Improving the Robustness of Deep Learning Models in Predicting Hematoma Expansion from Admission Head CT.

Journal: AJNR. American journal of neuroradiology
Published Date:

Abstract

BACKGROUND AND PURPOSE: Robustness against input data perturbations is essential for deploying deep learning models in clinical practice. Adversarial attacks involve subtle, voxel-level manipulations of scans to increase deep learning models' prediction errors. Testing deep learning model performance on examples of adversarial images provides a measure of robustness, and including adversarial images in the training set can improve the model's robustness. In this study, we examined adversarial training and input modifications to improve the robustness of deep learning models in predicting hematoma expansion (HE) from admission head CTs of patients with acute intracerebral hemorrhage (ICH).

Authors

  • Anh T Tran
    Department of Radiology, Columbia University Irving Medical Center, NewYork-Presbyterian Hospital, Columbia University, New York, NY 10032, USA.
  • Gaby Abou Karam
    Department of Radiology and Biomedical Imaging (A.T.T., G.A.K., D.Z., A.M.), Yale School of Medicine, New Haven, Connecticut.
  • Dorin Zeevi
    From the Department of Radiology (A.T.T., D.Z., S.P.), NewYork-Presbyterian/Columbia University Irving Medical Center, Columbia University, New York, New York.
  • Adnan I Qureshi
    Zeenat Qureshi Stroke Institute, St. Cloud, Minnesota, USA.
  • Ajay Malhotra
    Department of Radiology and Biomedical Imaging, Yale University School of Medicine, Box 208042, Tompkins East 2, 333 Cedar St, New Haven, CT, 06520-8042, USA. ajay.malhotra@yale.edu.
  • Shahram Majidi
    Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA.
  • Santosh B Murthy
    Department of Neurology (S.B.M.), Weill Cornell Medical College, Cornell University, New York.
  • Soojin Park
    Department of Neurology, Department of Biomedical Informatics, Columbia University, New York, NY, USA.
  • Despina Kontos
    Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA 19104, United States.
  • Guido J Falcone
    Department of Neurology (G.J.F., E.P.K., R.B.N., K.R., J.A., K.N.S.), Yale School of Medicine, New Haven, CT.
  • Kevin N Sheth
    Department of Neurology (G.J.F., E.P.K., R.B.N., K.R., J.A., K.N.S.), Yale School of Medicine, New Haven, CT.
  • Seyedmehdi Payabvash
    Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA.

Keywords

No keywords available for this article.