Skip to main content
SpringerLink
Log in

Bone Suppression in Chest Radiographs by Means of Anatomically Specific Multiple Massive-Training ANNs Combined with Total Variation Minimization Smoothing and Consistency Processing

  • Chapter
  • First Online:
Computational Intelligence in Biomedical Imaging

Abstract

Most lung nodules that are missed by radiologists as well as computer-aided detection (CADe) schemes overlap with ribs or clavicles in chest radiographs (CXRs). The purpose of this study was to separate bony structures such as ribs and clavicles from soft tissue in CXRs. To achieve this, we developed anatomically (location-) specific multiple massive-training artificial neural networks (MTANNs) which is a class of pixel-based machine learning combined with total variation (TV) minimization smoothing and a histogram-matching-based consistency processing technique. Multi-resolution MTANNs have previously been developed for rib suppression by use of input CXRs and the corresponding “teaching” images for training. Although they were able to suppress ribs, they did not suppress rib edges, ribs close to the lung wall, and the clavicles very well because the orientation, width, contrast, and density of bones are different from location to location and the capability of a single set of multi-resolution MTANNs is limited. To address this issue, the anatomically specific multiple MTANNs developed in this work were designed to separate bones from soft tissue in different anatomic segments of the lungs. Each of multiple anatomically specific MTANNs was trained with the corresponding anatomic segment in the teaching bone images. The output segmental images from the multiple MTANNs were merged to produce a whole bone image. Total variation minimization smoothing was applied to the bone image for reduction of noise while edges were preserved. This bone image was then subtracted from the original CXR to produce a soft-tissue image where the bones were separated out. In order to ensure the contrast and density in different segments were consistent, a histogram-matching technique was applied to the input segmental images. This new method was compared with the conventional MTANNs by using a database of 110 CXRs with pulmonary nodules. Our new anatomically (location-) specific MTANNs separated rib edges, ribs close to the lung wall, and the clavicles from soft tissue in CXRs to a substantially higher level than the conventional MTANNs did, while the visibility of lung nodules and vessels was maintained. Thus, our image-processing technique for bone-soft-tissue separation by means of our new anatomically specific multiple MTANNs would be potentially useful for radiologists as well as for CAD schemes in detection of lung nodules on CXRs.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Murray CJ, Lopez AD (1997) Mortality by cause for eight regions of the world: global burden of disease study. Lancet 349:1269–1276

    Article  Google Scholar 

  2. Murphy GP et al (1995) American Cancer Society textbook of clinical oncology, 2nd edn. The American Cancer Society, Atlanta

    Google Scholar 

  3. Frost JK et al (1984) Early lung cancer detection: results of the initial (prevalence) radiologic and cytologic screening in the Johns Hopkins study. Am Rev Respir Dis 130:549–554

    Google Scholar 

  4. Fontana RS et al (1984) Early lung cancer detection: results of the initial (prevalence) radiologic and cytologic screening in the Mayo Clinic study. Am Rev Respir Dis 130:561–565

    Google Scholar 

  5. Henschke CI et al (1994) Radiographic screening for cancer. Proposed paradigm for requisite research. Clin Imaging 18:16–20

    Article  Google Scholar 

  6. Heelan RT et al (1984) Non-small-cell lung cancer: results of the New York screening program. Radiology 151:289–293

    Google Scholar 

  7. Sobue T et al (1992) Survival for clinical stage I lung cancer not surgically treated. Comparison between screen-detected and symptom-detected cases. The Japanese Lung Cancer Screening Research Group. Cancer 69:685–692

    Article  Google Scholar 

  8. Flehinger BJ et al (1992) The effect of surgical treatment on survival from early lung cancer. Implications for screening. Chest 101:1013–1018

    Article  Google Scholar 

  9. Austin JH et al (1992) Missed bronchogenic carcinoma: radiographic findings in 27 patients with a potentially resectable lesion evident in retrospect. Radiology 182:115–122

    Google Scholar 

  10. Shah PK et al (2003) Missed non-small cell lung cancer: radiographic findings of potentially resectable lesions evident only in retrospect. Radiology 226:235–241

    Article  Google Scholar 

  11. Li F et al (2008) Improved detection of small lung cancers with dual-energy subtraction chest radiography. AJR Am J Roentgenol 190:886–891

    Article  Google Scholar 

  12. Giger ML et al (1988) Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields. Med Phys 15:158–166

    Article  Google Scholar 

  13. van Ginneken B et al (2001) Computer-aided diagnosis in chest radiography: a survey. IEEE Trans Med Imaging 20:1228–1241

    Article  Google Scholar 

  14. Abe K et al (1993) Computer-aided diagnosis in chest radiography. Preliminary experience. Invest Radiol 28:987–993

    Article  Google Scholar 

  15. Kobayashi T et al (1996) Effect of a computer-aided diagnosis scheme on radiologists’ performance in detection of lung nodules on radiographs. Radiology 199:843–848

    Google Scholar 

  16. Kakeda S et al (2004) Improved detection of lung nodules on chest radiographs using a commercial computer-aided diagnosis system. AJR Am J Roentgenol 182:505–510

    Article  Google Scholar 

  17. Matsumoto T et al (1992) Image feature analysis of false-positive diagnoses produced by automated detection of lung nodules. Invest Radiol 27:587–597

    Article  Google Scholar 

  18. Xu XW et al (1997) Development of an improved CAD scheme for automated detection of lung nodules in digital chest images. Med Phys 24:1395–1403

