Pattern Recognition of IVF’s Early Embryo Images Based on Support Vector Machines and Texture Features

Pattern Recognition of IVF’s Early Embryo Images Based on Support Vector Machines and Texture Features

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2018 by IJETT Journal
Volume-66 Number-1
Year of Publication : 2018
Authors : Li-Hui Wang, Zhi-Xiang Fu, Su-Zhe Ye, Da-Guan Ke
DOI :  10.14445/22315381/IJETT-V66P202

Citation 

MLA Style: Li-Hui Wang, Zhi-Xiang Fu, Su-Zhe Ye, Da-Guan Ke "Pattern Recognition of IVF’s Early Embryo Images Based on Support Vector Machines and Texture Features" International Journal of Engineering Trends and Technology 66.1 (2018): 7-11.

APA Style:Li-Hui Wang, Zhi-Xiang Fu, Su-Zhe Ye, Da-Guan Ke (2018). Pattern Recognition of IVF’s Early Embryo Images Based on Support Vector Machines and Texture Features. International Journal of Engineering Trends and Technology, 66(1), 7-11.

Abstract
For the evaluation of the implantation potential of IVF early embryos, it is necessary to culture the in vitro cultured embryos to the cleavage stage with morphological characteristics. Shortening the culture time of embryos in vitro is important and difficult in IVF technology, because embryos with shorter developmental time do not have morphological features, and clinicians cannot evaluate embryo quality from embryonic images. The most basic feature that can be obtained from the embryo images is texture information. This study uses two features commonly used in texture features: Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) as indicators for evaluating the implantation potential of IVF early embryos. In this study, the early embryo images with a developmental duration of only 2 h are used. Support Vector Machines (SVM) are used for pattern recognition of embryo images. After finding the best feature combination by feature selection method, all data is divided into training set and test set. The training set is used to build the model, and the test set verifies the robustness of the model. The accuracy of the ten-fold cross-validation of all samples under the best feature combination is reaches 84.72%, the accuracy of the test set is reaches 77.67%, and the AUC value is 0.78.

Reference
[1] Lu X, Wu Z, Wang M, et al. Effects of vitamin C on the outcome of in vitro fertilization–embryo transfer in endometriosis: A randomized controlled study [J]. Journal of International Medical Research, 2018:030006051878691.
[2] Kirstine K, Aishling A, Hans Jakob I, et al. Choosing the best embryo by time lapse versus standard morphology [J]. Fertility & Sterility, 2015, 103(2):323-332.
[3] Guerif F, Le G A, Giraudeau B, et al. Limited value of morphological assessment at days 1 and 2 to predict blastocyst development potential: a prospective study based on 4042 embryos. [J]. Human Reproduction, 2007, 22(7):1973-81.
[4] Tesarik J, Greco E. The probability of abnormal preimplantation development can be predicted by a single static observation on pronuclear stage morphology. [J]. Human Reproduction, 1999, 14(5):1318-23.
[5] Hao L, Yongquan Y, Xiancao G, et al. Improved LBP used for texture feature extraction [J]. Computer Engineering & Applications, 2014.
[6] Ahonen T, Hadid A, Pietikainen M. Face Description with Local Binary Patterns: Application to Face Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12):2037-2041.
[7] Tan X, Triggs B. Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions [J]. Amfg, 2007, 4778(6):1635-1650.
[8] Leenkiat Soh C T. Texture Analysis of SAR Sea Ice Imagery using Gray Level Co-occurrence Matrices [J]. IEEE Transactions on Geoscience & Remote Sensing, 1999, 37(2):780-795.
[9] Çamlica Z, Tizhoosh H R, Khalvati F. Medical Image Classification via SVM Using LBP Features from Saliency-Based Folded Data [J]. 2015:128-132.
[10] Jung J Y, Kim S W, Yoo C H, et al. LBP-ferns-based feature extraction for robust facial recognition[J]. IEEE Transactions on Consumer Electronics, 2017, 62(4):446-453.
[11] Ojala T, Pietik?Inen M , Harwood D . A comparative study of texture measures with classification based on featured distributions [J]. Pattern Recognition: The Journal of the Pattern Recognition Society, 1996, 29(1):51-59.
[12] Ozdek S, Lonneville Y H, Onol M, et al. Assessment of nerve fiber layer in diabetic patients with scanning laser polarimetry. [J]. Eye, 2002, 16(6):761-765.
[13] Ojala T, Pietikäinen M, Mäenpää T. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000, 24(7):971-987.
[14] Haralick R, Shanmugam K, Dinstein I, et al. Texture features for image classification [J]. IEEE Trans Smc, 1973, 3(6):610-621.
[15] Hengnian Q I. Support Vector Machines and Application Research Overview [J]. Computer Engineering, 2004.
[16] Chang C C, Lin C J. LIBSVM: A library for support vector machines [J]. 2011, 2(3):1-27.
[17] Sheng-Qiang J I, Hai-Ying J I, Xiao-Hu X, et al. Application of Several Feature Selection Methods in Partial Discharge Pattern Recognition [J]. Shaanxi Electric Power, 2011.

Keywords
in vitro fertilization-embryo transfer, Pattern recognition, Neural Networks, SVM, Texture feature, LBP, GLCM.