeCun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
 Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks[C]// Proceedings of the 25th International Conference on Neural Information Processing. Lake Tahoe:Curran Associates Inc,2012:1097-1105.
 He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[EB/OL]. https://arxiv.org/pdf/ 1512.03385v1.pdf,2015-12-10/2016-08-17.
 Szegedy C, Liu Wei, Jia Yangqing, et al. Going deeper with convolutions [EB/OL]. https://arxiv.org/pdf/1409.4842v1.pdf,2014-09-17/2016-08-17.
 Gu Jiuxiang, Wang Zhenhua,Kuen J,et al. Recent advances in convolutional neural networks[EB/OL]. https://arxiv.org/pdf/ 1512.07108v4.pdf,2016-08-06/2016-08-17.
 Jia Yingqing, Shelhamer E, Donahue J, et al. Caffe: Convolutional architecture for fast feature embedding[C]// Proceedings of the 22nd ACM international conference on Multimedia. Orlando:ACM,2014:675-678.
 Nair V, Hinton GE.Rectified linear units improve restricted Boltzmann machines[C]// Proceedings of the 27th International Conference on Machine Learning. Haifa:IMLS, 2010:807-814.
 Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[J].J Mach Learn Res,2010,9:249-256.