Improving the Robustness of Deep Learning Models in Predicting Hematoma Expansion from Admission Head CT.
Journal:
AJNR. American journal of neuroradiology
Published Date:
Jun 12, 2025
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
Keywords
No keywords available for this article.