Abstract
Endometrial Tuberculosis (ETB) is a major observation in Infertility due to Female Genital Tuberculosis (FGTB). Transvaginal ultrasound (TVUS) images are used to initiate the diagnostic procedure. An effective computational method to identify and classify ETB from TVUS images is presented in this paper. The images from female patients have been collected from medical centers in India. A composite co-occurrence model is proposed; where a Non-Subsampled Contourlet Transformation (NSCT) enhances the textural appearances of the images before feature extraction. Since original TVUS are inherently ill defined; the transformation highlights the directional, multi- scale spectral texture features for discriminatory analysis. Experimental results show that the textural features extracted from these transformed images are more discriminative. The proposed approach achieved an F-score of 0.821and a sensitivity of 0.801 for the dataset in hand. A dimensionality reduction of 66.6% is achieved by Entropy based Normalized Mutual Information ranking and subsequent feature subset selection for classification.
Similar content being viewed by others
References
World Health Organization: “Global tuberculosis report 2019” www.who.int/tb/publications/global_report
Sharma JB, Dharmendra S, Agarwal S et al (2016) Genital tuberculosis and infertility. Fertility Sci Res 3:6–18
Djuwantono T, Permadi W, Septiani L et al (2017) Female genital tuberculosis and infertility: serial cases report in Bandung, Indonesia and literature review. BMC Res Notes 10(1):1683MC
Bose M (2011) Female genital tract tuberculosis: How long will it elude diagnosis? Indian Journal of Med Res 134:13–14
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst, Man, Cybernetics 3:610–621
Kumar D (2020) Feature extraction and selection of kidney ultrasound images using GLCM and PCA. Proc Comp Sci 167:1722–1731
Ou X, Pan W, Xiao P (2014) In vivo skin capacitive imaging analysis by using grey level co-occurrence matrix (GLCM). Int J Pharm 460:28–32
Brehar R, Mitrea D, Nedevschi S et al. (2019) Hepatocellular carcinoma recognition in ultrasound images using textural descriptors and classical machine learning, IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP), 491–497
Dandan L, Huanhuan M et al. (2019) Classification of diffuse liver diseases based on ultrasound images with multimodal features. IEEE International Instrumentation and Measurement Technology Conference 1–5
Wei M, Wu X, Zhu J, et al. (2019) Multi-feature fusion for ultrasound breast image classification of benign and malignant. IEEE 4th International Conference on Image, Vision and Computing (ICIVC), 474–478
Dhaygude PS, Handore SM (2016) Feature extraction of thyroid nodule US images using GLCM. Int J Sci Res 51
Bogowicz M, Vuong D, Huellner MW et al (2019) CT radiomics and PET radiomics: ready for clinical implementation? Quarterly J Nuclear Med Mol Imaging: Off Publ Italian Assoc Nuclear Med (AIMN) 63(4):355
Nanni L, Lumini A, Brahnam S (2012) ‘Survey on LBP based texture descriptors for image classification. Expert Syst Appl 39(3):3634–3641
Ershad SF (2012) Texture classification approach based on combination of edge co-occurrence and local binary pattern. arXiv preprint arXiv: 1203.4855
Hamouchene I, Aouat S, Lacheheb H (2014) Texture segmentation and matching using LBP operator and GLCM matrix. Intel Systems Sci Inform 389–407
Ding X (2017) Texture feature extraction research based on GLCM-CLBP Algorithm. 7th International Conference on Education, Management, Information and Mechanical Engineering, EMIM
Sthevanie F, Ramadhani KN (2018) Spoofing detection on facial images recognition using LBP and GLCM combination. J Phys: Conf Ser 971(1):012014
Kobayashi T, Otsu N (2008) Image feature extraction using gradient local auto-correlations. European conference on computer vision, 346–358
Kobayashi T, Otsu N (2012) Motion recognition using local auto-correlation of space–time gradients. Pattern Recogn Lett 33(9):1188–1195
Chen C, Jiang J, Zhang B et al. (2015) Hyperspectral image classification using gradient local auto-correlations, 3rd IAPR Asian Conference on Pattern Recognition ACPR, 454–458
Kiaee N, Hashemizadeh E, Zarrinpanjeh N (2019) Using GLCM features in Haar wavelet transformed space for moving object classification. IET Intel Transport Syst 13(7):1148–1153
Dorini LB, Leite NJ (2009) Multiscale methods for image processing: wavelet and the scale-space approaches. Tutorials of the 22nd Brazilian Symposium on Computer Graphics and Image Processing, 31–44
Hazra D (2011) Texture recognition with combined GLCM, wavelet and rotated wavelet features. Int J Comput Electr Eng 3(1):146
Wenbo W, Yusong W, Xue D (2015) Sea ice classification of SAR image based on wavelet transform and gray level co-occurrence matrix, Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control 104–107
Çevik T, Alshaykha AMA, Çevik N (2016) Performance analysis of GLCM-based classification on Wavelet Transform-compressed fingerprint images, Sixth International Conference on Digital Information and Communication Technology and its Applications, 131–135
Yang MC, Moon WK, Wang YCF (2013) Robust texture analysis using multi-resolution grey-scale invariant features for breast sonographic tumour diagnosis. IEEE Trans Med Imaging 32(12):2262–2273
Sharma A, Deshmukh KA (2014) An efficient directional multiresolution image representation using Contourlet transform. Int J Comput Sci Mobile Comput 3(4):1240–1250
Nguyen HD, Le TT, Do TH (2012) A new descriptor for image retrieval using contourlet co-occurrence. Sci Tech Dev J 15(2):5–16
Telagarapu P, Poonguzhali S (2014) Analysis of contourlet texture feature extraction to classify the benign and malignant tumours from breast ultrasound images. Int J Eng Tech 6(1):239–305
Do MN, Vetterli M (2002) Contourlets: a directional multiresolution image representation. Proc Int Conf Image Proc 1:I–I
Da Cunha AL, Zhou J, Do MN (2006) The non-subsampled contourlet transform: theory, design, and applications. IEEE Trans Image Process 15(10):3089–3101
Vergara JR, Estévez PA (2014) A review of feature selection methods based on mutual information. Neural Comput Appl 24(1):175–186
Löfstedt T, Brynolfsson P, Asklund T, Nyholm T, Garpebring A (2019) Gray-level invariant Harlick texture features. PLoS ONE 14(2):e0212110
Acknowledgements
The authors would like to thank Yashoda Hospital, Kaushambi for assisting this research with the dataset as no public dataset is available. The dataset was enriched and expert support was provided by Dr. Vibha Bansal, Sai Polyclinic, a leading gynecologist in Delhi. We would like to extend our gratitude for cooperation of the clinical staff and ultrasonologists at both the centers. Informed consent has been taken from the concerned female participants in accordance with the Helsinki World Medical Association protocol 2013.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Garg, V., Sahoo, A. & Saxena, V. Enhanced textural analysis for endometrial tuberculosis identification from ultrasound images. Int. j. inf. tecnol. 13, 657–666 (2021). https://doi.org/10.1007/s41870-020-00605-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41870-020-00605-7