Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Machine Learning in Medical Imaging

MLMI 2017: Machine Learning in Medical Imaging pp 334–343Cite as

Neural Network Convolution (NNC) for Converting Ultra-Low-Dose to “Virtual” High-Dose CT Images

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 10541))

Abstract

To reduce radiation dose in CT, we developed a novel deep-learning technique, neural network convolution (NNC), for converting ultra-low-dose (ULD) to “virtual” high-dose (HD) CT images with less noise or artifact. NNC is a supervised image-based machine-learning (ML) technique consisting of a neural network regression model. Unlike other typical deep learning, NNC can learn thus output desired images, as opposed to class labels. We trained our NNC with ULDCT (0.1 mSv) and corresponding “teaching” HDCT (5.7 mSv) of an anthropomorphic chest phantom. Once trained, our NNC no longer require HDCT, and it provides “virtual” HDCT where noise and artifact are substantially reduced. To test our NNC, we collected ULDCT (0.1 mSv) of 12 patients with 3 different vendor CT scanners. To determine a dose reduction rate of our NNC, we acquired 6 CT scans of the anthropomorphic chest phantom at 6 different radiation doses (0.1–3.0 mSv). Our NNC reduced noise and streak artifacts in ULDCT substantially, while maintaining anatomic structures and pathologies such as vessels and nodules. With our NNC, the image quality of ULDCT (0.1 mSv) images was improved at the level equivalent to 1.1 mSv CT images, which corresponds to 91% dose reduction.

This is a preview of subscription content, 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   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight 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

Learn about institutional subscriptions

References

  1. National Lung Screening Trial Research, T., Church, T.R., Black, W.C., Aberle, D.R., Berg, C.D., Clingan, K.L., Duan, F., Fagerstrom, R.M., Gareen, I.F., Gierada, D.S., Jones, G.C., Mahon, I., Marcus, P.M., Sicks, J.D., Jain, A., Baum, S.: Results of initial low-dose computed tomographic screening for lung cancer. N. Engl. J. Med. 368, 1980–1991 (2013)

    Google Scholar 

  2. Brenner, D.J., Hall, E.J.: Computed tomography–an increasing source of radiation exposure. N. Engl. J. Med. 357, 2277–2284 (2007)

    Article  Google Scholar 

  3. Kalra, M.K., Woisetschlager, M., Dahlstrom, N., Singh, S., Digumarthy, S., Do, S., Pien, H., Quick, P., Schmidt, B., Sedlmair, M., Shepard, J.A., Persson, A.: Sinogram-affirmed iterative reconstruction of low-dose chest CT: effect on image quality and radiation dose. AJR Am. J. Roentgenol. 201, W235–W244 (2013)

    Article  Google Scholar 

  4. Volders, D., Bols, A., Haspeslagh, M., Coenegrachts, K.: Model-based iterative reconstruction and adaptive statistical iterative reconstruction techniques in abdominal CT: comparison of image quality in the detection of colorectal liver metastases. Radiology 269, 469–474 (2013)

    Article  Google Scholar 

  5. Lambert, L., Ourednicek, P., Jahoda, J., Lambertova, A., Danes, J.: Model-based vs hybrid iterative reconstruction technique in ultralow-dose submillisievert CT colonography. Br. J. Radiol. 88, 20140667 (2015)

    Article  Google Scholar 

  6. Thomas, P., Hayton, A., Beveridge, T., Marks, P., Wallace, A.: Evidence of dose saving in routine CT practice using iterative reconstruction derived from a national diagnostic reference level survey. Br. J. Radiol. 88, 20150380 (2015)

    Article  Google Scholar 

  7. Suzuki, K.: Supervised machine learning technique for reduction of radiation dose in computed tomography imaging. United States Patent No. US9332953 (2012)

    Google Scholar 

  8. Suzuki, K., Liu, Y., Higaki, T., Funama, Y., Awai, K.: Supervised conversion of ultra-low-dose to higher-dose CT images by using pixel-based machine learning: Phantom and initial patient studies. In: Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA), Chicago, IL, vol. SST14-06 (2013)

    Google Scholar 

  9. Fukumoto, W., Suzuki, K., Higaki, T., Awaya, Y., Fujita, M., Awai, K.: Lung Cancer Screening (LCS) in Ultra-low-dose CT (U-LDCT) by Means of Massive-Training Artificial Neural Network (MTANN) Image-Quality Improvement: An Initial Clinical Trial. In: Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA), Chicago, IL, vol. SSG14-01, (2015)

    Google Scholar 

  10. Suzuki, K., Higaki, T., Fukumoto, W., Awai, K.: “Virtual” high-dose CT: Converting ultra-low-dose (ULD) to higher-dose (HD) CT by means of supervised pixel-based machine-learning technique. In: Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA), Chicago, IL, vol. CHS-251 (2014)

    Google Scholar 

  11. Chen, H., Zhang, Y., Zhang, W., Liao, P., Li, K., Zhou, J., Wang, G.: Low-dose CT via convolutional neural network. Biomed. Opti. Express 8, 679–694 (2017)

