Image based measurements for evaluation of pelvic organ prolapse


Magnetic resonance imaging (MRI) measurements are essential for the diagnosis of pelvic organ prolapse given the inaccuracy of clinical examination. However, MRI pelvic floor measurements are currently performed manually and can be inconsistent and time-consuming. In this paper, we present a scheme for semi-automatic measurement modeling on MRI based on image segmentation and intersecting point identification methods. The segmentation algorithm is a multi-stage mechanism based on block grouping, support vector machine classification, morphological operation and prior shape information. Block grouping is achieved by classifying blocks as bone or background based on image texture features. The classified blocks are then used to find the initial segmentation by the first phase morphological opening. Prior shape information is incorporated into the initial segmentation to obtain the final segmentation using registration with the similarity type transformation. After segmentation, points of reference that are used for pelvic floor measurements are identified using morphological skeleton operation. The experiments on the MRI images show that the presented scheme can detect the points of reference on the pelvic floor structure to determine the reference lines needed for the assessment of pelvic organ prolapse. This will lead towards more consistent and faster pelvic organ prolapse diagnosis on dynamic MRI studies, and possible screening procedures for predicting predisposition to pelvic organ prolapse by radiologic evaluation of pelvic floor measurements.

Share and Cite:

Onal, S. , Lai-Yuen, S. , Bao, P. , Weitzenfeld, A. and Hart, S. (2013) Image based measurements for evaluation of pelvic organ prolapse. Journal of Biomedical Science and Engineering, 6, 45-55. doi: 10.4236/jbise.2013.61007.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] Dallenbach, P., Kaelin-Gambirasio, I., Jacob, S., Du-buisson, J.B. and Boulvain, M. (2008) Incidence rate and risk factors for vaginal vault prolapse repair after hysterectomy. International Urogynecology Journal, 19, 1623- 1629. doi:10.1007/s00192-008-0718-4
[2] AUGS Response: FDA Safety Communication (2011)
[3] Olsen, A.L., Smith, V.J, Bergstrom, J.O, Colling, J.C. and Clark, A.L. (1997) Epidemiology of surgically managed pelvic organ prolapse and urinary incontinence. Obstetrics & Gynecology, 89, 501-506. doi:10.1016/S0029-7844(97)00058-6
[4] Bump, R.C., Mattiasson, A., Bo, K., Brubaker, L.P., DeLancey, J.O.L., Klarskov, P., Shull, B.L. and Smith, A.R.B. (1996) The standardization of terminology of female pelvic organ prolapse and pelvic floor dysfunction. American Journal of Obstetrics & Gynecology, 175, 10- 17. doi:10.1016/S0002-9378(96)70243-0
[5] Fayyad, A.H.S., Gurung. V., Prashar, S. and Smith, A. (2007) How accurate is symptomatic and clinical evaluation of prolapse prior to surgical repair? International Urogyne-cology Journal, 18, 1179-1183. doi:10.1007/s00192-007-0306-z
[6] Altman, D. Lopez, A., Kierkegaard, J., Zetterstrom, J., Falconer, C., Pollack, J. and Mellgren, A. (2005) Assessment of posterior vaginal wall prolapse: Comparison of physical findings to cystodefecoperitoneography. International Urogynecology Journal and Pelvic Floor Dysfunction, 16, 96-103.
[7] Agildere, A.M., Tarhan, N.C., Ergeneli, M.H., Yologlu, Z., Kurt, A., Akgun, S. and Kayahan, E.M. (2003) MR rectography evaluation of rectoceles with oral gadopentetate dimeglumine and polyethylene glycol solution. Abdominal Imaging, 28, 28-35. doi:10.1007/s00261-002-0023-5
[8] Kaufman, H.S., Buller, J.L., Thompson, J.R., Pannu, H.K., DeMeester, S.L., Genadry, R.R., Bluemke, D.A., Jones, B., Rychcik, J.L. and Cundiff, G.W. (2001) Dynamic pelvic magnetic resonance imaging and cystocolpoproctography alter sur-gical management of pelvic floor disorders. Diseases of the Colon & Rectum, 44, 1575- 1583. doi:10.1007/BF02234374
[9] Colaiacomo, M.C., Mas-selli, G., Polettini, E., Lanciotti, S., Casciani, E., Bertini, L. and Gualdi, G. (2009) Dynamic MR imaging of the pelvic floor: A pictorial review. Radiographics, 29, p. e35. doi:10.1148/rg.e35
[10] Ginath, S., Garely, A., Luchs, J.S., Shahryarinejad. A., Olivera, C., Zhou, S., Ascher-Walsh, C., Condrea, A., Brodman, M. and Vardy, M. (2011) MRI pelvic landmark angles in the assessment of apical pelvic organ prolapse. Archives of Gynecology and Obstetrics, 284, 365-370. doi:10.1007/s00404-010-1648-1
[11] Goh, H.S.V., Kap-lan, G., Healy, J.C. and Bartram, C.I. (2000) Dynamic MR imaging of the pelvic floor in asymptomatic subjects. American Journal of Roentgenology, 174, 661-666.
