Comparison of two-dimensional synthesized mammograms versus original digital mammograms: a quantitative assessment

Abstract

This study objectively evaluates the similarity between standard full-field digital mammograms and two-dimensional synthesized digital mammograms (2DSM) in a cohort of women undergoing mammography. Under an institutional review board–approved data collection protocol, we retrospectively analyzed 407 women with digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) examinations performed from September 1, 2014, through February 29, 2016. Both FFDM and 2DSM images were used for the analysis, and 3216 available craniocaudal (CC) and mediolateral oblique (MLO) view mammograms altogether were included in the dataset. We analyzed the mammograms using a fully automated algorithm that computes 152 structural similarity, texture, and mammographic density–based features. We trained and developed two different global mammographic image feature analysis–based breast cancer detection schemes for 2DSM and FFDM images, respectively. The highest structural similarity features were obtained on the coarse Weber Local Descriptor differential excitation texture feature component computed on the CC view images (0.8770) and MLO view images (0.8889). Although the coarse structures are similar, the global mammographic image feature–based cancer detection scheme trained on 2DSM images outperformed the corresponding scheme trained on FFDM images, with area under a receiver operating characteristic curve (AUC) = 0.878 ± 0.034 and 0.756 ± 0.052, respectively. Consequently, further investigation is required to examine whether DBT can replace FFDM as a standalone technique, especially for the development of automated objective-based methods.

Graphical abstract

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Abbreviations

DBT:

Digital breast tomosynthesis

FFDM:

Full-field digital mammography

CC:

Craniocaudal

MLO:

Mediolateral oblique

2D:

Two-dimensional

2DSM:

2D synthesized mammogram

PD:

Percentage density

SSIM:

Structural similarity index metric

CW-SSIM:

Complex wavelet-structural similarity index metric

CB-SSIM:

Correlation-based SSIM

CB-CW-SSIM:

Correlation-based CW-SSIM

WLD:

Weber Local Descriptor

LDA:

Linear discriminant analysis

ROC:

Receiver operating characteristic

AUC:

Area under a ROC curve

CI:

Confidence interval

FDA:

Food and Drug Administration

PSNR:

Peak signal-to-noise

SIFT:

Scale-invariant feature transform

LBP:

Local binary pattern

RLS:

Run-length statistic

GLCM:

Gray level co-occurrence matrix

LOCO:

Leave-one-case-out

References

  1. 1.

    Al-Kadi OS, Watson D (2008) Texture analysis of aggressive and nonaggressive lung tumor CE CT images. IEEE Trans Biomed Eng 55:1822–1830

    Article  Google Scholar 

  2. 2.

    Andersson I, Ikeda DM, Zackrisson S, Ruschin M, Svahn T, Timberg P, Tingberg A (2008) Breast tomosynthesis and digital mammography: a comparison of breast cancer visibility and BIRADS classification in a population of cancers with subtle mammographic findings. Eur Radiol 18:2817–2825. https://doi.org/10.1007/s00330-008-1076-9

    Article  PubMed  Google Scholar 

  3. 3.

    Aujero MP, Gavenonis SC, Benjamin R, Zhang Z, Holt JS (2017) Clinical performance of synthesized two-dimensional mammography combined with tomosynthesis in a large screening population. Radiology 283:70–76. https://doi.org/10.1148/radiol.2017162674

    Article  PubMed  Google Scholar 

  4. 4.

    Byng JW, Boyd NF, Fishell E, Jong RA, Yaffe MJ (1994) The quantitative analysis of mammographic densities. Phys Med Biol 39:1629–1638

    CAS  Article  Google Scholar 

  5. 5.

    Casti P, Mencattini A, Salmeri M, Rangayyan RM (2015) Analysis of structural similarity in mammograms for detection of bilateral asymmetry. IEEE Trans Med Imaging 34:662–671. https://doi.org/10.1109/tmi.2014.2365436

    Article  PubMed  Google Scholar 

  6. 6.

    Chang Y-H, Wang X-H, Hardesty LA, Chang TS, Poller WR, Good WF, Gur D (2002) Computerized assessment of tissue composition on digitized mammograms. Acad Radiol 9:899–905

    Article  Google Scholar 

  7. 7.

