Abstract
An innovative algorithm has been developed for the segmentation of retroperitoneal tumors in 3D radiological images. This algorithm makes it possible for radiation oncologists and surgeons semiautomatically to select tumors for possible future radiation treatment and surgery. It is based on continuous convex relaxation methodology, the main novelty being the introduction of accumulated gradient distance, with intensity and gradient information being incorporated into the segmentation process. The algorithm was used to segment 26 CT image volumes. The results were compared with manual contouring of the same tumors. The proposed algorithm achieved 90 % sensitivity, 100 % specificity and 84 % positive predictive value, obtaining a mean distance to the closest point of 3.20 pixels. The algorithm’s dependence on the initial manual contour was also analyzed, with results showing that the algorithm substantially reduced the variability of the manual segmentation carried out by different specialists. The algorithm was also compared with four benchmark algorithms (thresholding, edge-based level-set, region-based level-set and continuous max-flow with two labels). To the best of our knowledge, this is the first time the segmentation of retroperitoneal tumors for radiotherapy planning has been addressed.
Similar content being viewed by others
References
Allen DM, Cady FB (1982) Analyzing experimental data by regression. Lifetime Learning Publications, Belmont
Bae E, Yuan J, Tai X-C (2011) Global minimization for continuous multiphase partitioning problems using a dual approach. Int J Comput Vis 92(1):112–129
Ball DL, Fisher RJ, Burmeister BH et al (2013) The complex relationship between lung tumor volume and survival in patients with non-small cell lung cancer treated by definitive radiotherapy: a prospective, observational prognostic factor study of the Trans-Tasman Radiation Oncology Group (TROG 99.05). Radiother Oncol 106:305–311
Ballangan C, Wang X, Fulham M, Eberl S, Feng DD (2013) Lung tumor segmentation in PET images using graph cuts. Comput Methods Programs Biomed 109(3):260–268
Barbu A, Suehling M, Xun X et al (2012) Automatic detection and segmentation of lymph nodes from CT data. IEEE Trans Med Imaging 31:241–250
Bland JM, Altman DG (1986) Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1(8476):307–310
Boykov Y, Funka G (2009) Graph cuts and efficient N–D image segmentation. Int J Comput Vis 70:109–131
Boykov Y, Kolmogorov V (2004) An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans Pattern Anal Mach Intell 26:1124–1137
Brennan C, Kajal D et al (2014) Solid malignant retroperitoneal masses—a pictorial review. Insights Imaging 5(1):53–65
Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277
Chang H, Zhuang AH, Valentino DJ, Chi WC (2009) Perfomance measure characterization for evaluating neuroimage segmentation algorithms. NeuroImage 47:122–135
Chen V, Ryan S (2010) Graph cut segmentation technique for MRI brain tumor extraction. In: IPTA, pp 284–287
Chen Q, Quan F, Xu J, Rubin DL (2013) Snake model-based lymphoma segmentation for sequential CT images. Comput Methods Programs Biomed 111(2):366–375
Cremers D, Pock T, Kolev K, Chambolle A (2011) Convex relaxation techniques for segmentation, stereo and multiview reconstruction. In: Blake A, Kohli P, Rother C (eds) Markov random fields for vision and image processing. MIT Press, Boston
DICE coefficient in http://sve.loni.ucla.edu/instructions/metrics/dice/. Accessed 15 July 2014
Feulner J, Zhou SK, Hammon M, Hornegger J, Comaniciu D (2011) Segmentation based features for lymph node detection from 3D Chest CT. LNCS MLMI 7009:91–99
Feulner J, Zhou S, Hammon M et al (2013) Lymph node detection and segmentation in chest CT data using discriminative learning and a spatial prior. Med Image Anal 17(2):254–270
Fleiss JL (1971) Measuring nominal scale agreement among many raters. Psychol Bull 76(5):378–382
Ford LR, Fulkerson DR (1962) Flows in Networks. Princeton University Press, Princeton
Gao Y, Liao S, Shen D (2012) Prostate segmentation by sparse representation based classification. MICCAI 15:451–458
Goenka AH, Shah SN, Remer EM (2012) Imaging of the retroperitoneum. Radiol Clin N Am 50(2):333–355
Gonzalez RC, Woods RE (2008) Digital image processing. Pearson Prentice Hall, Upper Saddle River
Jaccard P (1901) Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bulletin de la Société Vaudoise des Sciences Naturelles 37:547–579
Jameson MG, Holloway LC, Vial PJ et al (2010) A review of methods of analysis in contouring studies for radiation oncology. J Med Imaging Radiat Oncol 54:401–410
Moradi M, Janoos, F, Fedorov A, Risholm P, Kapur T, Wolfsberger LD, Wells WM (2012) Two solutions for registration of ultrasound to MRI for image-guided prostate interventions. IEEE EMBS, pp 1129–1132
Kuruvilla J, Gunavathi K (2014) Lung cancer classification using neural networks for CT images. Comput Methods Programs Biomed 113(1):202–209
