Abstract
Tumor delineation accuracy directly affects the effectiveness of radiotherapy. This study presents a methodology that minimizes potential errors during the automated segmentation of tumors in PET images. Iterative blind deconvolution was implemented in a region of interest encompassing the tumor with the number of iterations determined from contrast-to-noise ratios. The active contour and random forest classification-based segmentation method was evaluated using three distinct image databases that included both synthetic and real heterogeneous tumors. Ground truths about tumor volumes were known precisely. The volumes of the tumors were in the range of 0.49–26.34 cm3, 0.64–1.52 cm3, and 40.38–203.84 cm3 respectively. Widely available software tools, namely, MATLAB, MIPAV, and ITK-SNAP were utilized. When using the active contour method, image restoration reduced mean errors in volumes estimation from 95.85 to 3.37%, from 815.63 to 17.45%, and from 32.61 to 6.80% for the three datasets. The accuracy gains were higher using datasets that include smaller tumors for which PVE is known to be more predominant. Computation time was reduced by a factor of about 10 in the smaller deconvolution region. Contrast-to-noise ratios were improved for all tumors in all data. The presented methodology has the potential to improve delineation accuracy in particular for smaller tumors at practically feasible computational times.
Similar content being viewed by others
Abbreviations
- 3D-OSEM:
-
3D ordered subset expectation maximization
- ACRF:
-
Active contour and random forest classification-based segmentation
- AT:
-
Adaptive thresholding
- CE:
-
Classification error
- CNR:
-
Contrast-to-noise ratio
- DSC:
-
Dice similarity coefficient
- FCM:
-
Fuzzy C-means
- FNF:
-
False negative volume fraction
- FOV:
-
Field of view
- FPF:
-
False positive volume fraction
- FWHM:
-
Full width at half maximum
- MAE:
-
Mean absolute error
- MET:
-
Maximum entropy thresholding
- MSE:
-
Mean square error
- NCAT:
-
NURBS-based cardiac-torso
- NEMA:
-
National Electrical Manufacturers Association image quality phantom
- PSF:
-
Point spread function
- PSNR:
-
Peak signal to noise ratio
- PVC:
-
Partial volume correction
- PVE:
-
Partial volume effect
- RC:
-
Recovery coefficients
- RG:
-
Region growing
- ROI:
-
Region of interest
- RTP:
-
Radiation treatment planning
- SNR:
-
Signal to noise ratio
- SSIM:
-
Structural similarity index
- SUV:
-
Standardized uptake value
- TPF:
-
True positive volume fraction
- VE%:
-
Volume error percentage
- VOI:
-
Volume of interest
References
deKemp RA, Wells RG, Beanlands RSB (2018) Lesion contrast recovery for partial-volume averaging: quantitative correction or qualitative enhancement? J Nucl Cardiol 25:1757–1759. https://doi.org/10.1007/s12350-017-0869-0
Jomaa H, Mabrouk R, Khlifa N (2018) Post-reconstruction-based partial volume correction methods: a comprehensive review. Biomed Signal Process Control 46:131–144. https://doi.org/10.1016/j.bspc.2018.05.029
Erlandsson K (2017) Partial volume correction in PET imaging. In: Basic science of PET imaging. Springer, pp 355–378. doi: https://doi.org/10.1007/978-3-319-40070-9_15
Bettinardi V, Castiglioni I, De Bernardi E, Gilardi MC (2014) PET quantification: strategies for partial volume correction. Clin Trans Imaging 2:199–218. https://doi.org/10.1007/s40336-014-0066-y
Hielscher AH Model-based iterative image reconstruction for photon migration tomography. In, 1997. International Society for Optics and Photonics, pp 106–117
