Skip to main content
SpringerLink
Log in

A novel bone suppression method that improves lung nodule detection

Suppressing dedicated bone shadows in radiographs while preserving the remaining signal

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Suppressing thoracic bone shadows in chest radiographs has been previously reported to improve the detection rates for solid lung nodules, however at the cost of increased false detection rates. These bone suppression methods are based on an artificial neural network that was trained using dual-energy subtraction images in order to mimic their appearance.

Method

Here, a novel approach is followed where all bone shadows crossing the lung field are suppressed sequentially leaving the intercostal space unaffected. Given a contour delineating a bone, its image region is spatially transferred to separate normal image gradient components from tangential component. Smoothing the normal partial gradient along the contour results in a reconstruction of the image representing the bone shadow only, because all other overlaid signals tend to cancel out each other in this representation.

Results

The method works even with highly contrasted overlaid objects such as a pacemaker. The approach was validated in a reader study with two experienced chest radiologists, and these images helped improving both the sensitivity and the specificity of the readers for the detection and localization of solid lung nodules. The AUC improved significantly from 0.596 to 0.655 on a basis of 146 images from patients and normals with a total of 123 confirmed lung nodules.

Conclusion

Subtracting all reconstructed bone shadows from the original image results in a soft image where lung nodules are no longer obscured by bone shadows. Both the sensitivity and the specificity of experienced radiologists increased.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

Notes

  1. Images publicly available from http://www.jsrt.or.jp/jsrt-db/eng.php.

  2. Images publicly available from http://cancerimagingarchive.net.

References

  1. Ahmed B, Rasheed T, Khan MA, Cho SJ, Lee S, Kim TS (2007) Rib suppression for enhancing frontal chest radiographs using independent component analysis. In: Beliczynski B, Dzielinski A, Iwanowski M, Ribeiro B (eds) Adaptive and natural computing algorithms. Springer, Berlin, pp 300–308

  2. Armato SG III, McLennan G, Bidaut L, McNitt-Gray MF, Meyer CR, Reeves AP, Zhao B, Aberle DR, Henschke CI, Hoffman EA, Kazerooni EA, MacMahon H, van Beek EJR, Yankelevitz D, Biancardi AM, Bland PH, Brown MS, Engelmann RM, Laderach GE, Max D, Pais RC, Qing DPY, Roberts RY, Smith AR, Starkey A, Batra P, Caligiuri P, Farooqi A, Gladish GW, Jude CM, Munden RF, Petkovska I, Quint LE, Schwartz LH, Sundaram B, Dodd LE, Fenimore C, Gur D, Petrick N, Freymann J, Kirby J, Hughes B, Casteele AV, Gupte S, Sallam M, Heath MD, Kuhn MH, Dharaiya E, Burns R, Fryd DS, Salganicoff M, Anand V, Shreter U, Vastagh S, Croft BY, Clarke LP (2011) The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on ct scans. Med Phys 38(2):915–931

    Article  PubMed  PubMed Central  Google Scholar 

  3. DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845

  4. Freedman MT, Lo SCB, Seibel JC, Bromley CM (2011) Lung nodules: improved detection with software that suppresses the rib and clavicle on chest radiographs. Radiology 260(1):265–273

    Article  PubMed  Google Scholar 

  5. Hogeweg L, Sanchez C, van Ginneken B (2013) Suppression of translucent elongated structures: applications in chest radiography. IEEE Trans Med Imaging 32(11):2099–2113

  6. Hogeweg LE, Mol C, de Jong PA, van Ginneken B (2010) Rib suppression in chest radiographs to improve classification of textural abnormalities. In: Proceedings of the SPIE medical imaging, vol 7624

  7. Horváth Á, Orbán GG, Horváth Á, Horváth G (2013) An X-ray CAD system with ribcage suppression for improved detection of lung lesions. Electr Eng Comput Sci 57(1):19–33

    Google Scholar 

  8. Horváth G, Orbán G, Horváth Á, Simkó G, Pataki B, Máday P, Juhász S (2009) A CAD system for screening X-ray chest radiography. In: World congress on medical physics and biomedical engineering, September 7–12, 2009, Springer, Munich, Germany, pp 210–213