[12] Healy, J.C. and Reznek, R.H. (1997) Dy-namic MR imaging compared with evacuation proctography when evaluating anorectal configuration and pelvic floor movement. American Journal of Roentge-nology, 169, 775-779.
[13] Lienemann, A.C.A., Baron, A., Kohn, P. and Reiser, M. (1997) Dynamic MR colpo-cystorectography assessing pelvic floor descent. European Radiology, 7, 1309-1317. doi:10.1007/s003300050294
[14] Broekhuis, S.R., Futterer, J.J., Barentsz, J.O. and Vier-hout, M.E. (2009) A systematic review of clinical studies on dynamic magnetic resonance imaging of pelvic organ prolapse: The use of reference lines and anatomical land-marks. International Urogynecology Journal and Pelvic Floor Dysfunction, 20, 721-729. doi:10.1007/s00192-009-0848-3
[15] Mao, J. and Jain, A. (1992) Texture classification and segmentation using multiresolution simultaneous autoregressive models. Pattern Recognition, 25, 173-188. doi:10.1016/0031-3203(92)90099-5
[16] Hofmann, T., Puzicha, J. and Buhmann, J. (1998) Unsupervised texture segmentation in a deterministic annealing framework. IEEE Transactions on Pattern Analysis and Machine In-telligence, 20, 803-818. doi:10.1109/34.709593
[17] Hall, L.O., Bensaid, A.M., Clarke, L.P., Velthuizen, R.P., Silbiger, M.S. and Bezdek, J.C. (1992) A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain. IEEE Transactions on Neural Net-works, 3, 672-681. doi:10.1109/72.159057
[18] Tremeau, A. and Borel, N. (1997) A region growing and merging algorithm to colour segmentation. Pattern Recognition, 30, 1191-1203. doi:10.1016/S0031-3203(96)00147-1
[19] Hojjatoleslami, S. and Kittler, J. (1998) Region growing: A new approach. IEEE Transactions on Image Processing, 7, 1079-1084. doi:10.1109/83.701170
[20] Bao, P., Zhang, L. and Wu, X. (2005) Canny edge detection enhancement by scale multiplication. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 1485-1490. doi:10.1109/TPAMI.2005.173
[21] Bao, P. and Zhang, L. (2003) Noise reduction for magnetic resonance images via adaptive multiscale products thresholding. IEEE Transactions on Medical Imaging, 22, 1089-1099. doi:10.1109/TMI.2003.816958
[22] Canny, J. (1986) A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8, 679-698. doi:10.1109/TPAMI.1986.4767851
[23] Terzopoulos, D. and Fleischer, K. (1988) Deformable models. The Visual Computer, 4, 306-331. doi:10.1007/BF01908877
[24] Davatzikos, C., Fan, Y., Wu, X., Shen, D. and Resnick, S.M. (1995) An active contour model for mapping the cortex. IEEE Transactions on Medical Imaging, 14, 65. doi:10.1109/42.370403
[25] Ray, N. (2003) Merging parametric active contours within homogeneous image regions for MRI-based lung segmentation. IEEE Transactions on Fuzzy Systems Medical Imaging, 22, 189-199. doi:10.1109/TMI.2002.808354
[26] Lorigo, L. (1998) Segmentation of bone in clinical knee MRI using based geodesic active contours. MICCAI.
[27] Fripp, J. Crozier, S., Warfield, S.K. and Ourselin, S. (2007) Automatic segmentation of the bone and extraction of the bone-cartilage interface from magnetic resonance images of the knee. Physics in Medicine and Biology, 52, 1617-1631. doi:10.1088/0031-9155/52/6/005
[28] Bourgeat, P., Fripp, J., Stanwell, P., Ramadan, S. and Ourselin, S. (2007) MR image segmentation of the knee bone using phase information. Medical Image Analysis, 11, 325-335. doi:10.1016/
[29] Schmid, J. and Magnenat-Thalmann, N. (2008) MRI bone segmentation using deformable models and shape priors. Medical Image Computing, 5241, 119-126.
[30] Carballido-Gamio, J., Belongie, S. and Majumdar, S. (2004) Normalized cuts in 3-D for spinal MRI segmentation. IEEE Transactions on Medical Imaging, 23, 36-44. doi:10.1109/TMI.2003.819929
[31] Liu, L., Raber, D., Nopachai, D., Commean, P., Sinacore, P., Prior, F., Pless, R. and Ju, T. (2008) Interactive separation of segmented bones in ct volumes using graph cut. MICCAI, ser. LNCS.
[32] Boykov, Y. and Kolmogorov, V. (2004) An experiemental comparison of min-cut/maxflow algo-rithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 1124-1137. doi:10.1109/TPAMI.2004.60
[33] Haralick, R.M. and Shapiro, L.G. (1985) Survey of image segmentation techniques. Computer Vision Graphics Image Process, 29, 100-132. doi:10.1016/S0734-189X(85)90153-7
[34] Schmid, C., Mohr, R. and Bauckhage, C. (2000) Evaluation of interest point detectors. International Journal of Computer Vision, 37, 151-172. doi:10.1023/A:1008199403446

Copyright © 2024 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.