Abstract
Purpose
In modern oncology, disease progression and response to treatment are routinely evaluated with a series of volumetric scans. The number of tumors and their volume (mass) over time provides a quantitative measure for the evaluation. Thus, many of the scans are follow-up scans. We present a new, fully automatic algorithm for lung tumors segmentation in follow-up CT studies that takes advantage of the baseline delineation.
Methods
The inputs are a baseline CT scan and a delineation of the tumors in it and a follow-up scan; the output is the tumor delineations in the follow-up CT scan; the output is the tumor delineations in the follow-up CT scan. The algorithm consists of four steps: (1) deformable registration of the baseline scan and tumor’s delineations to the follow-up CT scan; (2) segmentation of these tumors in the follow-up CT scan with the baseline CT and the tumor’s delineations as priors; (3) detection and correction of follow-up tumors segmentation leaks based on the geometry of both the foreground and the background; and (4) tumor boundary regularization to account for the partial volume effects.
Results
Our experimental results on 80 pairs of CT scans from 40 patients with ground-truth segmentations by a radiologist yield an average DICE overlap error of 14.5 % (\(\hbox {std}=5.6\)), a significant improvement from the 30 % (\(\hbox {std}=13.3\)) result of stand-alone level-set segmentation.
Conclusion
The key advantage of our method is that it automatically builds a patient-specific prior to the tumor. Using this prior in the segmentation process, we developed an algorithm that increases segmentation accuracy and robustness and reduces observer variability.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Tuma SR (2006) Sometimes size does not matter: reevaluating RECIST and tumor response rate endpoints. J Natl Cancer Inst 98:1272–1274
Opfer R, Kabus S, Schneider T, Carlsen IC, Renisch S, Sabczynski J (2009) Follow-up segmentation of lung tumors in PET and CT data. SPIE, 72600X
Plajer IC, Richter D (2010) A new approach to model based active contours in lung tumor segmentation in 3D CT image data. In: Information Technology and Applications in Biomedicine (ITAB), 10th IEEE International Conference. IEEE, pp 1–4
Awad J, Owrangi A, Villemaire L, O’Riordan E, Parraga G (2012) A three-dimensional lung tumor segmentation from X-ray computed tomography using sparse field active models. Med Phys 39(2):851–865
Weizman L, Ben-Sira L, Joskowicz L, Precel R, Constantini S, Ben-Bashat D (2010) Automatic segmentation and components classification of optic pathway gliomas in MRI. In: Medical image computing and computer assisted intervention. Springer, Heidelberg, pp 103–111
Hollensen C, Cannon G, Cannon D, Bentzen S (2012) Lung tumor segmentation using electric flow lines for graph cuts. In: Image analysis recognition. Springer, Heidelberg, pp 206–213
Brown MS, McNitt-Gray MF, Goldin JG, Suh RD, Sayre JW, Aberle DR (2001) Patient-specific models for lung nodule detection and surveillance in CT images. Trans Med Imaging 20(12):1242–1250
Kuhnigk JM, Dicken V, Bornemann L, Wormanns D, Krass S, Peitgen HO (2004) Fast automated segmentation and reproducible volumetry of pulmonary metastases in CT-scans for therapy monitoring. In: Medical image computing and computer assisted intervention. Springer, Heidelberg, pp 933–941
Reeves A, Chan AB, Yankelevitz DF, Henschke CI, Kressler B, Kostis WJ (2006) On measuring the change in size of pulmonary nodules. Trans Med Imaging 25:435–450
Reeves AP, Jirapatnakul AC, Biancardi AM et al. (2009) The VOLCANO’09 Challenge: Preliminary Results. In: Brown M (ed) Proceedings of the 2nd International workshop on pulmonary imageanalysis. CreateSpace Independent Publishing Platform, London, pp 353–364. http://www.lungworkshop.org/2009/proc2009/353.pdf
Kostis WJ, Reeves AP, Yankelevitz DF, Henschke CI (2003) Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images. Trans Med Imaging 22(10):1259–1274
Jirapatnakul AC, Mulman YD, Reeves AP, Yankelevitz DF, Henschke CI (2011) Segmentation of juxtapleural pulmonary nodules using a robust surface estimate. J Biomed Imaging 1–14
Chen B, Hideto N, Yoshihiko N, Takayuki K, Daniel R, Hiroshi H, Hirotsugu T, Masaki M, Hiroshi N, Kensaku M (2011) Automatic segmentation and identification of solitary pulmonary nodules on follow-up CT Scans based on local intensity structure analysis and non-rigid image registration. SPIE, p 79630B
Gribben H, Miller P, Hanna GG, Carson KJ, Hounsell AR (2009) MAP-MRF segmentation of lung tumours in PET/CT images. Biomedical imaging: IEEE International Symposium, p 290–293
Kanakatte A, Gubbi J, Mani N, Kron T, Binns D (2007) A pilot study of automatic lung tumor segmentation from positron emission tomography images using standard uptake values. Computational intelligence in imaging signal processing, p 363–368
Gu Y, Kumar V, Hall LO, Goldgof DB, Li CY, Korn R, Bendtsen C, Velazquez ER, Dekker A, Aerts H, Lambin P, Li X, Tian J, Gatenby R, Gillies RJ (2013) Automated delineation of lung tumors from CT images using a single click ensemble segmentation approach. Pattern Recognit 46(3):692–702
Risser L, Baluwala H, Schnabel JA (2011) Diffeomorphic registration with sliding conditions: application to the registration of lungs CT images. MICCAI, 4th international workshop pulmonary image analysis, p 79–90
Gorbunova V, Durrleman S, Lo P, Pennec X, De Bruijne M (2010) Lung CT registration combining intensity, curves and surfaces. International symposium on biomedical imaging: From Nano to Macro, p 340–343
Murphy K, van Ginneken B, Reinhardt J, Kabus S, Ding K, Deng X, Cao K, Du K, Christensen G, Garcia V, Vercauteren T, Ayache N, Commowick O, Malandain G, Glocker B, Paragios N, Navab N (2011) Evaluation of registration methods on thoracic CT: the EMPIRE10. Chall Trans Med Imaging 30(11):1901–1920
Song G, Tustison N, Avants B, Gee JC (2010) Lung CT image registration using diffeomorphic transformation models. Medical image analysis for the clinic: a grand challenge, pp 23–32
Modat M, McClelland J, Ourselin S (2010) Lung registration using the NiftyReg package. Med Image Anal Clin:33–42
Kronman A, Joskowicz L, Sosna J (2012) Anatomical structures segmentation by spherical 3d ray casting and gradient domain editing. In: Medical image computing and computer assisted intervention:363–70
Tan Y, Schwartz LH, Zhao B (2013) Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random field. Med Phys 40(4):043502
Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW (2010) Elastix: a toolbox for intensity-based medical image registration. Trans Med Imaging 29(1):196–205
Bærentzen JA (2001) On the implementation of fast marching methods for 3D lattices. Math Model 13:1–19
Acknowledgments
This work was partially supported by KAMIN Grant 46217 from the Israeli Ministry of Trade and Industry.
Conflict of interest
None of the authors has any conflict of interest. The authors have no personal financial or institutional interest in any of the materials, software, or devices described in this article.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Vivanti, R., Joskowicz, L., Karaaslan, O.A. et al. Automatic lung tumor segmentation with leaks removal in follow-up CT studies. Int J CARS 10, 1505–1514 (2015). https://doi.org/10.1007/s11548-015-1150-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-015-1150-0