  9. Kim S, Pyo HB, Lee SK, Lee S, Park SH (2000) Digital image subtraction of temporally sequential chest images by rib image elimination. In: Proceedings of the 22nd annual international conference of the IEEE engineering in medicine and biology society, vol 3. IEEE, pp 1752–1755

  10. Lee JS, Wang JW, Wu HH, Yuan MZ (2012) A nonparametric-based rib suppression method for chest radiographs. Comput Math Appl 64(5):1390–1399

    Article  Google Scholar 

  11. Li F, Engelmann R, Pesce L, Armato SG III, MacMahon H (2012) Improved detection of focal pneumonia by chest radiography with bone suppression imaging. Eur Radiol 22(12):2729–2735

    Article  PubMed  Google Scholar 

  12. Li F, Engelmann R, Pesce LL, Doi K, Metz CE, MacMahon H (2011) Small lung cancers: improved detection by use of bone suppression imaging—comparison with dual-energy subtraction chest radiography. Radiology 261(3):937–949

    Article  PubMed  Google Scholar 

  13. Lo SCB, Freedman MT (2012) Changes of nodule detection after radiologists read bone opacity suppressed chest radiography. In: SPIE medical imaging. International Society for Optics and Photonics, pp 83152S–83152S

  14. Loog M, van Ginneken B, Schilham AM (2006) Filter learning: application to suppression of bony structures from chest radiographs. Med Image Anal 10(6):826–840

    Article  CAS  PubMed  Google Scholar 

  15. Novak RD, Novak NJ, Gilkeson R, Mansoori B, Aandal GE (2013) A comparison of computer-aided detection (CAD) effectiveness in pulmonary nodule identification using different methods of bone suppression in chest radiographs. J Digit Imaging 26(4):651–656

  16. Orbán G, Horváth Á, Horváth G (2010) Lung nodule detection on rib eliminated radiographs. In: XII mediterranean conference on medical and biological engineering and computing 2010. Springer, pp 363–366

  17. Schalekamp S, van Ginneken B, van den Berk IAH, Hartmann IJC, Snoeren MM, Odink AE, van Lankeren W, Pegge SAH, Schijf LJ, Karssemeijer N, Schaefer-Prokop CM (2014) Bone suppression increases the visibility of invasive pulmonary aspergillosis in chest radiographs. PloS One 9(10):e108,551

    Article  Google Scholar 

  18. Schalekamp S, van Ginneken B, Meiss L, Peters-Bax L, Quekel LG, Snoeren MM, Tiehuis AM, Wittenberg R, Karssemeijer N, Schaefer-Prokop CM (2013) Bone suppressed images improve radiologists detection performance for pulmonary nodules in chest radiographs. Eur J Radiol 82(12):2399–2405

    Article  PubMed  Google Scholar 

  19. Shah PK, Austin JH, White CS, Patel P, Haramati LB, Pearson GD, Shiau MC, Berkmen YM (2003) Missed non-small cell lung cancer: radiographic findings of potentially resectable lesions evident only in retrospect 1. Radiology 226(1):235–241

    Article  PubMed  Google Scholar 

  20. Shiraishi J, Katsuragawa S, Ikezoe J, Matsumoto T, Kobayashi T, Komatsu K, Matsui M, Fujita H, Kodera Y, Doi K (2000) Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am J Roentgenol 174(1):71–74

    Article  CAS  Google Scholar 

  21. Simkó G, Orbán G, Máday P, Horváth G (2009) Elimination of clavicle shadows to help automatic lung nodule detection on chest radiographs. In: 4th European conference of the international federation for medical and biological engineering. Springer, pp 488–491

  22. Suzuki K, Abe H, MacMahon H, Doi K (2006) Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN). IEEE Trans Med Imaging 25(4):406–416

    Article  PubMed  Google Scholar 

  23. Szucs-Farkas Z, Schick A, Cullmann JL, Ebner L, Megyeri B, Vock P, Christe A (2013) Comparison of dual-energy subtraction and electronic bone suppression combined with computer-aided detection on chest radiographs: effect on human observers’ performance in nodule detection. Am J Roentgenol 200(5):1006–1013

