Skip to main content

Advertisement

Log in

Automated segmentation of an intensity calibration phantom in clinical CT images using a convolutional neural network

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

Abstract

Purpose

In quantitative computed tomography (CT), manual selection of the intensity calibration phantom’s region of interest is necessary for calculating density (mg/cm3) from the radiodensity values (Hounsfield units: HU). However, as this manual process requires effort and time, the purposes of this study were to develop a system that applies a convolutional neural network (CNN) to automatically segment intensity calibration phantom regions in CT images and to test the system in a large cohort to evaluate its robustness.

Methods

This cross-sectional, retrospective study included 1040 cases (520 each from two institutions) in which an intensity calibration phantom (B-MAS200, Kyoto Kagaku, Kyoto, Japan) was used. A training dataset was created by manually segmenting the phantom regions for 40 cases (20 cases for each institution). The CNN model’s segmentation accuracy was assessed with the Dice coefficient, and the average symmetric surface distance was assessed through fourfold cross-validation. Further, absolute difference of HU was compared between manually and automatically segmented regions. The system was tested on the remaining 1000 cases. For each institution, linear regression was applied to calculate the correlation coefficients between HU and phantom density.

Results

The source code and the model used for phantom segmentation can be accessed at https://github.com/keisuke-uemura/CT-Intensity-Calibration-Phantom-Segmentation. The median Dice coefficient was 0.977, and the median average symmetric surface distance was 0.116 mm. The median absolute difference of the segmented regions between manual and automated segmentation was 0.114 HU. For the test cases, the median correlation coefficients were 0.9998 and 0.999 for the two institutions, with a minimum value of 0.9863.

Conclusion

The proposed CNN model successfully segmented the calibration phantom regions in CT images with excellent accuracy.

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

Access this article

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

Similar content being viewed by others

Data availability

The model used for phantom segmentation can be accessed via https://github.com/keisuke-uemura/CT-Intensity-Calibration-Phantom-Segmentation

Code availability

The code used for phantom segmentation can be accessed via https://github.com/keisuke-uemura/CT-Intensity-Calibration-Phantom-Segmentation

References

  1. Kanis JA, Cooper C, Rizzoli R, Reginster JY (2019) European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporos Int 30(1):3–44. https://doi.org/10.1007/s00198-018-4704-5

    Article  CAS  PubMed  Google Scholar 

  2. Orimo H, Nakamura T, Hosoi T, Iki M, Uenishi K, Endo N, Ohta H, Shiraki M, Sugimoto T, Suzuki T, Soen S, Nishizawa Y, Hagino H, Fukunaga M, Fujiwara S (2012) Japanese 2011 guidelines for prevention and treatment of osteoporosis–executive summary. Arch Osteoporos 7(1–2):3–20. https://doi.org/10.1007/s11657-012-0109-9

    Article  PubMed  PubMed Central  Google Scholar 

  3. Camacho PM, Petak SM, Binkley N, Diab DL, Eldeiry LS, Farooki A, Harris ST, Hurley DL, Kelly J, Lewiecki EM, Pessah-Pollack R, McClung M, Wimalawansa SJ, Watts NB (2020) American Association of clinical endocrinologists/American college of endocrinology clinical practice guidelines for the diagnosis and treatment of postmenopausal osteoporosis-2020 update. Endocr Pract Off J Am Coll Endocr Am Assoc Clin Endocr 26(Suppl 1):1–46. https://doi.org/10.4158/gl-2020-0524suppl

    Article  Google Scholar 

  4. Maeda Y, Sugano N, Saito M, Yonenobu K (2011) Comparison of femoral morphology and bone mineral density between femoral neck fractures and trochanteric fractures. Clin Orthop Relat Res 469(3):884–889. https://doi.org/10.1007/s11999-010-1529-8

    Article  PubMed  Google Scholar 

  5. Uemura K, Takao M, Otake Y, Hamada H, Sakai T, Sato Y, Sugano N (2018) The distribution of bone mineral density in the femoral heads of unstable intertrochanteric fractures. J Orthop Surg 26(2):2309499018778325. https://doi.org/10.1177/2309499018778325

    Article  Google Scholar 

  6. Whitmarsh T, Otake Y, Uemura K, Takao M, Sugano N, Sato Y (2019) A cross-sectional study on the age-related cortical and trabecular bone changes at the femoral head in elderly female hip fracture patients. Sci Rep 9(1):305. https://doi.org/10.1038/s41598-018-36299-y

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Hanusch BC, Tuck SP, Mekkayil B, Shawgi M, McNally RJQ, Walker J, Francis RM, Datta HK (2020) Quantitative computed tomography (QCT) of the distal forearm in men using a spiral whole-body CT scanner: description of a method and reliability assessment of the QCT Pro software. J Clin Densitom Off J Int Soc Clin Densitom 23(3):418–425. https://doi.org/10.1016/j.jocd.2019.05.005

    Article  Google Scholar 

  8. Adams JE (2009) Quantitative computed tomography. Eur J Radiol 71(3):415–424. https://doi.org/10.1016/j.ejrad.2009.04.074

    Article  PubMed  Google Scholar 

  9. Giambini H, Dragomir-Daescu D, Huddleston PM, Camp JJ, An KN, Nassr A (2015) The effect of quantitative computed tomography acquisition protocols on bone mineral density estimation. J Biomech Eng 137(11):114502. https://doi.org/10.1115/1.4031572

    Article  PubMed  Google Scholar 

  10. Lee DC, Hoffmann PF, Kopperdahl DL, Keaveny TM (2017) Phantomless calibration of CT scans for measurement of BMD and bone strength-Inter-operator reanalysis precision. Bone 103:325–333. https://doi.org/10.1016/j.bone.2017.07.029

    Article  PubMed  PubMed Central  Google Scholar 

  11. Hiasa Y, Otake Y, Takao M, Ogawa T, Sugano N, Sato Y (2020) Automated muscle segmentation from clinical CT using Bayesian U-net for personalized musculoskeletal modeling. IEEE Trans Med Imaging 39(4):1030–1040. https://doi.org/10.1109/tmi.2019.2940555

    Article  PubMed  Google Scholar 

  12. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. arXiv:150201852

  13. Kingma DP, J B (2017) Adam: a method for stochastic optimization. arXiv:14126980

  14. Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302. https://doi.org/10.2307/1932409

    Article  Google Scholar 

  15. Styner M, Lee J, Chin B, Chin M, Commowick O, Tran H, Markovic-Plese S, Jewells V, Warfield S (2008) 3D segmentation in the clinic: a grand challenge II: MS lesion segmentation. Midas J 1–5

  16. Aamodt A, Kvistad KA, Andersen E, Lund-Larsen J, Eine J, Benum P, Husby OS (1999) Determination of Hounsfield value for CT-based design of custom femoral stems. J Bone Joint surg Br 81(1):143–147

    Article  CAS  PubMed  Google Scholar 

  17. Gausden EB, Nwachukwu BU, Schreiber JJ, Lorich DG, Lane JM (2017) Opportunistic use of CT imaging for osteoporosis screening and bone density assessment: a qualitative systematic review. J Bone Joint Surg Am 99(18):1580–1590. https://doi.org/10.2106/jbjs.16.00749

    Article  PubMed  Google Scholar 

  18. Kitamura K, Fujii M, Utsunomiya T, Iwamoto M, Ikemura S, Hamai S, Motomura G, Todo M, Nakashima Y (2020) Effect of sagittal pelvic tilt on joint stress distribution in hip dysplasia: a finite element analysis. Clin Biomech 74:34–41. https://doi.org/10.1016/j.clinbiomech.2020.02.011

    Article  Google Scholar 

  19. Schreiber JJ, Anderson PA, Rosas HG, Buchholz AL, Au AG (2011) Hounsfield units for assessing bone mineral density and strength: a tool for osteoporosis management. J Bone Joint Surg Am 93(11):1057–1063. https://doi.org/10.2106/jbjs.j.00160

    Article  PubMed  Google Scholar 

  20. Mawatari T, Hayashida Y, Katsuragawa S, Yoshimatsu Y, Hamamura T, Anai K, Ueno M, Yamaga S, Ueda I, Terasawa T, Fujisaki A, Chihara C, Miyagi T, Aoki T, Korogi Y (2020) The effect of deep convolutional neural networks on radiologists’ performance in the detection of hip fractures on digital pelvic radiographs. Eur J Radiol 130:109188. https://doi.org/10.1016/j.ejrad.2020.109188

    Article  PubMed  Google Scholar 

  21. Cheng CT, Ho TY, Lee TY, Chang CC, Chou CC, Chen CC, Chung IF, Liao CH (2019) Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs. Eur Radiol 29(10):5469–5477. https://doi.org/10.1007/s00330-019-06167-y

    Article  PubMed  PubMed Central  Google Scholar 

  22. Therkildsen J, Thygesen J, Winther S, Svensson M, Hauge EM, Böttcher M, Ivarsen P, Jørgensen HS (2018) Vertebral bone mineral density measured by quantitative computed tomography with and without a calibration phantom: a comparison between 2 different software solutions. J Clin Densitom Off J Int Soc Clin Densitom 21(3):367–374. https://doi.org/10.1016/j.jocd.2017.12.003

    Article  Google Scholar 

  23. Feit A, Levin N, McNamara EA, Sinha P, Whittaker LG, Malabanan AO, Rosen HN (2019) Effect of positioning of the region of interest on bone density of the hip. J Clin Densitom Off J Int Soc Clin Densitom. https://doi.org/10.1016/j.jocd.2019.04.002

    Article  Google Scholar 

Download references

Acknowledgements

This study was supported by the Japan Society for the Promotion of Science Grants-in-Aid for Scientific Research (KAKENHI) numbers 19H01176 and 20H04550. The authors thank Tatsuya Kitaura MD and the radiological technologists for their help with data acquisition.

Funding

This study was supported by the Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (KAKENHI) Numbers 19H01176 and 20H04550.

Author information

Authors and Affiliations

Authors

Contributions

KU and YO contributed to conceptualization and methodology; KU, YO, and MS were involved in code writing; KU and AK contributed to formal analysis and investigation; KU contributed to writing—original draft preparation; YO, MT, MS, NS, and YS contributed to writing—review and editing; YO and YS contributed to funding acquisition. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Keisuke Uemura.

Ethics declarations

Conflict of interest

The authors have nothing to disclose.

Ethics approval

All procedures performed in this study were performed in accordance with the ethical standards as laid down in the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards.

Consent to participate

This study was approved by the Institutional Review Board of each participating hospital, and written informed consent was waived because of the retrospective design.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Uemura, K., Otake, Y., Takao, M. et al. Automated segmentation of an intensity calibration phantom in clinical CT images using a convolutional neural network. Int J CARS 16, 1855–1864 (2021). https://doi.org/10.1007/s11548-021-02345-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-021-02345-w

Keywords

Navigation