#PAGE_PARAMS# #ADS_HEAD_SCRIPTS# #MICRODATA#

Segmentation of distal airways using structural analysis


Autoři: Debora Gil aff001;  Carles Sanchez aff001;  Agnes Borras aff001;  Marta Diez-Ferrer aff002;  Antoni Rosell aff003
Působiště autorů: Comp. Vision Center and Comp. Science Dept, UAB, Barcelona, Spain aff001;  Pneumology Unit, Hosp. Univ. Bellvitge, IDIBELL, CIBERES, Barcelona, Spain aff002;  Hosp. Univ. Germans Trias i Pujol, Badalona, Spain aff003
Vyšlo v časopise: PLoS ONE 14(12)
Kategorie: Research Article
doi: https://doi.org/10.1371/journal.pone.0226006

Souhrn

Segmentation of airways in Computed Tomography (CT) scans is a must for accurate support of diagnosis and intervention of many pulmonary disorders. In particular, lung cancer diagnosis would benefit from segmentations reaching most distal airways. We present a method that combines descriptors of bronchi local appearance and graph global structural analysis to fine-tune thresholds on the descriptors adapted for each bronchial level. We have compared our method to the top performers of the EXACT09 challenge and to a commercial software for biopsy planning evaluated in an own-collected data-base of high resolution CT scans acquired under different breathing conditions. Results on EXACT09 data show that our method provides a high leakage reduction with minimum loss in airway detection. Results on our data-base show the reliability across varying breathing conditions and a competitive performance for biopsy planning compared to a commercial solution.

Klíčová slova:

Algorithms – Anisotropy – Bronchi – Computed axial tomography – Convolution – Diagnostic medicine – Pulmonary imaging – Structural analysis


Zdroje

1. Osborne D, Vock P, Godwin JD, Silverman PM. CT identification of bronchopulmonary segments: 50 normal subjects. American journal of roentgenology. 1984;142(1):47–52. doi: 10.2214/ajr.142.1.47 6606964

2. Dolina MY, Cornish DC, et al. Interbronchoscopist variability in endobronchial path selection: a simulation study. CHEST. 2008;133 (4):897–905. doi: 10.1378/chest.07-2540 18263679

3. Reynisson PJ, Leira HO, Hernes TN, Hofstad EF, Scali M, Sorger H, et al. Navigated bronchoscopy: a technical review. Journal of bronchology & interventional pulmonology. 2014;21(3):242–264. doi: 10.1097/LBR.0000000000000064

4. Eberhardt R, Kahn N, Gompelmann D, Schumann M, Heussel CP, Herth FJF. LungPoint–a new approach to peripheral lesions. JThorac Oncol. 2010;5(10):1559–1563. doi: 10.1097/JTO.0b013e3181e8b308

5. Pu J, Gu S, Liu S, Zhu S, Wilson D, Siegfried JM, et al. CT based computerized identification and analysis of human airways: a review. Medical physics. 2012;39(5):2603–2616. doi: 10.1118/1.4703901 22559631

6. Diez-Ferrer M, Cubero N, Lopez R, Minchole E, Dorca J, Rosell A. Relation between the bronchus sign and segmented airways in virtual bronchoscopic navigation. Impact on bronchoscopic diagnostic yield. In: ECBIP; 2017.

7. Nardelli P, Khan KA, Corvò A, Moore N, Murphy MJ, Twomey M, et al. Optimizing parameters of an open-source airway segmentation algorithm using different CT images. Biomedical engineering online. 2015;14(1):62. doi: 10.1186/s12938-015-0060-2 26112975

8. Reynisson PJ, Scali M, Smistad E, Hofstad EF, Leira HO, Lindseth F, et al. Airway Segmentation and Centerline Extraction from Thoracic CT–Comparison of a New Method to State of the Art Commercialized Methods. PloS one. 2015;10(12):e0144282. doi: 10.1371/journal.pone.0144282 26657513

9. Xu Z, Bagci U, Foster B, Mollura DJ. A hybrid multi-scale approach to automatic airway tree segmentation from CT scans. In: ISBI; 2013.

10. Rizi FY, Ahmadian A, Rezaie N, Iranmanesh SA. Leakage suppression in human airway tree segmentation using shape optimization based on fuzzy connectivity method. Int J Imaging Syst Technol. 2013;23(1):71–84. doi: 10.1002/ima.22040

11. Salito C, Barazzetti L, Woods JC, Aliverti A. 3D airway tree reconstruction in healthy subjects and emphysema. Lung. 2011;189(4):287–293. doi: 10.1007/s00408-011-9305-4

12. Gao D, Gao X, Ni C, Zhang T. MGRG-morphological gradient based 3D region growing algorithm for airway tree segmentation in image guided intervention therapy. In: ISBB; 2011. p. 76–79.

