Clinically applicable deep learning for diagnosis and referral in retinal disease

J. De Fauw, J. Ledsam, B. Romera-Paredes, S. Nikolov, N. Tomasev, S. Blackwell, H. Askham, X. Glorot, B. O’Donoghue, D. Visentin, G. van den Driessche, B. Lakshminarayanan, C. Meyer, F. Mackinder, S. Bouton, K. Ayoub, R. Chopra, D. King, A. Karthikesalingam, C. Hughes, R. Raine, J. Hughes, D. Sim, C. Egan, A. Tufail, H. Montgomery, D. Hassabis, G. Rees, T. Back, P. Khaw, M. Suleyman, J. Cornebise, P. Keane, Olaf Ronneberger
Nature Medicine, 24(9): 1342--1350, 2018
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.
Paper Publisher's link Downloads

Images and movies


BibTex reference

  author       = "J. De  Fauw and J. R. Ledsam and B. Romera-Paredes and S. Nikolov and N. Tomasev and S. Blackwell and H. Askham and X. Glorot and B. O’Donoghue and D. Visentin and G. van den  Driessche and B. Lakshminarayanan and C. Meyer and F. Mackinder and S. Bouton and K. Ayoub and R. Chopra and D. King and A. Karthikesalingam and C. O. Hughes and R. Raine and J. Hughes and D. A. Sim and C. Egan and A. Tufail and H. Montgomery and D. Hassabis and G. Rees and T. Back and P. T. Khaw and M. Suleyman and J. Cornebise and P. A. Keane and O. Ronneberger",
  title        = "Clinically applicable deep learning for diagnosis and referral in retinal disease",
  journal      = "Nature Medicine",
  number       = "9",
  volume       = "24",
  pages        = "1342--1350",
  month        = " ",
  year         = "2018",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2018/Ron18"

Other publications in the database