Lermé N, Malgouyres F, Rocchisani JM (2010) Fast and memory efficient segmentation of lung tumors using graph cuts. In: MICCAI, third international workshop on pulmonary image analysis, pp 9–20
Li C, Xu C, Gui C, Fox MD (2010) Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process 19(12):3243–3254
Luo Z (2011) Segmentation of liver tumor with local C–V level set. IEEE MACE. doi:10.1109/MACE.2011.5988824
MDCP coefficient in http://my.safaribooksonline.com/book/biotechnology/9781627054300/methods-for-evaluation-of-the-results/distance_measures. Accesed 15 July 2014
Moschidis E, Graham J (2010) Interactive differential segmentation of the prostate using graph-cuts with a feature detector-based boundary term. MIUA, pp 191–195
Osher S, Sethian J (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton–Jacobi formulations. J Comput Phys 79(1):12–49
Perez-Carrasco J, Suárez-Mejias C, Serrano C, López-Guerra J, Acha B (2013) Segmentation of retroperitoneal tumors using fast continuous max-flow algorithm. MEDICON 41:360–363
Plajer I, Nguyen-Pham T-K, Richter D (2009) Tumour segmentation by active contours in 3D CT wavelet enhanced image data. EUSIPCO
Punithakumar K, Yuan J et al (2012) A convex max-flow approach to distribution-based figure-ground separation. SIAM J Imaging Sci 5(4):1333–1354
Qiu W, Yuan J, Kishimoto J, Ukwatta E, Fenster A (2013) Lateral ventricle segmentation of 3D pre-term neonates US using convex optimization. MICCAI 16:559–566
Qiu W, Yuan J, Ukwatta E, Yue S, Rajchl M, Fenster A (2014) Prostate segmentation: an efficient convex optimization approach with axial symmetry using 3-D TRUS and MR images. IEEE Trans Med Imaging 33(4):947–960
Rajchl M, Yuan White J, Ukwatta E, Stirrat J, Nambakhsh C, Peters T (2014) Interactive hierarchical max-flow segmentation of scar tissue from late-enhancement cardiac MR images. IEEE Trans Med Imaging 33(1):159–172
Rajiah P, Sinha R, Cuevas C, Dubinsky TJ, Bush WH, Kolokythas O (2011) Imaging of uncommon retroperitoneal masses. RadioGraphics 31:949–976. doi:10.1148/rg.314095132
Rockafeller R, Wets RJB (1998) Variational analysis. Grundlehren der mathematischen Wissenschaften 317 Springer Verlag
Rosenfeld A, Pfaltz JL (1968) Distance functions on digital pictures. Pattern Recogn 1(1):33–61
Song Q, Chen M, Bai J et al (2011) Surface region context in optimal multi-object graph based segmentation: robust delineation of pulmonary tumors. IPMI, pp 61–72
Strang G (1983) Maximal flow through a domain. Math Program 26(2):123–143
Sun T, Wang J, Li X, Lv P, Liu F, Luo Y, Gao Q, Zhu H, Guo X (2013) Comparative evaluation of support vector machines for computer aided diagnosis of lung cancer in CT based on a multi-dimensional data set. Comput Methods Programs Biomed 111(2):519–524
Ukwatta E, Yuan J, Rajchl M, Qiu W, Tessier D, Fenster A (2013) 3-D carotid multi-region MRI segmentation by globally optimal evolution of coupled surfaces. IEEE Trans Med Imaging 32(4):770–785
Ukwatta E, Yuan J, Qiu W, Rajchl M, Chiu B, Shavakh S, Xu J, Fenster A (2013) Joint segmentation of 3D femoral lumen and outer wall surfaces from MR images. MICCAI 8149:534–541
Vincent L (1998) Minimal path algorithms for the robust detection of linear features in gray images. ISSM, pp 331–338
Wook-Jin C, Tae-Sun C (2014) Automated pulmonary nodule detection based on three-dimensional shape-based feature descriptor. Comput Methods Programs Biomed 113(1):37–54
Yin X, Ng WH, Yang Q, Pitman A, Ramamohanarao K, Abbott D (2012) Anatomical landmark localization in breast dynamic contrast-enhanced MR imaging. Med Biol Eng Comput 50(1):91–101
Yuan J, Bae E et al (2010) A study on continuous max-flow and min-cut approaches. In: CVPR, pp 2217–2224
Yuan J, Bae E, Tai XC, Boykov Y (2010) A continuous max-flow approach to Potts model. LNCS ECCV 6316:379–392
Yuan J, Ukwatta E, Tai X C, Fenster A, Schnoerr C (2012) A fast global optimization-based approach to evolving contours with generic shape prior. UCLA Tech. Report CAM 12-38
Yuan J, Qiu W, Rajchl M, Ukwatta E, Xue-Cheng T, Fenster A (2013) Efficient 3D endfiring TRUS prostate segmentation with globally optimized rotational symmetry. In: IEEE CVPR, pp 2211–2218
Zhang J, Wang Y, Shi X (2009) An improved graph cut segmentation method for cervical lymph nodes on sonograms and its relationship with node’s shape assessment. Comput Med Imaging Graph 33:602–607
Acknowledgments
This research was co-financed by TEC2010-21619-C04-02 (Government of Spain), P11-TIC-7727 (Regional Government of Andalusia, Spain), PT13/0006/0036 RETIC, FEDER Funds and Department of Health (Regional Government of Andalusia). We would like to thank Jose Manuel Conde and María José Ortíz for their clinical contribution to the development of this algorithm.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Suárez-Mejías, C., Pérez-Carrasco, J.A., Serrano, C. et al. Three-dimensional segmentation of retroperitoneal masses using continuous convex relaxation and accumulated gradient distance for radiotherapy planning. Med Biol Eng Comput 55, 1–15 (2017). https://doi.org/10.1007/s11517-016-1505-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-016-1505-x