UniTOBrain

Citation Author(s):
Umberto
Gava
Neurosciences Department, University of Turin (Italy)
Federico
D'Agata
Neurosciences Department, University of Turin (Italy)
Edwin
Bennink
Department of Radiology, University Medical Center Utrecht, Utrecht, the Netherlands, Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands
Enzo
Tartaglione
Computer Science Department, University of Turin, Turin (Italy)
Daniele
Perlo
Computer Science Department, University of Turin, Turin (Italy)
Annamaria
Vernone
Neurosciences Department, University of Turin (Italy)
Francesca
Bertolino
Neurosciences Department, University of Turin (Italy)
Eleonora
Ficiarà
Neurosciences Department, University of Turin (Italy)
Alessandro
Cicerale
Neurosciences Department, University of Turin (Italy)
Fabrizio
Pizzagalli
Neurosciences Department, University of Turin (Italy)
Caterina
Guiot
Neurosciences Department, University of Turin (Italy)
Marco
Grangetto
Computer Science Department, University of Turin, Turin (Italy)
Mauro
Bergui
Neurosciences Department, University of Turin (Italy)
Submitted by:
apns apns
Last updated:
Thu, 07/22/2021 - 10:59
DOI:
10.21227/x8ea-vh16
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

The University of Turin (UniTO) released the open-access dataset Stoke collected for the homonymous Use Case 3 in the DeepHealth project (https://deephealth-project.eu/). UniToBrain is a dataset of Computed Tomography (CT) perfusion images (CTP). The dataset includes 258 consecutive patients, a subsample of 100 training subjects and 15 testing subjects was used in a submitted publication for the training and the testing of a Convolutional Neural Network (CNN, see for details: https://arxiv.org/abs/2101.05992, https://paperswithcode.com/paper/neural-network-derived-perfusion-maps-a-model, https://www.medrxiv.org/content/10.1101/2021.01.13.21249757v1). The UniTO team released this dataset publicly.CTP data were retrospectively obtained from the hospital PACS of Città della Salute e della Scienza di Torino (Molinette). CTP acquisition parameters were as follows: Scanner GE, 64 slices, 80 kV, 150 mAs, 44.5 sec duration, 89 volumes (40 mm axial coverage), injection of 40 ml of Iodine contrast agent (300 mg/ml) at 4 ml/s speed.

Along with the dataset, we provide some utility files.

dicomtonpy.py: It converts the dicom files in the dataset to numpy arrays. These are 3D arrays, where CT slices at the same height are piled-up over the temporal acquisition.

dataloader_pytorch.py: Dataloader for the pytorch deep learning framework. It converts the numpy arrays in normalized tensors, which can be provided as input to standard deep learning models.

dataloader_pyeddl.py: Dataloader for the pyeddl deep learning framework. It converts the numpy arrays in normalized tensors, which can be provided as input to standard deep learning models using the european library EDDL. Visit https://github.com/EIDOSlab/UC3-UNITOBrain to have a full companion code where a U-Net model is trained over the dataset.

Instructions: 

Visit https://github.com/EIDOSlab/UC3-UNITOBrain to have a full companion code where a U-Net model is trained over the dataset.