Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning
This work addresses the problem of stroke diagnosis and treatment simulation for clinicians, offering a data-driven alternative to conventional methods, though it appears incremental as it builds on existing deep learning approaches in medical imaging.
The authors tackled predicting final infarct volume in acute stroke by developing a deep learning model that uses native CT perfusion images and treatment metadata, eliminating the need for deconvolution, and demonstrated improved prediction accuracy on a multicenter dataset.
CT Perfusion (CTP) imaging has gained importance in the diagnosis of acute stroke. Conventional perfusion analysis performs a deconvolution of the measurements and thresholds the perfusion parameters to determine the tissue status. We pursue a data-driven and deconvolution-free approach, where a deep neural network learns to predict the final infarct volume directly from the native CTP images and metadata such as the time parameters and treatment. This would allow clinicians to simulate various treatments and gain insight into predicted tissue status over time. We demonstrate on a multicenter dataset that our approach is able to predict the final infarct and effectively uses the metadata. An ablation study shows that using the native CTP measurements instead of the deconvolved measurements improves the prediction.