Rousset O, Rahmim A, Alavi A, Zaidi H (2007) Partial volume correction strategies in PET. PET Clin 2:235–249. https://doi.org/10.1016/j.cpet.2007.10.005
David LB, Ryan TF, James EH, Robert JN, Robert J (2010) A method for partial volume correction of PET-imaged tumor heterogeneity using expectation maximization with a spatially varying point spread function. Phys Med Biol 55:221–236. https://doi.org/10.1088/0031-9155/55/1/013
Hatt M, Le Pogam A, Visvikis D, Pradier O, Le Rest CC (2012) Impact of partial-volume effect correction on the predictive and prognostic value of baseline 18F-FDG PET images in esophageal cancer. J Nucl Med 53:12–20. https://doi.org/10.2967/jnumed.111.092775
Kirov AS, Piao JZ, Schmidtlein CR (2008) Partial volume effect correction in PET using regularized iterative deconvolution with variance control based on local topology. Phys Med Biol 53:2577–2591. https://doi.org/10.1088/0031-9155/53/10/009
Merlin T, Visvikis D, Fernandez P, Lamare F (2015) A novel partial volume effects correction technique integrating deconvolution associated with denoising within an iterative PET image reconstruction. Med Phys 42:804–819. https://doi.org/10.1118/1.4905162
Rizzo G, Castiglioni I, Russo G, Tana MG, Dell'Acqua F, Gilardi MC, Fazio F, Cerutti S (2007) Using deconvolution to improve PET spatial resolution in OSEM iterative reconstruction. Methods Inf Med 46:231–235. https://doi.org/10.1055/s-0038-1625413
Teo B-K, Seo Y, Bacharach SL, Carrasquillo JA, Libutti SK, Shukla H, Hasegawa BH, Hawkins RA, Franc BL (2007) Partial-volume correction in PET: validation of an iterative postreconstruction method with phantom and patient data. J Nucl Med 48:802–810. https://doi.org/10.2967/jnumed.106.035576
Guvenis A, Koc A (2015) Optimising delineation accuracy of tumours in PET for radiotherapy planning using blind deconvolution. Radiat Prot Dosim 165:495–498. https://doi.org/10.1093/rpd/ncv110
Li L, Wang J, Lu W, Tan S (2017) Simultaneous tumor segmentation, image restoration, and blur kernel estimation in PET using multiple regularizations. Comput Vis Image Underst 155:173–194. https://doi.org/10.1016/j.cviu.2016.10.002
Koç A, Güvenış A Implementation method in blind deconvolution based tumor segmentation using simulated PET images. In, 2017. IEEE, pp 1–4. doi:https://doi.org/10.1109/TIPTEKNO.2017.8238127
Cysouw MCF, Kramer GM, Schoonmade LJ, Boellaard R, De Vet HCW, Hoekstra OS (2017) Impact of partial-volume correction in oncological PET studies: a systematic review and meta-analysis. Eur J Nucl Med Mol Imaging 44:2105–2116
Conti M, Casey ME Estimating the optimal iteration number in iterative reconstruction: a statistical approach. In, 2007. IEEE, pp 4389–4394. doi:https://doi.org/10.1109/NSSMIC.2007.4437085
Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M (2013) The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26:1045–1057. https://doi.org/10.1007/s10278-013-9622-7
Muzi P, Wanner, Michelle, Kinahan, Paul. Data from RIDER_PHANTOM_PET-CT (2015). The Cancer Imaging Archive. doi: https://doi.org/10.7937/K9/TCIA.2015.8WG2KN4W. Accessed 19 April 2016
Tomei S, Reilhac A, Visvikis D, Boussion N, Odet C, Giammarile F, Lartizien C (2010) OncoPET_DB: a freely distributed database of realistic simulated whole body 18F-FDG PET images for oncology. IEEE Trans Nucl Sci 57:246–255. https://doi.org/10.1109/TNS.2009.2034375
Papadimitroulas P, Loudos G, Le Maitre A, Hatt M, Tixier F, Efthimiou N, Nikiforidis GC, Visvikis D, Kagadis GC (2013) Investigation of realistic PET simulations incorporating tumor patient’s specificity using anthropomorphic models: creation of an oncology database. Med Phys 40:112506. https://doi.org/10.1118/1.4826162
