White Blood Cell Differential Counts Using Convolutional Neural Networks for Low Resolution Images

The Complete Blood Count (CBC) is a medical diagnostic test concerned with identifying and counting basic blood cells such as red blood cells (RBC), white blood cells (WBC) and platelets. The computerized automation of CBC has been a challenging problem in medical diagnostics. In this work we describe a subcomponent system for the CBC to perform the automatic classification of WBC cells into one of five WBC types in low resolution cytological images. We describe feature extraction and consider three classifiers: a support vector machine (SVM) using standard intensity and histogram features, an SVM with features extracted by a kernel principal component analysis of the intensity and histogram features, and a convolutional neural network (CNN) which takes the entire image as input. The proposed classifiers were compared through experiments conducted on low resolution cytological images of normal blood smears. The best results were obtained with the CNN solution with recognition rates either higher or comparable to the SVM-based classifiers for all five types of WBCs.

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

[2]  A. Elmoataz,et al.  Segmentation of cytological images using color and mathematical morphology , 1999 .

[3]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[4]  Ewa Skubalska-Rafajlowicz,et al.  Pattern recognition algorithms based on space-filling curves and orthogonal expansions , 2001, IEEE Trans. Inf. Theory.

[5]  Dorin Comaniciu,et al.  Cell image segmentation for diagnostic pathology , 2001 .

[6]  S. Beksac,et al.  Feature extraction and classification of blood cells for an automated differential blood count system , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[7]  I. Jolliffe.  Principal Component Analysis , 2002 .

[8]  Sameer Singh,et al.  Advanced Algorithmic Approaches to Medical Image Segmentation , 2002, Advances in Computer Vision and Pattern Recognition.

[9]  Marek R. Ogiela,et al.  Syntactic reasoning and pattern recognition for analysis of coronary artery images , 2002, Artif. Intell. Medicine.

[10]  T. V. Sreenivas,et al.  Teager energy based blood cell segmentation , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[11]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[12]  Kan Jiang,et al.  A novel white blood cell segmentation scheme using scale-space filtering and watershed clustering , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[13]  A. G. Ramakrishnan,et al.  Automation of differential blood count , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[14]  Ewert Bengtsson,et al.  A Feature Set for Cytometry on Digitized Microscopic Images , 2003, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.

[15]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[17]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[18]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Support vector machines applied to white blood cell recognition , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[19]  H. Ramoser,et al.  Leukocyte segmentation and classification in blood-smear images , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[20]  Allen Tannenbaum,et al.  Statistical shape analysis using kernel PCA , 2006, Electronic Imaging.

[21]  Shitong Wang,et al.  A new detection algorithm (NDA) based on fuzzy cellular neural networks for white blood cell detection , 2006, IEEE Transactions on Information Technology in Biomedicine.

[22]  Nipon Theera-Umpon,et al.  Morphological Granulometric Features of Nucleus in Automatic Bone Marrow White Blood Cell Classification , 2007, IEEE Transactions on Information Technology in Biomedicine.

[23]  Ching Y. Suen,et al.  A trainable feature extractor for handwritten digit recognition , 2007, Pattern Recognit..

[24]  Jiang Bo,et al.  Wavelet transform and morphology image segmentation algorism for blood cell , 2009, 2009 4th IEEE Conference on Industrial Electronics and Applications.

[25]  Mohammad Hamghalam,et al.  Leukocyte Segmentation in Giemsa-stained Image of Peripheral Blood Smears Based on Active Contour , 2009, 2009 International Conference on Signal Processing Systems.

[26]  Jason Weston,et al.  A user's guide to support vector machines. , 2010, Methods in molecular biology.

[27]  Adam Krzyżak,et al.  APPLICATION OF PATTERN RECOGNITION TECHNIQUES FOR THE ANALYSIS OF THIN BLOOD SMEAR IMAGES , 2011 .

[28]  Adam Krzyzak,et al.  Counting of RBCs and WBCs in noisy normal blood smear microscopic images , 2011, Medical Imaging.

[29]  Adam Krzyzak,et al.  Analysis of White Blood Cell Differential Counts Using Dual-Tree Complex Wavelet Transform and Support Vector Machine Classifier , 2012, ICCVG.

[30]  Leyza Baldo Dorini,et al.  Semiautomatic White Blood Cell Segmentation Based on Multiscale Analysis , 2013, IEEE Journal of Biomedical and Health Informatics.

[31]  L. Chmielewski,et al.  Computer Vision and Graphics , 2014, Lecture Notes in Computer Science.