Segmentation of pulmonary vascular tree from 3D CT thorax scans

• Autorzy: Fabijańska A.

Identyfikatory

DOI

10.1016/j.bbe.2014.07.001

• Języki publikacji: EN

Abstrakty

EN

This paper considers the problem of pulmonary vessels identification in thoracic 3D CT scans. In particular, the method for pulmonary vascular tree segmentation is introduced. The main idea behind the introduced method is to extract both thoracic trees together (i.e. the vascular tree and the airway tree) and then remove airway walls. Therefore, firstly segmentation of vessels and airway walls is performed using 3D region growing where the growth of the region is guided and constrained by results of random walk segmentation applied to consecutive CT slices. In particular, results of random walk segmentation of one slice are used to determine seeds for random walk segmentation of the following slice. Next step is airway tree segmentation using 3D region growing algorithm guided and constrained by the morphological gradient. Finally, morphological processing is applied in order to extend airway lumen onto airway walls and remove the overlapping regions. The main steps of the proposed approach are described in detail. Results of pulmonary vascular tree segmentation from example thoracic volumetric CT datasets provided by the introduced approach are presented and discussed. Based on a manually selected and radiologist's verified ground truth pixels and the resulting quality measures it can be concluded, that the average accuracy of the introduced approach is about 90%.

Słowa kluczowe

EN

pulmonary vascular tree; airway tree; 3D CT; image segmentation; region growing; Random walk segmentation

PL

drzewo naczyniowe płuc; drzewo oskrzelowe; skan 3D CT; segmentacja obrazu

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2015
• Tom: Vol. 35, no. 2
• Strony: 106--119
• Opis fizyczny: Bibliogr. 36 poz., rys., tab., wykr.

Twórcy

autor

Fabijańska A.

• Lodz University of Technology, Institute of Applied Computer Science, 18/22 Stefanowskiego Str., 90-924 Lodz, Poland

