Abstract
Observing changes in females’ ovaries is essential in obstetrics and gynaecological imaging, e.g., genetic engineering and human reproduction. It is particularly important to monitor the dynamics of ovarian follicles’ growth, as only fully mature and grown follicles, i.e., the dominant follicles have a potential to ovulate at the end of a follicular phase. Gynaecologists follow this process in two dimensions, but recently three-dimensional (3-D) ultrasound examinations are coming to the fore. This paper surveys the existing computer methods for detection, recognition, and analyses of follicles in two-dimensional (2-D) and 3-D ovarian ultrasound recordings. Our study focuses on the efficiency, validation, and assessment of proposed follicle processing algorithms. The most important processing steps were identified in order to compare their performances. Higher ranking solutions are suggested for the so-called best algorithm for 2-D and 3-D ultrasound recordings of ovarian follicles. Finally, some guidelines for future research in this field are discussed, in particular for 3-D ultrasound volumes.
References
Adams J, Franks S, Polson DW (1985) Multifollicluar ovaries: clinical and endocrine features and response to pulsatile gonadotropin releasing hormone. Lancet II:1375–1379
Bian N, Eramian M, Pierson R (2006) Evaluation of texture features for analysis of ovarian follicular development. In: Larsen R, Nielsen M, Sporring J (eds) Lecture notes in computer science, vol 4,191, Springer, Berlin, pp 93–100
Brannstrorm M, Zickrisson U, Hagstroom H (1998) Blood flow indices as measured by color doppler ultrasonography in different regions of the human periovulatory follicle. Fertil. Steril. 69:435–442
Chen T, Zhang W, Good S, Zhou K, Comaniciu D (2009) Automatic ovarian follicle quantification from 3-D ultrasound data using global/local context with database guided segmentation. In: Proceedings of the 12th IEEE conference on computer vision, Kyoto, pp 795–802
Cigale B, Zazula D (2004) Segmentation of ovarian ultrasound images using cellular neural. Intern. J. Pattern. Recognit. Artif. Intell. 18(4):563–581
Cigale B, Lenič M, Zazula D (2006) Segmentation of ovarian ultrasound images using cellular neural networks trained by support vector machines. In: Gabrys B, Howlett R, Jain L (eds) Lecture notes in computer science, vol 4,253, Springer, Berlin, pp 515–522
Cigale B (2007) A multiscale approach to detection and growth assessment of structures in 3-D ultrasound volumes. Ph.D. thesis, Faculty of Electrical Engineering and Computer Science, University of Maribor, Maribor, Slovenia
Cigale B, Zazula D (2007) Segmentation of 3-D ovarian ultrasound volumes using continuous wavelet transform. In: Proceedings of the 11th Mediterranean Conference on Medical and Biological Enginering and Computing, pp. 1017–1020. Ljubljana, Slovenia
Cigale B, Šinjur S, Zazula D (2010) Automated quantitative assessment of perifollicular vascularization using power Doppler ultrasound images. WSEAS Trans Comput. 9(2):194–203
Cinthio M, Jansson T, Eriksson A, Ahlgren AR, Persson HW, Lindstrom K (2010) Evaluation of an algorithm for arterial lumen diameter measurements by means of ultrasound. Med. Biol. Eng. Comput. 48(11):1133–1140
Deutch T, Abuhamad A (2007) Sonography-based automated volume count (SonoAVC): an efficient and reproducible method of follicular assessment. GE Healthcare, Waukesha, USA
Deutch T, Joergner I, Matson D, Oehninger S, Bocca S, Hoenigmann D, Abuhamad A (2009) Automated assessment of ovarian follicles using a novel three-dimensional ultrasound software. Fertil. Steril. 92(5):1562–1568
Foulot H, Ranoux C, Dobuisson J, Rambaud FX, Poirot C (1989) In vitro fertilization without ovarian stimulation: a simplified protocol applied in 80 cycles. Fertil. Steril. 52:617–621
Gooding M, Kennedy S, Noble J (2003) Volume reconstruction from sparse 3-D ultrasonography. In: R. Ellis, T. Peters (eds) Lecture notes in computer science, vol 2,879, Springer, Berlin, pp 416–423
Gooding M (2004) 3-D ultrasound image analysis in assisted reproduction. PhD thesis, Merton College, University of Oxford, Oxford
Gooding M, Kennedy S, Noble J (2005) Temporal calibration of freehand three-dimensional ultrasound using image alignment. Ultrasound Med. Biol. 31(7):919–927