    Article  Google Scholar 

  12. Wolterink, J.M., Leiner, T., Viergever, M.A., Isgum, I.: Generative adversarial networks for noise reduction in low-dose CT. In: IEEE Transactions on Medical Imaging (2017)

    Google Scholar 

  13. Suzuki, K., Horiba, I., Ikegaya, K., Nanki, M.: Recognition of coronary arterial stenosis using neural network on DSA system. Syst. Comput. Jpn. 26, 66–74 (1995)

    Article  Google Scholar 

  14. Suzuki, K., Horiba, I., Sugie, N.: A simple neural network pruning algorithm with application to filter synthesis. Neural Process. Lett. 13, 43–53 (2001)

    Article  MATH  Google Scholar 

  15. Suzuki, K., Horiba, I., Sugie, N.: Efficient approximation of neural filters for removing quantum noise from images. IEEE Trans. Signal Process. 50, 1787–1799 (2002)

    Article  Google Scholar 

  16. Suzuki, K., Armato 3rd, S.G., Li, F., Sone, S., Doi, K.: Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. Med. Phys. 30, 1602–1617 (2003)

    Article  Google Scholar 

  17. Suzuki, K., Horiba, I., Sugie, N.: Neural edge enhancer for supervised edge enhancement from noisy images. IEEE Trans. Pattern Anal. Mach. Intell. 25, 1582–1596 (2003)

    Article  Google Scholar 

  18. Suzuki, K., Horiba, I., Sugie, N., Nanki, M.: Neural filter with selection of input features and its application to image quality improvement of medical image sequences. IEICE Trans. Inf. Syst. E85-D, 1710–1718 (2002)

    Google Scholar 

  19. Suzuki, K., Horiba, I., Sugie, N., Nanki, M.: Extraction of left ventricular contours from left ventriculograms by means of a neural edge detector. IEEE Trans. Med. Imaging 23, 330–339 (2004)

    Article  Google Scholar 

  20. Suzuki, K., Li, F., Sone, S., Doi, K.: Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network. IEEE Trans. Med. Imaging 24, 1138–1150 (2005)

    Article  Google Scholar 

  21. Suzuki, K., Yoshida, H., Nappi, J., Armato 3rd, S.G., Dachman, A.H.: Mixture of expert 3D massive-training ANNs for reduction of multiple types of false positives in CAD for detection of polyps in CT colonography. Med. Phys. 35, 694–703 (2008)

    Article  Google Scholar 

  22. Xu, J., Suzuki, K.: Massive-training support vector regression and Gaussian process for false-positive reduction in computer-aided detection of polyps in CT colonography. Med. Phys. 38, 1888–1902 (2011)

    Article  Google Scholar 

  23. Suzuki, K., Zhang, J., Xu, J.: Massive-training artificial neural network coupled with Laplacian-eigenfunction-based dimensionality reduction for computer-aided detection of polyps in CT colonography. IEEE Trans. Med. Imaging 29, 1907–1917 (2010)

    Article  Google Scholar 

  24. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)

    Article  MATH  Google Scholar 

  25. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)

    Article  Google Scholar 

  26. Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process. 15, 3736–3745 (2006)

    Article  MathSciNet  Google Scholar 

  27. Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16, 2080–2095 (2007)

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgments

The authors are grateful to Y. Liu, Ph.D. at Zhejiang University of Technology, S. Chen, Ph.D., at University of Shanghai for Science and Technology, M.K. Kalra, M.D. at Massachusetts General Hospital, S. Date, M.D. at Hiroshima University Hospital, Y. Funama, Ph.D. at Kumamoto University for discussing the issues and current status of CT and dose reduction techniques.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering & Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL, USA

    Kenji Suzuki, Junchi Liu & Amin Zarshenas

  2. Department of Diagnostic Radiology, Institute of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan

    Toru Higaki, Wataru Fukumoto & Kazuo Awai

Authors
  1. Kenji Suzuki
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Junchi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Amin Zarshenas
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Toru Higaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wataru Fukumoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kazuo Awai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kenji Suzuki .

Editor information

Editors and Affiliations

  1. Shanghai Jiao Tong University, Shanghai, China

    Qian Wang

  2. Nanjing University , Nanjing, China

    Yinghuan Shi

  3. Korea University , Seoul, Korea (Republic of)

    Heung-Il Suk

  4. Illinois Institute of Technology, Chicago, Illinois, USA

    Kenji Suzuki

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Suzuki, K., Liu, J., Zarshenas, A., Higaki, T., Fukumoto, W., Awai, K. (2017). Neural Network Convolution (NNC) for Converting Ultra-Low-Dose to “Virtual” High-Dose CT Images. In: Wang, Q., Shi, Y., Suk, HI., Suzuki, K. (eds) Machine Learning in Medical Imaging. MLMI 2017. Lecture Notes in Computer Science(), vol 10541. Springer, Cham. https://doi.org/10.1007/978-3-319-67389-9_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-67389-9_39

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-67388-2

  • Online ISBN: 978-3-319-67389-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation