Abstract
Perirectal space segmentation in computed tomography images aids in quantifying radiation dose received by healthy tissues and toxicity during the course of radiation therapy treatment of the prostate. Radiation dose normalised by tissue volume facilitates predicting outcomes or possible harmful side effects of radiation therapy treatment. Manual segmentation of the perirectal space is time consuming and challenging in the presence of inter-patient anatomical variability and may suffer from inter- and intra-observer variabilities. However automatic or semi-automatic segmentation of the perirectal space in CT images is a challenging task due to inter patient anatomical variability, contrast variability and imaging artifacts. In the model presented here, a volume of interest is obtained in a multi-atlas based segmentation approach. Un-supervised learning in the volume of interest with a Gaussian-mixture-modeling based clustering approach is adopted to achieve a soft segmentation of the perirectal space. Probabilities from soft clustering are further refined by rigid registration of the multi-atlas mask in a probabilistic domain. A maximum a posteriori approach is adopted to achieve a binary segmentation from the refined probabilities. A mean volume similarity value of 97% and a mean surface difference of 3.06 ± 0.51 mm is achieved in a leave-one-patient-out validation framework with a subset of a clinical trial dataset. Qualitative results show a good approximation of the perirectal space volume compared to the ground truth.
Similar content being viewed by others
References
Michalski JM, Gay H, Jackson A, Tucker SL, Deasy JO (2010) Radiation dose-volume effects in radiation-induced rectal injury. Int J Radiat Oncol Biol Phys 76(3, Supplement 1):S123–S129
Smeenk RJ, Hoffmann AL, Hopman WP, van Lin EN, Kaanders JH (2012) Dose-effect relationships for individual pelvic floor muscles and anorectal complaints after prostate radiotherapy. Int J Radiat Oncol Biol Phys 83(2):636–644. doi:10.1016/j.ijrobp.2011.08.007
Gaballah AH, Shaaban AM, Elguindy YM, Elsayes KM (2015) The extraperitoneal spaces. In: Elsayes KM (ed) Cross-sectional imaging of the abdomen and pelvis: a practical algorithmic approach. Springer, New York
Ghose S, Denham J, Ebert M, Kennedy A, Mitra J, Rose S, Dowling J (2013) Multi-atlas and gaussian mixture modeling based perirectal fat segmentation from CT images. In: Yoshida H, Warfield S, Vannier M (eds) Abdominal imaging. Computation and clinical applications. Lecture notes in computer science, vol 8198. Springer, Berlin, pp 194–202. doi:10.1007/978-3-642-41083-3_22
Wang H, Suh JW, Das SR, Pluta JB, Craige C, Yushkevich PA (2013) Multi-atlas segmentation with joint label fusion. IEEE Trans Pattern Anal Mach Intell 35(3):611–623. doi:10.1109/tpami.2012.143
Isgum I, Staring M, Rutten A, Prokop M, Viergever MA, Bv Ginneken (2009) Multi-atlas-based segmentation with local decision fusion—application to cardiac and aortic segmentation in CT scans. IEEE Trans Med Imaging 28(7):1000–1010. doi:10.1109/TMI.2008.2011480
Klein S, van der Heide UA, Lips IM, van Vulpen M, Staring M, Pluim JP (2008) Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med Phys 35(4):1407–1417. doi:10.1118/1.2842076
Studholme C, Hill DLG, Hawkes DJ (1999) An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognit 32(1):71–86. doi:10.1016/S0031-3203(98)00091-0
Chandra SS, Dowling JA, Shen KK, Raniga P, Pluim JP, Greer PB, Salvado O, Fripp J (2012) Patient specific prostate segmentation in 3-d magnetic resonance images. IEEE Trans Med Imaging 31(10):1955–1964. doi:10.1109/tmi.2012.2211377
Zaim A (2005) Automatic segmentation of the prostate from ultrasound data using feature-based self organizing map. In: Kalviainen H, Parkkinen J, Kaarna A (eds) Image analysis. Springer, Berlin, pp 1259–1265. doi:10.1007/11499145_127
Li W, Liao S, Feng Q, Chen W, Shen D (2011) Learning image context for segmentation of prostate in CT-guided radiotherapy. In: Fichtinger G, Martel A, Peters T (eds) Medical image computing and computer-assisted intervention—MICCAI 2011. Springer, Berlin, pp 570–578. doi:10.1007/978-3-642-23626-6_70
Liao S, Shen D (2011) A learning based hierarchical framework for automatic prostate localization in CT images. In: Madabhushi A, Dowling J, Huisman H, Barratt D (eds) Prostate cancer imaging. Image analysis and image-guided interventions. Springer, Berlin, pp 1–9. doi:10.1007/978-3-642-23944-1_1