Gooding M, Kennedy S, Noble J (2008) Volume segmentation and reconstruction from freehand three-dimensional ultrasound data with application to ovarian follicle measurement. Ultrasound Med. Biol. 34(2):183–195
Gore M, Nayudu P, Valisavljević V (1995) Prediction of ovarian cycle outcome by follicular characteristics, stage 1. Hum. Reprod. 10(9):2313–2319
Hiremath P, Tegnoor J (2009) Recognition of follicles in ultrasound images of ovaries using geometric features. In: Proceedings of the 2nd IEEE conference on biomedical and pharmaceutical engineering (ICBPE 2009), Singapore, pp 1–8
Hiremath P, Tegnoor J (2010) Automatic detection of follicles in ultrasound images of ovaries using edge based method. IJCA, Special Issue on RTIPPR 2:120–125
Hiremath P, Tegnoor J (2010) Automatic detection of follicles in ultrasound images of ovaries using HRGMF based segmentation. Int. J. Multimed. Comput. Vision Mach. Learn. 1(1):83–87
Hsu YC, Jiang CF, Uang CM (2001) Auto-segmentation of ultrasonic images by the genetic algorithm. J. Med. Biol. Eng. 21(2):121–126
Jarvela IY, Sladkevicius P, Kelly S, Ojha K, Nargund G, Campbell S (2002) Three-dimensional sonographic and power Doppler characterization of ovaries in late follicular phase. Ultrasound Obstet. Gynecol. 20(3):281–285
Jayaprakasan K, Hilwah N, Kendall N, Hopkisson J, Campbell B, Johnson I, Raine-Fenning N (2007) Does 3-D ultrasound offer any advantage in the pretreatment assessment of ovarian reserve and prediction of outcome after assisted reproduction treatment?. Hum. Reprod. 22(1):1–10
Jiang CF, Chen ML (1998) Segmentation of ultrasonic ovarian images by texture features. In: Proceedings of the 20th annual international conference of the IEEE engineering in medicine and biology society, vol 20, Hong Kong, pp 850–853
Jörgner I, Scherleitner E (2008) SonoAVC: Studies on automated detection and measurements of hyper-stimulated follicles utilizing a new algorithm. GE Healthcare, Waukesha, USA
Krivanek A, Sonka M (1998) Ovarian ultrasound image analysis: follicle segmentation. IEEE Trans. Med. Imaging 17(9):935–944
Lawrence M, Eramian M, Pierson R, Neufeld E (2007) Computer assisted detection of polycystic ovary morphology in ultrasound images. In: Proceedings of the 4th Canadian conference on computer and robot vision, Canada, pp 105–112
Lenič M, Zazula D, Cigale B (2007) Obtaining completely stable cellular neural network templates for ultrasound image segmentation. In: Proceedings of the 11th Mediterranean conference on medical and biological enginering and computing, Ljubljana, Slovenia, pp 1013–1016
Lenič M, Zazula D, Cigale B (2007) Segmentation of ovarian ultrasound images using single template cellular neural networks trained with support vector machines. In: Proceedings of the IEEE symposium on computer-based medical systems, Maribor, Slovenia, pp 205–210
Loizou C, Pattichis C, Pantziaris M, Tyllis T, Nicolaides A (2007) Snakes based segmentation of the common carotid artery intima media. Med. Biol. Eng. Comput. 45(1):35–49
Lu Q (2008) 3-D follicle segmentation in ultrasound image volumes of ex-situ bovine ovaries. Master’s thesis, College of graduate studies and research, University of Saskatchewan, Saskatchewan, Canada
Moher D, Liberati A, Tetzlaff J, Altman D (2009) Preferred reporting items for systematic reviews and meta-analyses: The prisma statement. Open Med. 3:123–130
Muzzolini R, Yang YH, Pierson R (1993) Multiresolution texture segmentation with application to diagnostic ultrasound images. IEEE Trans. Med. Imaging 12(1):108–123
Ng E, Tang O, Ho P (2000) The significance of the number of antral follicles prior to stimulation in predicting ovarian response in an IVF programme. Hum. Reprod. 15:1937–1942
Nilsson L, Wikland M, Hamburger L, Hillensjo T, Chari S, Sturm G, Daume E (1985) Simplification of the method of in vitro fertilization: sonographic measurements of follicular diameter as a sole index of follicular maturity. J. In Vitro Fertil. Embryo. Transf. 2(1):17–22
Noble J, Boukerroui D (2006) Ultrasound image segmentation: A survey. IEEE Trans. Med. Imaging 25(8):987–1010
Pedersen P, Mitra V, Dey J (2006) Boundary detection in 3-D ultrasound reconstruction using nearest neighbor map. In: Proceedings of the SPIE international symposium on medical imaging, vol 6,147, San Diego, pp 57–67
