UniToBrain dataset: a Brain Perfusion Dataset

TL;DR

The UniToBrain dataset is the first open-source collection of brain perfusion CT data, enabling improved ischemic stroke diagnosis through deep learning models that match ground truth maps and potentially reduce radiation exposure.

Contribution

This paper introduces the UniToBrain dataset and a novel neural network algorithm for brain perfusion analysis, advancing open data availability and AI-based diagnostic tools.

Findings

Neural network models accurately match ground truth perfusion maps.

The approach could reduce the number of CT maps needed, lowering radiation doses.

Open-source dataset facilitates further research in brain perfusion imaging.

Abstract

The CT perfusion (CTP) is a medical exam for measuring the passage of a bolus of contrast solution through the brain on a pixel-by-pixel basis. The objective is to draw "perfusion maps" (namely cerebral blood volume, cerebral blood flow and time to peak) very rapidly for ischemic lesions, and to be able to distinguish between core and penumubra regions. A precise and quick diagnosis, in a context of ischemic stroke, can determine the fate of the brain tissues and guide the intervention and treatment in emergency conditions. In this work we present UniToBrain dataset, the very first open-source dataset for CTP. It comprises a cohort of more than a hundred of patients, and it is accompanied by patients metadata and ground truth maps obtained with state-of-the-art algorithms. We also propose a novel neural networks-based algorithm, using the European library ECVL and EDDL for the image processing and developing deep learning models respectively. The results obtained by the neural network models match the ground truth and open the road towards potential sub-sampling of the required number of CT maps, which impose heavy radiation doses to the patients.