# Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning

## TL;DR

This paper introduces a deep learning model that predicts final infarct volume directly from native CT perfusion images and metadata, bypassing traditional deconvolution methods, to aid stroke treatment planning.

## Contribution

It presents a novel deconvolution-free, data-driven approach using deep neural networks for infarct prediction from native CTP data and metadata.

## Key findings

- Effective prediction of final infarct volume demonstrated on multicenter data.
- Using native CTP measurements improves prediction accuracy.
- Metadata such as treatment parameters enhances model performance.

## Abstract

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.