Bibliografia

• [1] Jardins T. Cardiopulmonary anatomy & physiology: essentials for respiratory care. Clifton Park, New York, USA: Delmar Cengage Learning; 2007.
• [2] Masutani Y, MacMahon H, Doi K. Computerized detection of pulmonary embolism in spiral CT angiography based on volumetric image analysis. IEEE Trans Med Imag 2002;21 (11):1517–23.
• [3] Linguraru M, Pura J, Uitert R, Mukherjee N, Summers R, Minniti C, et al. Segmentation and quantification of pulmonary artery for noninvasive CT assessment of sickle cell secondary pulmonary hypertension. Med Phys 2010;37(4):1522–32.
• [4] Croisille P, Souto M, Cova M, Wood S, Afework Y, Kuhlman J, et al. Pulmonary nodules: improved detection with vascular segmentation and extraction with spiral CT. Radiology 1995;197(2):397–401.
• [5] Zhu X, Xue Z, Gao X, Zhu Y. VOLES. Vascularity-oriented level set algorithm for pulmonary vessel segmentation in image guided intervention therapy. Biomedical Imaging: From Nano to Macro, ISBI '09. IEEE International Symposium on; 2009. pp. 1247–50.
• [6] Sonka M, Park W, Hoffman E. Rule-based detection of intrathoracic airway trees. IEEE Trans Med Imag 1996;15 (3):314–26.
• [7] Lo P, Sporring J, Ashraf H, Pedersen J, de Bruijne M. Vessel-guided airway tree segmentation: a voxel classification approach. Med Image Anal 2010;14(4):527–38.
• [8] Kirbas C, Quek F. A review of vessel extraction techniques and algorithms. J ACM Comput Surv 2004;36(2):81–121.
• [9] Fabijańska A. Two-pass region growing algorithm for segmenting airway tree from MDCT chest scans. Comput Med Imag Grap 2009;33(7):537–46.
• [10] Mason R, Broaddus V, Martin T, King T, Schraufnagel D, Murray J, et al. Murray and Nadel's textbook of respiratory medicine. Maryland Heights, USA: W.B. Saunders; 2010.
• [11] Kaftan J, Aach T. Pulmonary vessel segmentation for multislice CT data: methods and applications. In: Suri J, editor. Lung imaging and computer aided diagnosis. Boca Raton, Florida: CRC; 2011. pp. 189–219.
• [12] Wood E, Hoford J, Hoffman E, Mitzner M. Measurement of three-dimension lung tree structures by using computed tomography. J Appl Physiol 1995;79(5):687–1697.
• [13] Kiraly A, Pichon E, Naidich D, Novak C. Analysis of arterial subtrees affected by pulmonary emboli. Proc SPIE Med Imag 2004;5370:1720–9.
• [14] Zhou X, Hayashi T, Hara T, Fujita H, Yokoyama R, Kiryu T, et al. Automatic segmentation and recognition of anatomical lung structures from high-resolution chest CT images. Comput Med Imag Graph 2006;30(5):299–313.
• [15] Wu C, Agam G, Roy A, Armato S. Regulated morphology approach to fuzzy shape analysis with application to blood vessel extraction in thoracic CT scans. Proc SPIE Med Imag 2004;5370:1262–70.
• [16] Park S. Artery-vein separation from thoracic CTA scans with application to PE detection and volume visualization [Ph.D. thesis]. Austin, TX: University of Texas at Austin; 2006.
• [17] Masutani Y, MacMahon H, Doi K. Automated segementation and visualization of the pulmonary vascular tree in spiral CT angiography: an anatomy-oriented approach based on three-dimensional image analysis. J Comput Assist Tomo 2001;25:587–97.
• [18] Bruyninckx P, Loeckx D, Vandermeulen D, Suetens P. Segmentation of lung vessel trees by global optimization. Proc SPIE Med Imag 2009;7259:1–12.
• [19] Shikata H, Hoffman E, Sonka M. Automated segmentation of pulmonary vascular tree from 3D CT images. Proc SPIE Med Imag 2004;5369:107–16.
• [20] Shikata H, McLennan G, Hoffman E, Sonka M. Segmentation of pulmonary vascular trees from thoracic 3D CT images. Int J Biomed Imag 2009;2009:107. http://dx.doi.org/10.1155/2009/636240. Article ID 636240.
• [21] van Dongen E, van Ginneken B. Automatic segmentation of pulmonary vasculature in thoracic CT scans with local thresholding and airway wall removal. Biomedical Imaging: From Nano to Macro, 2010 IEEE International Symposium on; 2010. pp. 668–671.
• [22] Frangi A, Niessen W, Vincken K, Viergever M. Multiscale vessel enhancement filtering. LNCS 1998;1496:130–7.
• [23] Sato Y, Nakajima S, Shiraga N, Atsumi H, Yoshida S, Koller T, et al. Threedimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. Med Image Anal 1998;2(2):143–68.
• [24] Krissian K, Malandain G, Ayache N, Vaillant R, Trousset Y. Model based detection of tubular structures in 3D images. Comput Vis Image Und 2000;80(2):130–71.
• [25] Xiao C, Staring M, Shamonin D, Reiber J, Stolk J, Stoel B. A strain energy filter for 3D vessel enhancement with application to pulmonary CT images. Med Image Anal 2011;15(1):112–24.
• [26] Hang H, Bian Z, Dazong J, Yuan Z, Ye M. Level set method for pulmonary vessels extraction. Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on; 2003. II - 1105-8 vol. 3.
• [27] Buelow T, Wiemker R, Blaffert T, Lorenz C, Renisch S. Automatic extraction of the pulmonary artery tree from multi-slice CT data. Proc SPIE Med Imag 2005;5746:730–40.
• [28] Lorigo L, Faugeras O, Grimson W, Keriven R. Curves: curve evolution for vessel segmentation. Med Image Anal 2001;5 (3):195–206.
• [29] Kaftan J, Kiraly A, Bakai A, Das M, Novak C, Aach T. Fuzzy pulmonary vessel segmentation in contrast enhanced CT data. Proc SPIE Med Imag 2008;6914:1–12.
• [30] Agam G, Armato S, Changhua W. Vessel tree reconstruction in thoracic CT scans with application to nodule detection. IEEE Trans Med Imag 2005;24(4):486–99.
• [31] Fetita C, Brillet P, Preteux F. Morpho-geometrical approach for 3D segmentation of pulmonary vascular tree in multi-slice CT. Proc SPIE Med Imag 2009;7259:1–12.
• [32] Lo P, van Ginneken B, Reinhardt J, de Bruijne M. Extraction of airways from CT (EXACT'09). Second International Workshop on Pulmonary Image Analysis, Create Space. 2009. pp. 175–89.
• [33] Extraction of airways from CT, Exact'09; 2009.
• [34] Grady L. Random walks for image segmentation. IEEE Trans Pattern Anal 2006;28(11):1768–83.
• [35] Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 1979;9(1):62–6.
• [36] Brown M, de Bruijne M, van Ginneken B, Kiraly A, Kuhnigk J, Lorenz C, et al. The Second International Workshop on Pulmonary Image Analysis, Create Space; 2009.