Modelowanie struktur anatomicznych dla potrzeb planowania leczenia w procesie radioterapii nowotworu prostaty

• Autorzy: Skalski A.

Warianty tytułu

EN

Anatomical structure modelling for treatment planning in prostate cancer radiotherapy process

• Języki publikacji: PL

Abstrakty

PL

W pracy przedstawiono problematykę modelowania struktur anatomicznych zobrazowanych w danych tomograficznych na przykładzie pacjentów z nowotworem prostaty. Modele wiedzy a priori umożliwiają znaczące zwiększenie skuteczności segmentacji dla potrzeb planowania leczenia radioterapeutycznego pacjentów z chorobą nowotworową. Opisane i przebadane metody wykorzystywały informację o położeniu pacjenta zapisaną w formacie DICOM, transformację afiniczną oraz jednoczesne deformowalne dopasowanie wielu obrazów wykorzystujące funkcję B-sklejane. Metodologia została przetestowana na rzeczywistych danych tomograficznych. Otrzymane wyniki potwierdzają skuteczność zaprezentowanego rozwiązania z wykorzystaniem połączenia globalnej transformacji i deformowalnego modelowania.

EN

In developed countries, prostate cancer is one of the most often tumors in male population. Radiotherapy is a very important treatment in prostate cancer therapy. The most important, difficult and time-consuming part of radiation therapy planning is precise, manual anatomical organ delineation by medical doctors. For this reason development of special, fast, data-robust, automatic or semi-automatic CT data segmentation methods is a crucial and challenging research topic in image-guided radiother-apy. In a solution of this kind a priori knowledge of segmentation algo-rithms can improve the effectiveness considerably. In the paper there is proposed a method for construction of a geometrical and value model of anatomical structures for prostate, bladder, femoral heads and rectum from the CT data making use of groupwise registration. A short state of the art of model building (Section 2) for medical images is shown. The main idea of the described method is average 3D image creation from training images using combination of an affine transform and B-Spline Free Form Deformation in the groupwise framework [17]. As a result, the algorithm provides 3D deformation fields which can be used for mapping manual outlines of anatomical structures connected to training data made by a medical doctor. The model was built using CT data of real patients with prostate cancer. Exemplary results are shown in Fig. 3. This kind of model can be used as a priori knowledge in segmentation algorithms like deformable models or level sets. The proposed solution was compared with the affine transform and mapping based on the patient position provided with CT images in DICOM format (Section 3) in a qualitative (Fig. 1) and quantitative (Tab. 1) way. The obtained results are presented and discussed in the paper.

Słowa kluczowe

PL

CT; modelowanie struktur anatomicznych; segmentacja; radioterapia; prostata; dopasowanie obrazów

EN

CT; anatomical structure modelling; segmentation; radiotherapy; prostate; image registration

• Wydawca: Wydawnictwo PAK
• Czasopismo: Pomiary Automatyka Kontrola
• Rocznik: 2012
• Tom: R. 58, nr 4
• Strony: 372--375
• Opis fizyczny: Bibliogr. 17 poz., rys., tab., wzory

Twórcy

autor

Skalski A.

• AGH Akademia Górniczo-Hutnicza, Katedra Metrologii, Al. Mickiewicza 30, 30-059 Warszawa,

Bibliografia

• [1] (pod red.) Krzakowski M., et al.: Onkologia w Praktyce Klinicznej. tom. 3, supl. C, VIA MEDICA, str. 274-281, Gdańsk, 2007.
• [2] Chen, S., Lovelock, M., and Radke, R. J.: Segmenting the prostate and rectum in CT imagery using anatomical constraints. Medical Image Analysis 15 (1), str. 1-11, 2011.
• [3] Cootes T. F., i in.: Traning models of shape from sets of examples. Proceedings of the British Machine Vision Conference. Leads, UK, str. 9-18, 1992.
• [4] Cootes T. F., Cooper D., Taylor C. J. and Graham J.: Active Shape Models - Their Training and Application. Computer Vision and Image Understanding. 61 (1), str. 38-59, 1995.
• [5] Cootes T. F., Edwards G. J. and C. J.Taylor: Active Appearance Models. Proceedings of European Conference on Computer Vision. Vol. 2, str. 484-498, Springer, 1998.
• [6] Jeong, Y., Radke, R.: Reslicing axially sampled 3D shapes using elliptic Fourier descriptors. Medical Image Analysis, 11 (2), str. 197-206, 2007.
• [7] Heimann T., Meinzer H. P.: Statistical shape models for 3D medical image segmentation: A review, Medical Image Analysis. 13 (4), str. 543-563, 2009.
• [8] Rohlfing T. i in.: Quo Vadis, Atlas-Based Segmentation?. W: J. Suri, D. L. Wilson, and S. Laxminarayan (eds.), The Handbook of Medical Image Analysis: Segmentation and Registration Models, Kluwer, 2005.
• [9] Acosta, O. i in.: Atlas Based Segmentation and Mapping of Organs at Risk from Planning CT for the Development of Voxel-Wise Predictive Models of Toxicity in Prostate Radiotherapy. A. Madabhushi et al. (Eds.): Prostate Cancer Imaging, LNCS 6367, Springer-Verlag, str. 42-51. 2010.
• [10] Skalski A. i in.: Computed tomography-based radiotherapy planning on the example of prostate cancer: application of level-set segmentation method guided by atlas-type knowledge. Proc. of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL’11). ACM. 2011. DOI: 10.1145/2093698. 2093840
• [11] Martin, S., Daanen V., Troccaz J.: Atlas-based prostate segmentation using an hybrid registration. International Journal of Computer Assisted Radiology and Surgery. 3 str. 485-492, 2008. DOI: 10.1007/ s11548-008-0247-0.
• [12] Klein, S., i in.: Segmentation of the prostate in MR images by Atlas Matching. 4th IEEE International Symposium on Biomedical Imaging From Nano to Macro. str. 1300-1303, 2007.
• [13] Pasquier D., i in.: Automatic segmentation on pelvic structures from Magnetic Resonance images for prostate cancer radiotherapy. Int. J. Radiation Oncology Biol. Phys., 68 (2), str. 592-600, 2007.
• [14] Digital Imaging and Communications in Medicine. DICOM. http://medical.nema.org/
• [15] Rueckert D., i in.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Transactions on Medical Imaging, 18 (8), str.712-721, 1999.
• [16] Thirion J. P.: Image matching as a diffusion process: an analogy with Maxwell’s demon’s. Medical Image Analysis. 2 (3), str. 243-260, 1998.
• [17] Balci, S. K., Golland, P., Wells, W. M.: Non-rigid Groupwise Registration using B-Spline Deformation Model. The Insight Journal. DOI= http://hdl.handle.net/1926/568 2007.