13. Graham MW, Gibbs JD, Cornish DC, Higgins WE. Robust 3-D airway tree segmentation for image-guided peripheral bronchoscopy. IEEE transactions on medical imaging. 2010;29(4):982–997. doi: 10.1109/TMI.2009.2035813 20335095

14. Petersen J, Nielsen M, Lo P, Saghir Z, Dirksen A, De Bruijne M. Optimal graph based segmentation using flow lines with application to airway wall segmentation. In: BICIPMI; 2011. p. 49–60.

15. Bauer C, Eberlein M, Beichel RR. Graph-based airway tree reconstruction from chest CT scans: evaluation of different features on five cohorts. TMI. 2015;34 (5):1063–1076.

16. Charbonnier JP, Van Rikxoort EM, Setio AA, Schaefer-Prokop CM, van Ginneken B, Ciompi F. Improving airway segmentation in computed tomography using leak detection with convolutional networks. Medical image analysis. 2017;36 : 52–60. doi: 10.1016/j.media.2016.11.001 27842236

17. Lo P, van Ginneken B, Reinhardt JM, Yavarna T, de Jong PA, Irving B, et al. Extraction of Airways from CT (EXACT09). TMI. 2012;31 : 2093–2107.

18. Diez-Ferrer M, Gil D, Carreño E, Padrones S, Aso S, Vicens V, et al. Positive airway pressure-enhanced CT to improve virtual bronchoscopic navigation. In: AABIP-CHEST; 2016.

19. Burden R, Faires J. Numerical Analysis (3rd ed). PWS Publishers; 1985.

20. Lowe D. Distinctive Image Features from Scale-Invariant Keypoints. IJCV. 2004;60(2):91–110. doi: 10.1023/B:VISI.0000029664.99615.94

21. Bertalmío M, Sapiro G, Caselles V, Ballester C. Image Inpainting. In: SIGGRAPH; 2000.

22. Chatfield K, Simonyan K, Vedaldi A, Zisserman A. Return of the Devil in the Details: Delving Deep into Convolutional Nets. In: BMVC; 2014.

23. Van Uitert R, Bitter I. Subvoxel precise skeletons of volumetric data based on fast marching methods. Med Phys. 2007;34(2):627–638. doi: 10.1118/1.2409238 17388180

24. Kerschnitzki M, Kollmannsberger P, Burghammer M, Duda GN, Weinkamer R, Wagermaier W, et al. Architecture of the osteocyte network correlates with bone material quality. JBMR. 2013;28(8):1837–45. doi: 10.1002/jbmr.1927

25. Diez-Ferrer M, Gil D, Tebe C, Sanchez C, Cubero N, López-Lisbona R, et al. Positive airway pressure to enhance computed tomography imaging for airway segmentation for virtual bronchoscopic navigation. Respiration. 2018;96(6):525–534. doi: 10.1159/000490915 30227414

26. Stoel BC, Putter H, Bakker ME, Dirksen A, Stockley RA, Piitulainen E, et al. Volume correction in computed tomography densitometry for follow-up studies on pulmonary emphysema. Proceedings of the American Thoracic Society. 2008;5(9):919–924. doi: 10.1513/pats.200804-040QC 19056717

27. F Inoue YLWI Y Kitamura. Robust airway extraction based on machine learning and minimum spanning tree. In: SPIE; 2013.

28. Ramírez E, Sánchez C, Borràs A, Diez-Ferrer M, Rosell A, Gil D. BronchoX: bronchoscopy exploration software for biopsy intervention planning. Healthcare technology letters. 2018;5(5):177–182. doi: 10.1049/htl.2018.5074 30464850


Článek vyšel v časopise

PLOS One


2019 Číslo 12
Nejčtenější tento týden
Nejčtenější v tomto čísle
Kurzy

Zvyšte si kvalifikaci online z pohodlí domova

BONE ACADEMY 2025
nový kurz
Autoři: prof. MUDr. Pavel Horák, CSc., doc. MUDr. Ludmila Brunerová, Ph.D, doc. MUDr. Václav Vyskočil, Ph.D., prim. MUDr. Richard Pikner, Ph.D., MUDr. Olga Růžičková, MUDr. Jan Rosa, prof. MUDr. Vladimír Palička, CSc., Dr.h.c.

Cesta pacienta nejen s SMA do nervosvalového centra
Autoři: MUDr. Jana Junkerová, MUDr. Lenka Juříková

Svět praktické medicíny 2/2025 (znalostní test z časopisu)

Eozinofilní zánět a remodelace
Autoři: MUDr. Lucie Heribanová

Hypertrofická kardiomyopatie: Moderní přístupy v diagnostice a léčbě
Autoři: doc. MUDr. David Zemánek, Ph.D., MUDr. Anna Chaloupka, Ph.D.

Všechny kurzy
Kurzy Podcasty Doporučená témata Časopisy
Přihlášení
Zapomenuté heslo

Zadejte e-mailovou adresu, se kterou jste vytvářel(a) účet, budou Vám na ni zaslány informace k nastavení nového hesla.

Přihlášení

Nemáte účet?  Registrujte se

#ADS_BOTTOM_SCRIPTS#