Skip to main page content
U.S. flag

An official website of the United States government

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Sep;24(9):1342-1350.
doi: 10.1038/s41591-018-0107-6. Epub 2018 Aug 13.

Clinically applicable deep learning for diagnosis and referral in retinal disease

Jeffrey De Fauw  1 , Joseph R Ledsam  1 , Bernardino Romera-Paredes  1 , Stanislav Nikolov  1 , Nenad Tomasev  1 , Sam Blackwell  1 , Harry Askham  1 , Xavier Glorot  1 , Brendan O'Donoghue  1 , Daniel Visentin  1 , George van den Driessche  1 , Balaji Lakshminarayanan  1 , Clemens Meyer  1 , Faith Mackinder  1 , Simon Bouton  1 , Kareem Ayoub  1 , Reena Chopra  2 , Dominic King  1 , Alan Karthikesalingam  1 , Cían O Hughes  1   3 , Rosalind Raine  3 , Julian Hughes  2 , Dawn A Sim  2 , Catherine Egan  2 , Adnan Tufail  2 , Hugh Montgomery  3 , Demis Hassabis  1 , Geraint Rees  3 , Trevor Back  1 , Peng T Khaw  2 , Mustafa Suleyman  1 , Julien Cornebise  1   3 , Pearse A Keane  4 , Olaf Ronneberger  5
Affiliations

Clinically applicable deep learning for diagnosis and referral in retinal disease

Jeffrey De Fauw et al. Nat Med. 2018 Sep.

Abstract

The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.

PubMed Disclaimer

Comment in

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

Publication types