Tutar IB, Pathak SD, Gong L, Cho PS, Wallner K, Kim Y (2006) Semiautomatic 3-D prostate segmentation from TRUS images using spherical harmonics. IEEE Trans Med Imag 25(12):1645–1654. doi:10.1109/TMI.2006.884630
Yiqiang Z, Dinggang S (2006) Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method. IEEE Trans Med Imag 25(3):256–272. doi:10.1109/TMI.2005.862744
Cosio FA (2008) Automatic initialization of an active shape model of the prostate. Med Image Anal 12(4):469–483. doi:10.1016/j.media.2008.02.001
Yan P, Xu S, Turkbey B, Kruecker J (2010) Discrete deformable model guided by partial active shape model for TRUS image segmentation. IEEE Trans Biomed Eng 57(5):1158–1166. doi:10.1109/tbme.2009.2037491
Makni N, Puech P, Lopes R, Dewalle AS, Colot O, Betrouni N (2008) Combining a deformable model and a probabilistic framework for an automatic 3D segmentation of prostate on MRI. Int J Comput Assist Radiol Surg 4(2):181–188. doi:10.1007/s11548-008-0281-y
Martin S, Troccaz J, Daanenc V (2010) Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model. Med Phys 37(4):1579–1590. doi:10.1118/1.3315367
Gao Y, Sandhu R, Fichtinger G, Tannenbaum AR (2010) A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE Trans Med Imag 29(10):1781–1794. doi:10.1109/TMI.2010.2052065
Toth R, Bloch BN, Genega EM, Rofsky NM, Lenkinski RE, Rosen MA, Kalyanpur A, Pungavkar S, Madabhushi A (2011) Accurate prostate volume estimation using multifeature active shape models on T2-weighted MRI. Acad Radiol 18(6):745–754. doi:10.1016/j.acra.2011.01.016
Song Q, Wu X, Liu Y, Smith M, Buatti J, Sonka M (2009) Optimal graph search segmentation using arc-weighted graph for simultaneous surface detection of bladder and prostate. Med Image Comput Comput Assist Interv 12(Pt 2):827–835
Chen S, Lovelock DM, Radke RJ (2011) Segmenting the prostate and rectum in CT imagery using anatomical constraints. Med Image Anal 15(1):1–11. doi:10.1016/j.media.2010.06.004
Toth R, Madabhushi A (2012) Multifeature landmark-free active appearance models: application to prostate MRI segmentation. IEEE Trans Med Imag 31(8):1638–1650. doi:10.1109/TMI.2012.2201498
Chowdhury N, Toth R, Chappelow J, Kim S, Motwani S, Punekar S, Lin H, Both S, Vapiwala N, Hahn S, Madabhushi A (2012) Concurrent segmentation of the prostate on MRI and CT via linked statistical shape models for radiotherapy planning. Med Phys 39(4):2214–2228. doi:10.1118/1.3696376
Zhan Y, Shen D (2003) Automated segmentation of 3D US prostate images using statistical texture-based matching method. Medical image computing and computer-assisted intervention—MICCAI 2003. Springer, Berlin, p 688. doi:10.1007/978-3-540-39899-8_84
Rueckert D, Sonoda LI, Hayes C, Hill DL, Leach MO, Hawkes DJ (1999) Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans Med Imaging 18(8):712–721. doi:10.1109/42.796284
Ourselin S, Roche A, Subsol G, Pennec X, Ayache N (2001) Reconstructing a 3D structure from serial histological sections. Image Vis Comput 19(1–2):25–31. doi:10.1016/S0262-8856(00)00052-4
Dempster AP, Laird NM, Rubin DP (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Ser B 39:1–38
Denham JW, Wilcox C, Joseph D, Spry NA, Lamb DS, Tai KH, Matthews J, Atkinson C, Turner S, Christie D, Gogna NK, Kenny L, Duchesne G, Delahunt B, McElduff P (2012) Quality of life in men with locally advanced prostate cancer treated with leuprorelin and radiotherapy with or without zoledronic acid (TROG 03.04 RADAR): secondary endpoints from a randomised phase 3 factorial trial. Lancet Oncol 13(12):1260–1270. doi:10.1016/s1470-2045(12)70423-0
Dowling J (2013) Importing contours from DICOM-RT structure sets with ITK4. http://hdl.handle.net/10380/3401. Accessed 22 Jan 2014
Anderson TW, Darling DA (1952) Asymptotic theory of certain “goodness of fit” criteria based on stochastic processes. Ann Math Stat 23(2):193–212. doi:10.1214/aoms/1177729437
Theodoridis S, Koutroumbas K (2009) Pattern recognition, 4th edn. Academic Press, Burlington
Acknowledgements
We gratefully acknowledge the support of the Australian National Health and Medical Research Council (Grant Nos 1006447 and 1077788).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ghose, S., Denham, J.W., Ebert, M.A. et al. Multi-atlas and unsupervised learning approach to perirectal space segmentation in CT images. Australas Phys Eng Sci Med 39, 933–941 (2016). https://doi.org/10.1007/s13246-016-0496-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-016-0496-0