"skipMainNavigation"
Search
Quick Search in Journals
Quick Search anywhere
Advanced Search
Radiology
Menu
Previous
Next
Original Research

Radiomic versus Convolutional Neural Networks Analysis for Classification of Contrast-enhancing Lesions at Multiparametric Breast MRI

Published Online:Nov 13 2018https://doi.org/10.1148/radiol.2018181352

Abstract

Convolutional neural networks were superior to radiomic analysis for classification of enhancing lesions. Although both approaches were inferior to radiologists’ performance, convolutional neural networks have the potential for further improvement with more training data whereas radiomic analysis does not.

Purpose

To compare the diagnostic performance of radiomic analysis (RA) and a convolutional neural network (CNN) to radiologists for classification of contrast agent–enhancing lesions as benign or malignant at multiparametric breast MRI.

Materials and Methods

Between August 2011 and August 2015, 447 patients with 1294 enhancing lesions (787 malignant, 507 benign; median size, 15 mm ± 20) were evaluated. Lesions were manually segmented by one breast radiologist. RA was performed by using L1 regularization and principal component analysis. CNN used a deep residual neural network with 34 layers. All algorithms were also retrained on half the number of lesions (n = 647). Machine interpretations were compared with prospective interpretations by three breast radiologists. Standard of reference was histologic analysis or follow-up. Areas under the receiver operating curve (AUCs) were used to compare diagnostic performance.

Results

CNN trained on the full cohort was superior to training on the half-size cohort (AUC, 0.88 vs 0.83, respectively; P = .01), but there was no difference for RA and L1 regularization (AUC, 0.81 vs 0.80, respectively; P = .76) or RA and principal component analysis (AUC, 0.78 vs 0.78, respectively; P = .93). By using the full cohort, CNN performance (AUC, 0.88; 95% confidence interval: 0.86, 0.89) was better than RA and L1 regularization (AUC, 0.81; 95% confidence interval: 0.79, 0.83; P < .001) and RA and principal component analysis (AUC, 0.78; 95% confidence interval: 0.76, 0.80; P < .001). However, CNN was inferior to breast radiologist interpretation (AUC, 0.98; 95% confidence interval: 0.96, 0.99; P < .001).

Conclusion

A convolutional neural network was superior to radiomic analysis for classification of enhancing lesions as benign or malignant at multiparametric breast MRI. Both approaches were inferior to radiologists’ performance; however, more training data will further improve performance of convolutional neural network, but not that of radiomics algorithms.

© RSNA, 2018

Online supplemental material is available for this article.

References

  • 1. Sardanelli F, Boetes C, Borisch B, et al. Magnetic resonance imaging of the breast: recommendations from the EUSOMA working group. Eur J Cancer 2010;46(8):1296–1316.
    Medline Google Scholar
  • 2. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology 2016;278(2):563–577.
    Google Scholar
  • 3. Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 2014;5(1):4006.
    Medline Google Scholar
  • 4. Li H, Zhu Y, Burnside ES, et al. MR imaging radiomics signatures for predicting the risk of breast cancer recurrence as given by research versions of MammaPrint, Oncotype DX, and PAM50 gene assays. Radiology 2016;281(2):382–391.
    Google Scholar
  • 5. Kooi T, Litjens G, van Ginneken B, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 2017;35:303–312.
    Medline Google Scholar
  • 6. Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A. Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 2017;52(7):434–440.
    Medline Google Scholar
  • 7. Bickelhaupt S, Paech D, Kickingereder P, et al. Prediction of malignancy by a radiomic signature from contrast agent-free diffusion MRI in suspicious breast lesions found on screening mammography. J Magn Reson Imaging 2017;46(2):604–616.
    Medline Google Scholar
  • 8. Kuhl CK, Strobel K, Bieling H, Leutner C, Schild HH, Schrading S. Supplemental breast MR imaging screening of women with average risk of breast cancer. Radiology 2017;283(2):361–370.
    Google Scholar
  • 9. Oliphant TE. Python for scientific computing. Comput Sci Eng 2007;9(3):10–20.
    Google Scholar
  • 10. Tustison NJ, Avants BB, Cook PA, et al. N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 2010;29(6):1310–1320.
    Medline Google Scholar
  • 11. van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017;77(21):e104–e107.
    Medline Google Scholar
  • 12. Haarburger C, Langenberg P, Truhn D, et al. Transfer learning for breast cancer malignancy classification based on dynamic contrast-enhanced MR images. In: Maier A, Deserno T, Handels H, Maier-Hein K, Palm C, Tolxdorff T, eds. Bildverarbeitung für die Medizin 2018. Berlin, Germany: Springer, 2018; 216–221.
    Google Scholar
  • 13. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, June 27–30, 2016. Piscataway, NJ: Institute of Electrical and Electronics Engineers, 2016; 770–778.
    Google Scholar
  • 14. Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge. Int J Comput Vis 2015;115(3):211–252.
    Google Scholar
  • 15. Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982;143(1):29–36.
    Google Scholar
  • 16. Litjens G, Sánchez CI, Timofeeva N, et al. Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Sci Rep 2016;6(1):26286.
    Medline Google Scholar
  • 17. Goeman JJ, Solari A. Multiple hypothesis testing in genomics. Stat Med 2014;33(11):1946–1978.
    Medline Google Scholar
  • 18. Leach MO, Boggis CR, Dixon AK, et al. Screening with magnetic resonance imaging and mammography of a UK population at high familial risk of breast cancer: a prospective multicentre cohort study (MARIBS). Lancet 2005;365(9473):1769–1778 [Published correction appears in Lancet 2005;365(9474):1848.] https://doi.org/10.1016/S0140-6736(05)66481-1.
    Medline Google Scholar
  • 19. Kriege M, Brekelmans CT, Boetes C, et al. Efficacy of MRI and mammography for breast-cancer screening in women with a familial or genetic predisposition. N Engl J Med 2004;351(5):427–437.
    Medline Google Scholar
  • 20. Warner E, Plewes DB, Shumak RS, et al. Comparison of breast magnetic resonance imaging, mammography, and ultrasound for surveillance of women at high risk for hereditary breast cancer. J Clin Oncol 2001;19(15):3524–3531.
    Medline Google Scholar
  • 21. Kuhl C, Weigel S, Schrading S, et al. Prospective multicenter cohort study to refine management recommendations for women at elevated familial risk of breast cancer: the EVA trial. J Clin Oncol 2010;28(9):1450–1457.
    Medline Google Scholar
  • 22. Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: NIPS’14: Proceedings of the 27th International Conference on Neural Information Processing Systems, Volume 2, Montreal, Canada, December 8–13, 2014. Cambridge, Mass: MIT Press, 2014; 2672–2680.
    Google Scholar
  • 23. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542(7639):115–118.
    Medline Google Scholar

Article History

Received: June 9 2018
Revision requested: July 26 2018
Revision received: Sept 25 2018
Accepted: Sept 26 2018
Published online: Nov 13 2018
Published in print: Feb 2019