Bakr S, Gevaert O, Echegaray S, Ayers K, Zhou M, Shafiq M, Zheng H, Zhang W, Leung A, Kadoch M (2017) Data for NSCLC Radiogenomics Collection. The Cancer Imaging Archive
Gevaert O, Xu J, Hoang CD, Leung AN, Xu Y, Quon A, Rubin DL, Napel S, Plevritis SK (2012) Non-small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data—methods and preliminary results. Radiology 264:387–396
Beyer T, Townsend DW, Czernin J, Freudenberg LS (2011) The future of hybrid imaging—part 2: PET/CT. Insights into Imaging 2:225–234. https://doi.org/10.1007/s13244-011-0069-4
El-Gamal FE-ZA, Elmogy M, Atwan A (2016) Current trends in medical image registration and fusion. Egyptian Informatics Journal 17:99–124. https://doi.org/10.1016/j.eij.2015.09.002
Mahmoudzadeh AP, Kashou NH (2013) Evaluation of interpolation effects on upsampling and accuracy of cost functions-based optimized automatic image registration. Journal of Biomedical Imaging 2013:16. https://doi.org/10.1155/2013/395915
Jiang S, Zhang P, Han T, Liu W, Liu M (2013) Tri-linear interpolation-based cerebral white matter fiber imaging. Neural Regen Res 8:2155–2164. https://doi.org/10.3969/j.issn.1673-5374.2013.23.005
McAuliffe MJ, Lalonde FM, McGarry D, Gandler W, Csaky K, Trus BL Medical image processing, analysis and visualization in clinical research. In: Computer-based medical systems, 2001. CBMS 2001. Proceedings. 14th IEEE Symposium on, 2001. IEEE, pp 381–386. doi:https://doi.org/10.1109/CBMS.2001.941749
Ayers GR, Dainty JC (1988) Iterative blind deconvolution method and its applications. Opt Lett 13:547–549. https://doi.org/10.1364/OL.13.000547
Fish DA, Brinicombe AM, Pike ER, Walker JG (1995) Blind deconvolution by means of the Richardson–Lucy algorithm. JOSA A 12:58–65. https://doi.org/10.1364/JOSAA.12.000058
MATLAB and Image Processing Toolbox Release 2015a, MathWorks I, Natick, Massachusetts, United States
Medical Image Processing, Analysis and Visualization (MIPAV) (version 7.3.0) 2015, The National Institutes of Health Center for Information Technology (CIT), http://mipav.cit.nih.gov/
Greffier J, Macri F, Larbi A, Fernandez A, Khasanova E, Pereira F, Mekkaoui C, Beregi JP (2015) Dose reduction with iterative reconstruction: optimization of CT protocols in clinical practice. Diag Interven Imaging 96:477–486. https://doi.org/10.1016/j.diii.2015.02.007
Nandy K, Kim J, McCullough DP, McAuliffe M, Meaburn KJ, Yamaguchi TP, Gudla PR, Lockett SJ (2014) Segmentation and quantitative analysis of individual cells in developmental tissues. In: Mouse Molecular Embryology. Springer, pp 235–253
Cabello J, Bailey A, Kitchen I, Guy M, Wells K Segmentation of low contrast-to-noise ratio images applied to functional imaging using adaptive region growing. In, 2009. International Society for Optics and Photonics, p 725940. doi: https://doi.org/10.1117/12.811325
Foster B, Bagci U, Mansoor A, Xu Z, Mollura DJ (2014) A review on segmentation of positron emission tomography images. Comput Biol Med 50:76–96. https://doi.org/10.1016/j.compbiomed.2014.04.014
Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, Gerig G (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31:1116–1128. https://doi.org/10.1016/j.neuroimage.2006.01.015
ITK-SNAP, 2017 (version 3.6.0), Yushkevich PA, Gerig G, http://itksnap.org
Davis JB, Reiner B, Huser M, Burger C, Székely G, Ciernik IF (2006) Assessment of 18F PET signals for automatic target volume definition in radiotherapy treatment planning. Radiother Oncol 80:43–50
