News & Views | Published:

MACHINE LEARNING

AI for medical imaging goes deep

An artificial intelligence (AI) using a deep-learning approach can classify retinal images from optical coherence tomography for early diagnosis of retinal diseases and has the potential to be used in other image-based medical diagnoses.

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

References

  1. 1.

    LeCun, Y., Bengio, Y. & Hinton, G. Nature 521, 436–444 (2015).

  2. 2.

    Ting, D. S. W. et al. J. Am. Med. Assoc. 318, 2211–2223 (2017).

  3. 3.

    Kermany, D. S. et al. Cell 172, 1122–1131 (2018).

  4. 4.

    Burlina, P. M. et al. JAMA Ophthalmol 135, 1170–1176 (2017).

  5. 5.

    Lakhani, P. & Sundaram, B. Radiology 284, 574–582 (2017).

  6. 6.

    Ting, D. S. W., Yi, P. H. & Hui, F. Radiology 286, 729–731 (2018).

  7. 7.

    Esteva, A. et al. Nature 542, 115–118 (2017).

  8. 8.

    Poplin, R. et al. Nat. Biomed. Eng 2, 158–164 (2018).

  9. 9.

    Chew, E. Y. & Schachat, A. P. Ophthalmology 122, 2155–2156 (2015).

  10. 10.

    Ting, D. S. W. & Wong, T. Y. Lancet 389, 2165–2166 (2017).

  11. 11.

    Shen, D., Wu, G. & Suk, H. I. Annu. Rev. Biomed. Eng. 19, 221–248 (2017).

  12. 12.

    Yi, P. H., Hui, F. & Ting, D. S. J. Am. Coll. Radiol. https://doi.org/10.1016/j.jacr.2017.12.037 (2018).

Download references

Author information

Correspondence to Daniel S. W. Ting.

Ethics declarations

Competing interests

D.S.W.T. and T.Y.W. are co-inventors of a patent on a deep learning system in detection of retinal diseases. N.M.B. and P.B. are co-inventors of a patent on a deep learning system in detection of age-related macular degeneration.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Further reading

Fig. 1: Transfer learning can be applied to classify retinal optical coherence tomography images for early diagnosis of retinal diseases.