    Chen J, Shan S, He C, Zhao G, Pietikainen M, Chen X, Gao W (2010) WLD: a robust local image descriptor. IEEE Trans Pattern Anal Mach Intell 32:1705–1720. https://doi.org/10.1109/tpami.2009.155

    Article  PubMed  Google Scholar 

  8. 8.

    Choi G, Woo OH, Shin HS, Jang S, Cho KR, Seo BK (2017) Comparison of two-dimensional synthesized mammogram (2DSM) and conventional full-field digital mammogram (FFDM) for evaluation of breast cancer. Clin Imaging 43:170–174. https://doi.org/10.1016/j.clinimag.2017.03.004

    Article  PubMed  Google Scholar 

  9. 9.

    Choi JS, Han BK, Ko EY, Kim GR, Ko ES, Park KW (2019) Comparison of synthetic and digital mammography with digital breast tomosynthesis or alone for the detection and classification of microcalcifications. Eur Radiol 29:319–329. https://doi.org/10.1007/s00330-018-5585-x

    Article  PubMed  Google Scholar 

  10. 10.

    Conant EF, Keller BM, Pantalone L, Gastounioti A, McDonald ES, Kontos D (2017) Agreement between breast percentage density estimations from standard-dose versus synthetic digital mammograms: results from a large screening cohort using automated measures. Radiology 283:673–680. https://doi.org/10.1148/radiol.2016161286

    Article  PubMed  PubMed Central  Google Scholar 

  11. 11.

    D’Orsi CJ, Acr (2014) 2013 ACR BI-RADS atlas: breast imaging reporting and data system. American College of Radiology, Reston

    Google Scholar 

  12. 12.

    DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 11:837–845

    Article  Google Scholar 

  13. 13.

    des Plantes BGZ (1932) EINE NEUE METHODE ZUR DIFFERENZIERUNG IN DER RÖNTGENOGRAPHIE (PLANIGRAPHIE). Acta Radiol 13:182–192. https://doi.org/10.1177/028418513201300211

    Article  Google Scholar 

  14. 14.

    Galloway M (1975) Texture analysis using gray level run lengths. Comput Graph Image Process 4:172–179

    Article  Google Scholar 

  15. 15.

    Garayoa J, Chevalier M, Castillo M, Mahillo-Fernandez I, Amallal El Ouahabi N, Estrada C, Tejerina A, Benitez O, Valverde J (2018) Diagnostic value of the stand-alone synthetic image in digital breast tomosynthesis examinations. Eur Radiol 28:565–572. https://doi.org/10.1007/s00330-017-4991-9

    Article  PubMed  Google Scholar 

  16. 16.

    Gastounioti A, Conant EF, Kontos D (2016) Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment. Breast Cancer Res 18:91. https://doi.org/10.1186/s13058-016-0755-8

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  17. 17.

    Gierach GL, Li H, Loud JT, Greene MH, Chow CK, Lan L, Prindiville SA, Eng-Wong J, Soballe PW, Giambartolomei C, Mai PL, Galbo CE, Nichols K, Calzone KA, Olopade OI, Gail MH, Giger ML (2014) Relationships between computer-extracted mammographic texture pattern features and BRCA1/2 mutation status: a cross-sectional study. Breast Cancer Res 16:424. https://doi.org/10.1186/s13058-014-0424-8

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  18. 18.

    Hadjipanteli A, Kontos M, Constantinidou A (2019) The role of digital breast tomosynthesis in breast cancer screening: a manufacturer- and metrics-specific analysis. Cancer Manag Res 11:9277–9296. https://doi.org/10.2147/CMAR.S210979

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  19. 19.

    Haralick RM, Shanmugam K, Dinstein I (1973) Texture features for image classification. IEEE Trans Syst Man Cybern 3:610–621

    Article  Google Scholar 

  20. 20.