Sahoo PK, Soltani S, Wong AKC (1988) A survey of thresholding techniques. Comput Vision, Graphics, Image Process 41:233–260
Yushkevich PA, Gao Y, Gerig G ITK-SNAP: An interactive tool for semi-automatic segmentation of multi-modality biomedical images. In, 2016. IEEE, pp 3342–3345
Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22:61–79
Zhou H, Schaefer G, Shi C (2009) Fuzzy C-means techniques for medical image segmentation. In: Fuzzy systems in bioinformatics and computational biology. Springer, pp 257–271
Khamwan K, Krisanachinda A, Pluempitiwiriyawej C (2012) Automated tumour boundary delineation on 18F-FDG PET images using active contour coupled with shifted-optimal thresholding method. Phys Med Biol 57:5995–6005. https://doi.org/10.1088/0031-9155/57/19/5995
Zou KH, Warfield SK, Bharatha A, Tempany CMC, Kaus MR, Haker SJ, Wells Iii WM, Jolesz FA, Kikinis R (2004) Statistical validation of image segmentation quality based on a spatial overlap index1: scientific reports. Acad Radiol 11:178–189
IBM Corp. Released 2015. IBM SPSS Statistics for Windows, Version 23.0. Armonk, NY: IBM Corp.,
Hatt M, Le Rest CC, Turzo A, Roux C, Visvikis D (2009) A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET. IEEE Trans Med Imaging 28:881–893. https://doi.org/10.1109/TMI.2008.2012036
Firouzian A, Kelly MD, Declerck JM (2014) Insight on automated lesion delineation methods for PET data. EJNMMI Res 4:69. https://doi.org/10.1186/s13550-014-0069-8
Cheebsumon P, Yaqub M, van Velden FHP, Hoekstra OS, Lammertsma AA, Boellaard R (2011) Impact of [18 F] FDG PET imaging parameters on automatic tumour delineation: need for improved tumour delineation methodology. Eur J Nucl Med Mol Imaging 38:2136–2144. https://doi.org/10.1007/s00259-011-1899-5
Soret M, Bacharach SL, Buvat I (2007) Partial-volume effect in PET tumor imaging. J Nucl Med 48:932–945. https://doi.org/10.2967/jnumed.106.035774
Xu Z, Gao M, Papadakis GZ, Luna B, Jain S, Mollura DJ, Bagci U (2018) Joint solution for PET image segmentation, denoising, and partial volume correction. Med Image Anal 46:229–243. https://doi.org/10.1016/j.media.2018.03.007
Kipli K, Krishnan S, Zamhari N, Muhammad MS, Masra SMW, Chin KL, Lias K Full reference image quality metrics and their performance. In, 2011. IEEE, pp 33–38
Laasmaa M, Vendelin M, Peterson P (2011) Application of regularized Richardson–Lucy algorithm for deconvolution of confocal microscopy images. J Microsc 243:124–140. https://doi.org/10.1111/j.1365-2818.2011.03486.x
Acknowledgments
The authors sincerely acknowledge the National Cancer Institute and the National Institute of Health for RIDER PHANTOM PET-CT data obtained from the publicly available Cancer Imaging Archive (TCIA). In addition, the authors would like to thank Sandrine Tomei, Anthonin Reilhac, Dimitris Visvikis, Nicolas Boussion, Christophe Odet, Francesco Giammarile, and Carole Lartizien for simulated PET oncology images obtained from the OncoPET_DB database. Finally, the authors also thank Panagiotis Papadimitroulas, George Loudos, Amandine Le Maitre, Mathieu Hatt, Florent Tixier, Nikos Efthimiou, George C. Nikiforidis, Dimitris Visvikis, and George C. Kagadis for simulated clinical images obtained from an oncology database.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Koç, A., Güveniş, A. Design and evaluation of an accurate CNR-guided small region iterative restoration-based tumor segmentation scheme for PET using both simulated and real heterogeneous tumors. Med Biol Eng Comput 58, 335–355 (2020). https://doi.org/10.1007/s11517-019-02094-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-019-02094-8