Potočnik B, Zazula D, Solina F (1997) Classical image processing vs. computer vision techniques in automated computer-assisted detection of follicles in ultrasound images of ovary. In: Proceedings of the 6th international conference on image processing and its applications, pp 551–555
Potočnik B, Zazula D, Korže D (1997) Automated computer-assisted detection of follicles in ultrasound images of ovary. J. Med. Syst. 21(6):445–457
Potočnik B, Zazula D (2002) Automated analysis of a sequence of ovarian ultrasound images, Part I: Segmentation of single 2-D images. Image Vision Comput. 20(3):217–225
Potočnik B, Zazula D (2002) Automated analysis of a sequence of ovarian ultrasound images, Part II: Prediction-based object recognition from a sequence of images. Image Vision Comput. 20(3):227–235
Potočnik B, Zazula D (2003) Improved prediction-based ovarian follicle detection from a sequence of ultrasound images. Comput. Methods Programs Biomed. 70:199–213
Raine-Fenning N, Jayaprakasan K, Clewes J (2007) Automated follicle tracking facilitates standardization and may improve work flow. Ultrasound Obstet. Gynecol. 30(7):1015–1018
Raine-Fenning N, Jayaprakasan K, Clewes J, Joergner I, Bonaki S, Chamberlain S, Devlin L, Priddle H, Johnson I (2008) SonoAVC: a novel method of automatic volume calculation. Ultrasound Obstet. Gynecol. 31(6):691–696
Romeny B, Tirtulaer B, Kalitzin S, Scheffer G, Broekmans F, Staal J, Velde E (1999) Computer assisted human follicle analysis for fertility prospects with 3-D ultrasound. In: A. Kuba, M. Šaamal, A. Todd-Pokropek (eds) Lecture notes in computer science, vol 1,613, Springer, Berlin, pp 56–69
Sarty G, Liang W, Sonka M, Pierson R (1998) Semiautomated segmentation of ovarian follicular ultrasound images using a knowledge-based algorithm. Ultrasound Med. Biol. 24(1):27–42
Sugawara M, Niki K, Ohte N, Okada T, Harada A (2009) Clinical usefulness of wave intensity analysis. Med. Biol. Eng. Comput. 47(2):197–206
Tomaževič T, Vrtovec HM (1996) Early timed follicular aspiration prevents severe ovarian hyperstimulation syndrome. J. Assist. Reprod. Genet. 13:282–286
VanderLaan D, Khurshid K, Ireland J, Jimenez-Krassel F, McGough R (2008) Automated follicle segmentation in ultrasound scans of bovine ovaries. Int. J. Appl. Electromagn. Mech. 28:49–54
Viher B, Dobnikar A, Zazula D (1998) Cellular automata and follicle recognition problem and possibilities of using cellular automata for image recognition purposes. Int. J. Med. Inform. 49:231–241
Vlaisavljević V, Reljič M, Gavrić-Lovrec V, Zazula D, Sergent N (2003) Measurement of perifollicular blood flow of the dominant preovulatory follicle using three-dimensional power Doppler. Ultrasound Obstet. Gynecol. 22(5):520–526
Vlaisavljević V, Borko E, Radaković B, Zazula D, Došen M (2010) Changes in perifollicular vascularity after administration of human chorionic gonadotropin measured by quantitative three-dimensional power Doppler ultrasound. Wien. klin. Wochenschr. 122(Suppl 2):85–90
Vlaisavljević V, Dosen M (2008) Ultrasound in human reproduction. In: Ahmed B, Adra A, Kavak ZN (eds) Donald school basic textbook of ultrasound in obstetrics and gynecology, Jaypee brothers medical publishers, India, pp 480–517
Zazula D, Sergent N, Vlaisavljević V (2004) Automated estimation of blood volume around the ovarian follicles. In: Antoniou G, Mastorakis N, Panfilov O (eds) Advances in signal processing and computer technologies. Electrical and computer engineering series, WSES Press, USA, pp 145–150
Zimmer Y, Akselrod S (2000) Image segmentation in obstetrics and gynecology. Ultrasound Med. Biol. 26(Suppl 1):S39–S40
Acknowledgments
The authors gratefully acknowledge a valuable contribution of Professor Dr. Veljko Vlaisavljević from the University Clinical Centre of Maribor, who provided us with annotated ovarian ultrasound recordings.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Potočnik, B., Cigale, B. & Zazula, D. Computerized detection and recognition of follicles in ovarian ultrasound images: a review. Med Biol Eng Comput 50, 1201–1212 (2012). https://doi.org/10.1007/s11517-012-0956-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-012-0956-y