Critical evaluation of deep neural networks for wrist fracture detection.

Journal: Scientific reports
Published Date:

Abstract

Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection-DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set-average precision of 0.99 (0.99-0.99) versus 0.64 (0.46-0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98-0.99) versus 0.84 (0.72-0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems.

Authors

  • Abu Mohammed Raisuddin
    University of Oulu, Oulu, Finland. abu.raisuddin@oulu.fi.
  • Elias Vaattovaara
    University of Oulu, Oulu, Finland.
  • Mika Nevalainen
    University of Oulu, Oulu, Finland.
  • Marko Nikki
    Oulu University Hospital, Oulu, Finland.
  • Elina Järvenpää
    Oulu University Hospital, Oulu, Finland.
  • Kaisa Makkonen
    Oulu University Hospital, Oulu, Finland.
  • Pekka Pinola
    University of Oulu, Oulu, Finland.
  • Tuula Palsio
    University of Oulu, Oulu, Finland.
  • Arttu Niemensivu
    University of Oulu, Oulu, Finland.
  • Osmo Tervonen
  • Aleksei Tiulpin
    Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland. aleksei.tiulpin@oulu.fi.