    Heidari M, Mirniaharikandehei S, Liu W, Hollingsworth AB, Liu H, Zheng B (2019) Development and assessment of a new global mammographic image feature analysis scheme to predict likelihood of malignant cases. IEEE Trans Med Imaging 39:1235–1244. https://doi.org/10.1109/tmi.2019.2946490

    Article  PubMed  Google Scholar 

  21. 21.

    Hofvind S, Hovda T, Holen AS, Lee CI, Albertsen J, Bjorndal H, Brandal SHB, Gullien R, Lomo J, Park D, Romundstad L, Suhrke P, Vigeland E, Skaane P (2018) Digital breast tomosynthesis and synthetic 2D mammography versus digital mammography: evaluation in a population-based screening program. Radiology 287:787–794. https://doi.org/10.1148/radiol.2018171361

    Article  PubMed  Google Scholar 

  22. 22.

    Hooley RJ, Durand MA, Philpotts LE (2016) Advances in digital breast tomosynthesis. Am J Roentgenol 208:256–266. https://doi.org/10.2214/AJR.16.17127

    Article  Google Scholar 

  23. 23.

    Kerlikowske K, Grady D, Barclay J, Sickles EA, Ernster V (1996) Effect of age, breast density, and family history on the sensitivity of first screening mammography. JAMA 276:33–38

    CAS  Article  Google Scholar 

  24. 24.

    Marcelja S (1980) Mathematical description of the responses of simple cortical cells. J Opt Soc Am 70:1297–1300

    CAS  Article  Google Scholar 

  25. 25.

    Mariscotti G, Durando M, Houssami N, Fasciano M, Tagliafico A, Bosco D, Casella C, Bogetti C, Bergamasco L, Fonio P, Gandini G (2017) Comparison of synthetic mammography, reconstructed from digital breast tomosynthesis, and digital mammography: evaluation of lesion conspicuity and BI-RADS assessment categories. Breast Cancer Res Treat 166:765–773. https://doi.org/10.1007/s10549-017-4458-3

    CAS  Article  PubMed  Google Scholar 

  26. 26.

    Nelson JS, Wells JR, Baker JA, Samei E (2016) How does c-view image quality compare with conventional 2D FFDM? Med Phys 43:2538–2547. https://doi.org/10.1118/1.4947293

    Article  PubMed  Google Scholar 

  27. 27.

    Portilla J, Simoncelli E (2000) A parametric texture model based on joint statistics of complex wavelet coefficients. Int J Comput Vis 40:49–70. https://doi.org/10.1023/a:1026553619983

    Article  Google Scholar 

  28. 28.

    Rafferty EA, Park JM, Philpotts LE, Poplack SP, Sumkin JH, Halpern EF, Niklason LT (2013) Assessing radiologist performance using combined digital mammography and breast tomosynthesis compared with digital mammography alone: results of a multicenter, multireader trial. Radiology 266:104–113. https://doi.org/10.1148/radiol.12120674

    Article  PubMed  PubMed Central  Google Scholar 

  29. 29.

    Rangayyan RM, Ayres FJ (2006) Gabor filters and phase portraits for the detection of architectural distortion in mammograms. Med Biol Eng Comput 44:883–894. https://doi.org/10.1007/s11517-006-0088-3

    Article  PubMed  Google Scholar 

  30. 30.

    Rodriguez-Ruiz A, Gubern-Merida A, Imhof-Tas M, Lardenoije S, Wanders AJT, Andersson I, Zackrisson S, Lång K, Dustler M, Karssemeijer N, Mann RM, Sechopoulos I (2018) One-view digital breast tomosynthesis as a stand-alone modality for breast cancer detection: do we need more? Eur Radiol 28:1938–1948. https://doi.org/10.1007/s00330-017-5167-3

    Article  PubMed  Google Scholar 

  31. 31.

    Sampat MP, Wang Z, Gupta S, Bovik AC, Markey MK (2009) Complex wavelet structural similarity: a new image similarity index. IEEE Trans Image Process 18:2385–2401. https://doi.org/10.1109/tip.2009.2025923

    Article  PubMed  Google Scholar 

  32. 32.

    Skaane P, Bandos AI, Eben EB, Jebsen IN, Krager M, Haakenaasen U, Ekseth U, Izadi M, Hofvind S, Gullien R (2014) Two-view digital breast tomosynthesis screening with synthetically reconstructed projection images: comparison with digital breast tomosynthesis with full-field digital mammographic images. Radiology 271:655–663. https://doi.org/10.1148/radiol.13131391

    Article  PubMed  Google Scholar 

  33. 33.

    Soh LK, Tsatsoulis C (1999) Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens 37:780–795. https://doi.org/10.1109/36.752194

    Article  Google Scholar 

  34. 34.

    Tan M, Aghaei F, Wang Y, Zheng B (2017) Developing a new case based computer-aided detection scheme and an adaptive cueing method to improve performance in detecting mammographic lesions. Phys Med Biol 62:358–376

    Article  Google Scholar 

  35. 35.

    Tan M, Mariapun S, Yip CH, Ng KH, Teo S-H (2019) A novel method of determining breast cancer risk using parenchymal textural analysis of mammography images on an Asian cohort. Phys Med Biol 64:035016. https://doi.org/10.1088/1361-6560/aafabd

    Article  PubMed  Google Scholar 

  36. 36.

    Tan M, Pu J, Cheng S, Liu H, Zheng B (2015) Assessment of a four-view mammographic image feature based fusion model to predict near-term breast cancer risk. Ann Biomed Eng 43:2416–2428. https://doi.org/10.1007/s10439-015-1316-5

    Article  PubMed  PubMed Central  Google Scholar 

  37. 37.

    Tan M, Qian W, Pu J, Liu H, Zheng B (2015) A new approach to develop computer-aided detection schemes of digital mammograms. Phys Med Biol 60:4413–4427. https://doi.org/10.1088/0031-9155/60/11/4413

    Article  PubMed  PubMed Central  Google Scholar 

  38. 38.

    Tan M, Zheng B, Leader JK, Gur D (2016) Association between changes in mammographic image features and risk for near-term breast cancer development. IEEE Trans Med Imaging 35:1719–1728

    Article  Google Scholar 

  39. 39.

    Tan M, Zheng B, Ramalingam P, Gur D (2013) Prediction of near-term breast cancer risk based on bilateral mammographic feature asymmetry. Acad Radiol 20:1542–1550. https://doi.org/10.1016/j.acra.2013.08.020

    Article  PubMed  Google Scholar 

  40. 40.

    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13:600–612

    Article  Google Scholar 

  41. 41.

    Zuckerman SP, Conant EF, Keller BM, Maidment AD, Barufaldi B, Weinstein SP, Synnestvedt M, McDonald ES (2016) Implementation of synthesized two-dimensional mammography in a population-based digital breast tomosynthesis screening program. Radiology 281:730–736. https://doi.org/10.1148/radiol.2016160366

    Article  PubMed  PubMed Central  Google Scholar 

  42. 42.

    Zuley ML, Guo B, Catullo VJ, Chough DM, Kelly AE, Lu AH, Rathfon GY, Spangler ML, Sumkin JH, Wallace LP, Bandos AI (2014) Comparison of two-dimensional synthesized mammograms versus original digital mammograms alone and in combination with tomosynthesis images. Radiology 271:664–671. https://doi.org/10.1148/radiol.13131530

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgments

The authors acknowledge Dr. Nazimah Ab Mumin from University Teknologi Mara for contributing most of the images used in this study.

Funding

This study was funded by the Electrical and Computer Systems Engineering and Advanced Engineering Platform, School of Engineering, Monash University Malaysia, and the University of Malaya Research Grant (Grant Number: PO035-2015).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Maxine Tan.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was waived by the obtained IRB approval.

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

Verify currency and authenticity via CrossMark

Cite this article

Tan, M., Al-Shabi, M., Chan, W.Y. et al. Comparison of two-dimensional synthesized mammograms versus original digital mammograms: a quantitative assessment. Med Biol Eng Comput 59, 355–367 (2021). https://doi.org/10.1007/s11517-021-02313-1

Download citation

Keywords

  • Mammography
  • Algorithms
  • Breast density
  • Two-dimensional synthesized mammograms
  • Structural similarity