Abstract
In recent years, hysteroscopy, used as an outpatient office procedure, in combination with endometrial biopsy, has demonstrated its great potential as the method of first choice in the diagnosis of various gynecological abnormalities including abnormal uterine bleeding (AUB) and endometrial cancer (CA). In patients suffering with AUB, the blood vessels of the endometrium are hypertrophic, whereas in the case of CA vascularization is irregular or anarchic. In this paper, a methodology for the classification of hysteroscopical images of endometrium using vessel and texture features is presented. A total of 28 patients with abnormal uterine bleeding, 10 patients with endometrial cancer and 39 subjects with no pathological condition were imaged. 16 of the patients with AUB were premenopausal and 12 postmenopausal, all with CA were postmenopausal, and all with no pathological condition were premenopausal. All images were examined for the appearance of endometrial vessels and non-vascular structures. For each image, 167 texture and vessel’s features were initially extracted, which were reduced after feature selection in only 4 features. The images were classified into three categories using artificial neural networks and the reported classification accuracy was 91.2 %, while the specificity and sensitivity were 83.8 and 93.6 % respectively.
Similar content being viewed by others
References
Allain M, Cloitre M (1991) Characterizing the lacunarity of random and deterministic fractal sets. Phys Rev A 44:3552–3558
Asvestas P, Matsopoulos GK, Nikita KS (1999) Estimation of fractal dimension of images using a fixed mass approach. Pattern Recogn Lett 20:347–354
Asvestas PA, Ventouras E, Karanasiou I, and Matsopoulos GK (2008) Classification of event-related potentials associated with response errors in actors. In: 8th IEEE International Conference on BioInformatics and BioEngineering (BIBE). Athens, Greece
Berget I, Mevik BH, Naes T (2008) New modifications and applications of fuzzy C-means methodology. Comput Stat Data Anal 52:2403–2418
Gavião W, Scharcanski J (2007) Evaluating the mid-secretory endometrium appearance using hysteroscopic digital video summarization. Image Vis Comput 25:70–77
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3, pp 610–621
Hickey M, Fraser IS (2002) Surface vascularization and endometrial appearance in women with menorrhagia or using levonorgestrel contraceptive implants. Implications for the mechanisms of breakthrough bleeding. Hum Reprod 17(9):2428–2434
Hummel R (1977) Image enhancement by histogram transformation. Comput Vis Graph Image Process 6:184–195
Lewis BV (1984) Hysteroscopy in gynecological practice: a review. J R Soc Med 77:235–237
Martinez-Perez ME, Hughes AD, Thom SA, Bharath AA, Parker KH (2007) Segmentation of blood vessels from red-free and fluorescein retinal images. Med Image Anal 11:47–61
Neophytou MS, Tanos V, Pattichis MS, Pattichis CS, Kyriacou ES, Koutsouris DD (2007) A standardized protocol for texture analysis of endoscopic images in gynecological cancer. Biomed Eng Online
Piramuthu S, Shaw MJ, Gentry JA (1994) A classification approach using multi-layered neural networks. Decis Support Syst 11:509–525
Press WH, Teukolsky SA, Vetterling WT, Flannery BP (1993) Minimization or maximization of functions. Numerical recipes in C: the art of scientific computing, 2nd edn. Cambridge University Press, UK, pp 412–420
Reza AM (2004) Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement. J VLSI Sig Proc 38:35–44
Steger C (1998) An unbiased detector of curvilinear structures. IEEE Trans PAMI 20(2):113–125
Sugimoto O (1975) Hysteroscopic diagnosis of endometrial carcinoma. A report of fifty-three cases examined at the Women’s Clinic of Kyoto University Hospital. Am J Obstet Gynecol 121:105–113
van Herendael BJ, Sievens MJ, Flakiewicz-Kula A, Hansch C (1987) Dating of the endometrium by microhysteroscopy. Gynecol Obstet Invest 24:114–118
Zola FE, Nogueira AA, de Andrade JM, Candido dos Reis FJ (2007) Hysteroscopic appearance of malignant and benign endometrial lesions: a case–control study. Arch Gynecol Obstet 275:49–52
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
1.1 The sequential floating forward search (SFFS) method
Suppose \( D \) is the number of the available features (\( D = 167 \)), \( i(1 \le i \le D) \) is a feature and \( X_{k} \) is a subset of \( k \) features. The SFFS method requires the existence of a function \( J \) that evaluates the “goodness” of the feature subset under consideration.
-
Step 1:
\( X_{0} = \emptyset \) and \( k = 0 \)
-
Step 2:
While \( k < 2 \)
-
Find the most significant feature \( y = \mathop {\arg \hbox{Max} }\limits_{{a \in (Y - X_{k} )}} J(X_{k} \cup \{ a\} ) \)
$$ X_{k + 1} = X_{k} \cup y $$$$ k = k + 1 $$ -
-
Step 3:
While \( k < D \)
-
Find the most significant feature \( y = \mathop {\arg \hbox{Max} }\limits_{{a \in (Y - X_{k} )}} J(X_{k} \cup \{ a\} ) \)
$$ X_{k + 1} = X_{k} \cup y $$-
While \( k < 2 \)
Find the least significant feature \( x = \mathop {\arg \hbox{Max} }\limits_{{a \in X_{k} }} J(X_{k} \cup \{ a\} ) \)
If \( J(X_{k} - \{ x\} ) > J(X_{k - 1} ) \)
$$ X_{k - 1} = X_{k} - \{ x\} $$$$ k = k - 1 $$
-
The algorithm is initialized by setting \( X_{0} = \emptyset \) and \( k = 0 \) and the feature selection technique is used until the set \( X_{k} \) includes the \( k \) more significant features, with the maximum value of the evaluation function. The subset of the selected features \( X_{k} \) is obtained according to the following rule:
The selected evaluation function is the clustering accuracy of the FCM algorithm, which is described above.
Rights and permissions
About this article
Cite this article
Vlachokosta, A.A., Asvestas, P.A., Gkrozou, F. et al. Classification of hysteroscopical images using texture and vessel descriptors. Med Biol Eng Comput 51, 859–867 (2013). https://doi.org/10.1007/s11517-013-1058-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-013-1058-1