    Article  Google Scholar 

  19. Kido S et al (2002) Detection of simulated pulmonary nodules by single-exposure dual-energy computed radiography of the chest: effect of a computer-aided diagnosis system (part 2). Eur J Radiol 44:205–209

    Article  Google Scholar 

  20. Kido S et al (2002) Computerized detection of pulmonary nodules by single-exposure dual-energy computed radiography of the chest (part 1). Eur J Radiol 44:198–204

    Article  Google Scholar 

  21. Glocker R, Frohnmayer W (1925) Uber die rontgenspektroskopische Bestimmung des Gewichtsanteiles eines Elementes in Gememgen und Verbindungen. Ann Phys 76:369–395

    Article  Google Scholar 

  22. Jacobson B, Mackay RS (1958) Radiological contrast enhancing methods. Adv Biol Med Phys 6:201–261

    Article  Google Scholar 

  23. Suzuki K et al (2006) Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN). IEEE Trans Med Imaging 25:406–416

    Article  Google Scholar 

  24. Suzuki K et al (2004) Suppression of the contrast of ribs in chest radiographs by means of massive training artificial neural network. In: Proceedings of SPIE medical imaging (SPIE MI), San Diego, pp 1109–1119

    Google Scholar 

  25. Suzuki K (2012) Pixel-based machine learning in medical imaging. Int J Biomed Imaging 2012:18

    Google Scholar 

  26. Oda S et al (2009) Performance of radiologists in detection of small pulmonary nodules on chest radiographs: effect of rib suppression with a massive-training artificial neural network. AJR Am J Roentgenol 193:W397–W402

    Article  Google Scholar 

  27. Ahmed B, Rasheed T (2007) Rib suppression for enhancing frontal chest radiographs using independent component analysis. In: Adaptive and natural computing algorithms. Lecture notes in computer science, vol 4432. Springer, New York, pp 300–308

    Google Scholar 

  28. Loog M et al (2006) Filter learning: application to suppression of bony structures from chest radiographs. Med Image Anal 10:826–840

    Article  Google Scholar 

  29. Ishigaki T et al (1986) One-shot dual-energy subtraction imaging. Radiology 161:271–273

    Google Scholar 

  30. Ishigaki T et al (1988) One-shot dual-energy subtraction chest imaging with computed radiography: clinical evaluation of film images. Radiology 168:67–72

    Google Scholar 

  31. Stewart BK, Huang HK (1990) Single-exposure dual-energy computed radiography. Med Phys 17:866–875

    Article  Google Scholar 

  32. Suzuki K et al (2003) Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose CT. Med Phys 30:15

    Article  Google Scholar 

  33. Suzuki K et al (1995) Recognition of coronary arterial stenosis using neural network on DSA system. Syst Comput Jpn 26:66–74

    Article  Google Scholar 

  34. Suzuki K et al (2003) Neural edge enhancer for supervised edge enhancement from noisy images. IEEE Trans Pattern Anal Mach Intell 25:1582–1596

    Article  Google Scholar 

  35. Xu J, Suzuki K (2011) Massive-training support vector regression and Gaussian process for false-positive reduction in computer-aided detection of polyps in CT colonography. Med Phys 38:14

    Google Scholar 

  36. van Ginneken B et al (2006) Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med Image Anal 10:19–40

    Article  Google Scholar 

  37. Chen S et al (2011) Development and evaluation of a computer-aided diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification. Med Phys 38:15

    Article  Google Scholar 

  38. van Ginneken B et al (2002) Active shape model segmentation with optimal features. IEEE Trans Med Imaging 21:924–933

    Article  Google Scholar 

  39. Rudin LI et al (1992) Nonlinear total variation based noise removal algorithms. Physica D 60:259–268

    Article  MATH  Google Scholar 

Download references

Acknowledgments

The authors are grateful to Heber MacMahon, MD, for his valuable clinical suggestions. Initial bone suppression technology and source code have been non-exclusively licensed to Riverain Medical (Riverain Technologies). It is the policy of University of Chicago that investigators disclose publicly actual or potential financial interests that may appear to be affected by research activities.

Author information

Authors and Affiliations

  1. University of Shanghai for Science and Technology, Room 402, Building of Optical and Electrical Engineering School, 516 Jungong Road, Shanghai, 200093, China

    Sheng Chen

  2. Department of Radiology, University of Chicago, 5841 South Maryland Avenue, MC 2026, Chicago, IL, 60637, USA

    Sheng Chen & Kenji Suzuki

Authors
  1. Sheng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kenji Suzuki
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sheng Chen .

Editor information

Editors and Affiliations

  1. Department of Radiology, University of Chicago, Chicago, Illinois, USA

    Kenji Suzuki

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer Science+Business Media New York

About this chapter

Cite this chapter

Chen, S., Suzuki, K. (2014). Bone Suppression in Chest Radiographs by Means of Anatomically Specific Multiple Massive-Training ANNs Combined with Total Variation Minimization Smoothing and Consistency Processing. In: Suzuki, K. (eds) Computational Intelligence in Biomedical Imaging. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-7245-2_9

Download citation

  • DOI: https://doi.org/10.1007/978-1-4614-7245-2_9

  • Published:

  • Publisher Name: Springer, New York, NY

  • Print ISBN: 978-1-4614-7244-5

  • Online ISBN: 978-1-4614-7245-2

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation