Digital breast tomosynthesis versus digital mammography: integration of image modalities enhances deep learning-based breast mass classification

  • Xin Li
  • Genggeng Qin
  • Qiang He
  • Lei Sun
  • Hui Zeng
  • Zilong He
  • Weiguo Chen
  • Xin ZhenEmail author
  • Linghong ZhouEmail author



To evaluate the impact of utilizing digital breast tomosynthesis (DBT) or/and full-field digital mammography (FFDM), and different transfer learning strategies on deep convolutional neural network (DCNN)-based mass classification for breast cancer.


We retrospectively collected 441 patients with both DBT and FFDM on which regions of interest (ROIs) covering the malignant, benign and normal tissues were extracted for DCNN training and validation. Experiments were conducted for tasks in distinguishing malignant/benign/normal: (1) classification capabilities of DBT vs FFDM and the role of transfer learning were validated on 2D-DCNN; (2) different strategies of combining DBT and FFDM and the associated impacts on classification were explored; (3) 2D-DCNN and 3D-DCNN trained from scratch with volumetric DBT were compared.


2D-DCNN with transfer learning outperformed that without for DBT in distinguishing malignant (ΔAUC = 0.059 ± 0.009, p < 0.001), benign (ΔAUC = 0.095 ± 0.010, p < 0.001) and normal tissue (ΔAUC = 0.042 ± 0.004, p < 0.001) (paired samples t test). 2D-DCNN trained on DBT (with transfer learning) achieved higher accuracy than those on FFDM (malignant: ΔAUC = 0.014 ± 0.014, p = 0.037; benign: ΔAUC = 0.031 ± 0.006, p < 0.001; normal: ΔAUC = 0.017 ± 0.004, p < 0.001) (independent samples t test). The 2D-DCNN employing both DBT and FFDM for training achieved better performances in benign (FFDM: ΔAUC = 0.010 ± 0.008, p < 0.001; DBT: ΔAUC = 0.009 ± 0.005, p < 0.001) and normal (FFDM: ΔAUC = 0.005 ± 0.003, p < 0.001; DBT: ΔAUC = 0.002 ± 0.002, p < 0.001) (related samples Friedman test). The 3D-DCNN and 2D-DCNN trained from scratch with DBT only produced moderate classification.


Transfer learning facilitates mass classification for both DBT and FFDM, and DBT outperforms FFDM when equipped with transfer learning. Integrating DBT and FFDM in DCNN training enhances mass classification accuracy for breast cancer.

Key Points

• Transfer learning facilitates mass classification for both DBT and FFDM, and the DBT-based DCNN outperforms the FFDM-based DCNN when equipped with transfer learning.

• Integrating DBT and FFDM in DCNN training enhances breast mass classification accuracy.

• 3D-DCNN/2D-DCNN trained from scratch with volumetric DBT but without transfer learning only produce moderate mass classification result.


Breast Mammography Deep learning Neural network (computer) Classification 





Area under the ROC curve


Computer-aided detection


Computer-aided diagnosis




Digital breast tomosynthesis


Deep convolutional neural network


Double transfer learning


Full-field digital mammography


Mixture of DBT&FFDM




Mediolateral oblique


Picture archiving and communication system


Positive predictive value


Recurrent neural network


Receiver operating characteristic


Region of interest






Single transfer learning


Transfer learning


Visual geometry group



We gratefully acknowledge all the members of Department of Radiology, Nanfang Hospital, for continuous assistance. In particular, we would like to thank Dr. Weiguo Chen for his advice during the project.

Funding information

This study has received funding by the National Natural Science Foundation of China (81874216 and 81728016), the National Key Research and Development Program of China (2017YFC0112900).

Compliance with ethical standards


The scientific guarantor of this publication is Professor Linghong Zhou.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• experimental

• performed at one institution

Supplementary material

330_2019_6457_MOESM1_ESM.docx (325 kb)
ESM 1 (DOCX 325 kb)


  1. 1.
    Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A (2018) Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 68:394–424PubMedCrossRefGoogle Scholar
  2. 2.
    Munoz D, Near AM, van Ravesteyn NT et al (2014) Effects of screening and systemic adjuvant therapy on ER-specific US breast cancer mortality. J Natl Cancer Inst 106:dju289PubMedPubMedCentralCrossRefGoogle Scholar
  3. 3.
    Youlden DR, Cramb SM, Dunn NA, Muller JM, Pyke CM, Baade PD (2012) The descriptive epidemiology of female breast cancer: an international comparison of screening, incidence, survival and mortality. Cancer Epidemiol 36:237–248PubMedCrossRefGoogle Scholar
  4. 4.
    Berry DA, Cronin KA, Plevritis SK et al (2005) Effect of screening and adjuvant therapy on mortality from breast cancer. N Engl J Med 353:1784–1792CrossRefGoogle Scholar
  5. 5.
    Althuis MD, Dozier JM, Anderson WF, Devesa SS, Brinton LA (2005) Global trends in breast cancer incidence and mortality 1973-1997. Int J Epidemiol 34:405–412PubMedCrossRefGoogle Scholar
  6. 6.
    Tagliafico A, Houssami N, Calabrese M (2016) Digital breast tomosynthesis: a practical approach, 1st edn. Springer International Publishing, New York City, New YorkCrossRefGoogle Scholar
  7. 7.
    Niklason LT, Christian BT, Niklason LE et al (1997) Digital tomosynthesis in breast imaging. Radiology 205:399–406CrossRefGoogle Scholar
  8. 8.
    Lång K, Andersson I, Rosso A, Tingberg A, Timberg P, Zackrisson S (2016) Performance of one-view breast tomosynthesis as a stand-alone breast cancer screening modality: results from the Malmo breast Tomosynthesis screening trial, a population-based study. Eur Radiol 26:184–190PubMedCrossRefGoogle Scholar
  9. 9.
    Friedewald SM, Rafferty EA, Rose SL et al (2014) Breast cancer screening using tomosynthesis in combination with digital mammography. JAMA 311:2499–2507PubMedPubMedCentralCrossRefGoogle Scholar
  10. 10.
    Durand MA, Haas BM, Yao X et al (2015) Early clinical experience with digital breast tomosynthesis for screening mammography. Radiology 274:85–92PubMedCrossRefGoogle Scholar
  11. 11.
    McCarthy AM, Kontos D, Synnestvedt M et al (2014) Screening outcomes following implementation of digital breast tomosynthesis in a general-population screening program. J Natl Cancer Inst 106:dju316PubMedPubMedCentralCrossRefGoogle Scholar
  12. 12.
    Lourenco AP, Barry-Brooks M, Baird GL, Tuttle A, Mainiero MB (2015) Changes in recall type and patient treatment following implementation of screening digital breast tomosynthesis. Radiology 274:337–342PubMedCrossRefGoogle Scholar
  13. 13.
    Skaane P, Bandos AI, Gullien R et al (2013) Comparison of digital mammography alone and digital mammography plus tomosynthesis in a population-based screening program. Radiology 267:47–56CrossRefGoogle Scholar
  14. 14.
    Skaane P, Bandos AI, Gullien R et al (2013) Prospective trial comparing full-field digital mammography (FFDM) versus combined FFDM and tomosynthesis in a population-based screening programme using independent double reading with arbitration. Eur Radiol 23:2061–2071PubMedPubMedCentralCrossRefGoogle Scholar
  15. 15.
    Ciatto S, Houssami N, Bernardi D et al (2013) Integration of 3D digital mammography with tomosynthesis for population breast-cancer screening (STORM): a prospective comparison study. Lancet Oncol 14:583–589PubMedPubMedCentralCrossRefGoogle Scholar
  16. 16.
    Haas BM, Kalra V, Geisel J, Raghu M, Durand M, Philpotts LE (2013) Comparison of tomosynthesis plus digital mammography and digital mammography alone for breast cancer screening. Radiology 269:694–700PubMedCrossRefPubMedCentralGoogle Scholar
  17. 17.
    Mall S, Noakes J, Kossoff M et al (2018) Can digital breast tomosynthesis perform better than standard digital mammography work-up in breast cancer assessment clinic? Eur Radiol 28:5182–5194PubMedCrossRefGoogle Scholar
  18. 18.
    Dang PA, Freer PE, Humphrey KL, Halpern EF, Rafferty EA (2014) Addition of tomosynthesis to conventional digital mammography: effect on image interpretation time of screening examinations. Radiology 270:49–56PubMedCrossRefGoogle Scholar
  19. 19.
    Bernardi D, Ciatto S, Pellegrini M et al (2012) Application of breast tomosynthesis in screening: incremental effect on mammography acquisition and reading time. Br J Radiol 85:e1174–e1178PubMedPubMedCentralCrossRefGoogle Scholar
  20. 20.
    Palma G, Bloch I, Muller S (2014) Detection of masses and architectural distortions in digital breast tomosynthesis images using fuzzy and a contrario approaches. Pattern Recogn 47:2467–2480CrossRefGoogle Scholar
  21. 21.
    Wei J, Chan HP, Sahiner B et al (2011) Computer-aided detection of breast masses in digital breast tomosynthesis (DBT): improvement of false positive reduction by optimization of object segmentation. In: SPIE medical imaging 2011, Lake Buena Vista, Florida, United States, 796311:1–6Google Scholar
  22. 22.
    Chan HP, Wei J, Sahiner B et al (2005) Computer-aided detection system for breast masses on digital tomosynthesis mammograms: preliminary experience. Radiology 237:1075–1080PubMedPubMedCentralCrossRefGoogle Scholar
  23. 23.
    Kim ST, Kim DH, Ro YM (2014) Breast mass detection using slice conspicuity in 3D reconstructed digital breast volumes. Phys Med Biol 59:5003–5023PubMedCrossRefGoogle Scholar
  24. 24.
    Kim DH, Kim ST, Ro YM (2015) Improving mass detection using combined feature representations from projection views and reconstructed volume of DBT and boosting based classification with feature selection. Phys Med Biol 60:8809–8832PubMedCrossRefGoogle Scholar
  25. 25.
    Kim DH, Kim ST, Baddar WJ, Ro YM (2015) Feature extraction from bilateral dissimilarity in digital breast tomosynthesis reconstructed volume. In: 2015 IEEE international conference on image processing (ICIP), Quebec City, Quebec, Canada, 4521–4524Google Scholar
  26. 26.
    Chan HP, Wu YT, Sahiner B et al (2010) Characterization of masses in digital breast tomosynthesis: comparison of machine learning in projection views and reconstructed slices. Med Phys 37:3576–3586PubMedPubMedCentralCrossRefGoogle Scholar
  27. 27.
    Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248PubMedPubMedCentralCrossRefGoogle Scholar
  28. 28.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  29. 29.
    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117PubMedCrossRefGoogle Scholar
  30. 30.
    Samala RK, Chan HP, Hadjiiski LM, Helvie MA, Wei J, Cha KH (2016) Mass detection in digital breast tomosynthesis: deep convolutional neural network with transfer learning from mammography. Med Phys 43:6654–6666PubMedPubMedCentralCrossRefGoogle Scholar
  31. 31.
    Fotin SV, Yin Y, Haldankar H, Hoffmeister JW, Periaswamy S (2016) Detection of soft tissue densities from digital breast tomosynthesis: comparison of conventional and deep learning approaches. In: SPIE medical imaging 2016, San Diego, California, United States, 97850X:1–6Google Scholar
  32. 32.
    Kim DH, Kim ST, Ro YM (2016) Latent feature representation with 3-D multi-view deep convolutional neural network for bilateral analysis in digital breast tomosynthesis. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), Shanghai, China, 927–931Google Scholar
  33. 33.
    Kim DH, Kim ST, Chang JM, Ro YM (2017) Latent feature representation with depth directional long-term recurrent learning for breast masses in digital breast tomosynthesis. Phys Med Biol 62:1009–1031PubMedCrossRefGoogle Scholar
  34. 34.
    Samala RK, Chan HP, Hadjiiski LM, Helvie MA, Richter CD, Cha KH (2018) Evolutionary pruning of transfer learned deep convolutional neural network for breast cancer diagnosis in digital breast tomosynthesis. Phys Med Biol 63:095005PubMedPubMedCentralCrossRefGoogle Scholar
  35. 35.
    Mendel K, Li H, Sheth D, Giger M (2018) Transfer learning from convolutional neural networks for computer-aided diagnosis: a comparison of digital breast Tomosynthesis and full-field digital mammography. Acad Radiol. PubMedCrossRefGoogle Scholar
  36. 36.
    Samala RK, Chan H, Hadjiiski L, Helvie MA, Richter CD, Cha KH (2019) Breast cancer diagnosis in digital breast tomosynthesis: effects of training sample size on multi-stage transfer learning using deep neural nets. IEEE Trans Med Imaging 38:686–696PubMedCrossRefGoogle Scholar
  37. 37.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: arXiv e-prints. Available via Accessed 10 Apr 2015
  38. 38.
    Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2014) Learning spatiotemporal features with 3D convolutional networks. In: arXiv e-prints. Available via Accessed 7 Oct 2015
  39. 39.
    Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. In: arXiv e-prints. Available via Accessed 13 Dec 2017
  40. 40.
    Fitzpatrick JM, Sonka M (2000) Handbook of medical imaging: volume 2. Medical image processing and analysis. SPIE, Bellingham, WashingtonGoogle Scholar
  41. 41.
    Seeram E (2010) Digital radiography: an introduction, 1st edn. Delmar Learning, Clifton Park, New YorkGoogle Scholar
  42. 42.
    Gonzalez RC, Woods RE (2017) Digital image processing, 4th edn. Pearson, HobokenGoogle Scholar
  43. 43.
    Wu T, Moore RH, Rafferty EA, Kopans DB (2004) A comparison of reconstruction algorithms for breast tomosynthesis. Med Phys 31:2636–2647PubMedCrossRefGoogle Scholar
  44. 44.
    Reiser I, Bian J, Nishikawa RM, Sidky EY, Pan X (2009) Comparison of reconstruction algorithms for digital breast tomosynthesis. In: arXiv e-prints. Available via Accessed 01 Aug 2009
  45. 45.
    D’Orsi CJ, Sickles EA, Mendelson EB, Morris EA (2013) ACR BI-RADS® atlas: breast imaging reporting and data system, 5th edn. American College of Radiology, RestonGoogle Scholar
  46. 46.
    Lehman CD, Arao RF, Sprague BL et al (2016) National Performance Benchmarks for modern screening digital mammography: update from the breast Cancer surveillance consortium. Radiology 283:49–58PubMedPubMedCentralCrossRefGoogle Scholar
  47. 47.
    Sprague BL, Arao RF, Miglioretti DL et al (2017) National Performance Benchmarks for modern diagnostic digital mammography: update from the breast Cancer surveillance consortium. Radiology 283:59–69PubMedPubMedCentralCrossRefGoogle Scholar
  48. 48.
    Seo BK, Pisano ED, Kuzmiak CM et al (2006) The positive predictive value for diagnosis of breast Cancer: full-field digital mammography versus film-screen mammography in the diagnostic mammographic population. Acad Radiol 13:1229–1235PubMedCrossRefGoogle Scholar
  49. 49.
    Liberman L, Abramson AF, Squires FB, Glassman JR, Morris EA, Dershaw DD (1998) The breast imaging reporting and data system: positive predictive value of mammographic features and final assessment categories. AJR Am J Roentgenol 171:35–40PubMedCrossRefGoogle Scholar
  50. 50.
    Zou XN (2017) Epidemic trend, screening, and early detection and treatment of cancer in Chinese population. Cancer Biol Med 14:50–59PubMedPubMedCentralCrossRefGoogle Scholar
  51. 51.
    Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK (2018) Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med 15:e1002683PubMedPubMedCentralCrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  1. 1.School of Biomedical EngineeringSouthern Medical UniversityGuangzhouChina
  2. 2.Department of RadiologyNanfang Hospital, Southern Medical UniversityGuangzhouChina

Personalised recommendations