    Article  Google Scholar 

  24. Tanaka R, Sanade M, Oda M, Suzuki M, Sakuta H, Kawashima H, Iida H (2013) Improved accuracy of IGRT with bone suppression image-processing. Int J CARS 8(suppl I):41

    Google Scholar 

  25. Vogelsang F, Weiler F, Dahmen J, Kilbinger M, Wein B, Günther R (1998) Detection and compensation of rib structures in chest radiographs for diagnose assistance. In: Proceedings of the international symposium on medical imaging, vol 3338, p 1

Download references

Acknowledgments

We would like to thank Martin Haker and Moritz Schaar, both former employees of Philips Research Hamburg, for their algorithmic contribution. We also would like to thank Raoul Florent and Claire Levrier, Philips Medisys, Paris and Harald Heese, Philips Research Hamburg, for some valuable suggestions. We are grateful to Cornelia Schaefer-Prokop, Meander Medical Center Amersfoort, the Netherlands, and Martin Uffmann, Landesklinikum Neunkirchen, Austria, for their assessments in the early phases of the project. We would like to thank C. A. Nuñez at Hospital Sant Pau, Barcelona, for her support in preparing the reader study.

Author information

Authors and Affiliations

  1. Digital Imaging, Philips Research, Hamburg, Germany

    Jens von Berg, Stewart Young, Heike Carolus & Axel Saalbach

  2. Clinical Science, Diagnostix X-Ray, Philips Healthcare, Hamburg, Germany

    Robin Wolz

  3. Department of Radiology, Hospital de la Santa Creu i Sant Pau, Carrer de Sant Quintí, 89, Barcelona, Spain

    Alberto Hidalgo, Ana Giménez & Tomás Franquet

Authors
  1. Jens von Berg
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stewart Young
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Heike Carolus
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Robin Wolz
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Axel Saalbach
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alberto Hidalgo
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ana Giménez
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Tomás Franquet
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jens von Berg.

Ethics declarations

Conflict of interest

J. von Berg, S. Young, H. Carolus, A. Saalbach, and R. Wolz are employees of Philips. A. Hidalgo, A. Giménez, and T. Franquet do not have a conflict of interest.

Appendix

Appendix

In order to prove that

$$\begin{aligned} {I}^l_{r_C}\left( \mathbf {p_i}\right) \mathop {=}\limits ^{?} {I}^c_{r_C}\left( \mathbf {p_c}\right) \end{aligned}$$

we set

$$\begin{aligned}&I_{r_C}\left( \mathbf {p_i}\right) + \frac{I_{r_C}\left( \mathbf {p_c}\right) -I_{r_C}\left( \mathbf {p_i}\right) }{2} \\&\quad \mathop {=}\limits ^{?} I_{r_C}\left( \mathbf {p_c}\right) + \frac{I_{r_C}\left( \mathbf {p_i}\right) -I_{r_C}\left( \mathbf {p_c}\right) }{2} \\&I_{r_C}\left( \mathbf {p_i}\right) -I_{r_C}\left( \mathbf {p_c}\right) \\&\quad \mathop {=}\limits ^{?} \frac{I_{r_C}\left( \mathbf {p_i}\right) -I_{r_C}\left( \mathbf {p_c}\right) - \left( I_{r_C}\left( \mathbf {p_c}\right) -I_{r_C}\left( \mathbf {p_i}\right) \right) }{2} \\&\quad I_{r_C}\left( \mathbf {p_i}\right) -I_{r_C}\left( \mathbf {p_c}\right) = I_{r_C}\left( \mathbf {p_i}\right) -I_{r_C}\left( \mathbf {p_c}\right) \end{aligned}$$

which proves the convergence of \({I}^i_{r_C}\) and \({I}^c_{r_C}\) at the centerline.

Informed consent was obtained from all patients for being included in the study.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

von Berg, J., Young, S., Carolus, H. et al. A novel bone suppression method that improves lung nodule detection. Int J CARS 11, 641–655 (2016). https://doi.org/10.1007/s11548-015-1278-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-015-1278-y

Keywords

Search

Navigation