End-to-End Deep Learning Approach for Perfusion Data: A Proof-of-Concept Study to Classify Core Volume in Stroke CT
Authors:
- Andreas MittermeierAMAndreas Mittermeier
- Paul ReidlerPRPaul Reidler
- Matthias P. FabritiusMFMatthias P. Fabritius
- Balthasar SchachtnerBSBalthasar Schachtner
- Philipp WespPWPhilipp Wesp
- Birgit Ertl-WagnerBEBirgit Ertl-Wagner
- Olaf DietrichODOlaf Dietrich
- Jens RickeJRJens Ricke
- Lars KellertLKLars Kellert
- Steffen TiedtSTSteffen Tiedt
- Wolfgang G. KunzWolfgang G. Kunz
- Michael IngrischMIMichael Ingrisch
Open Access
- 5 May 2022
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 12 (5) , 1142
Abstract
(1) Background: CT perfusion (CTP) is used to quantify cerebral hypoperfusion in acute ischemic stroke. Conventional attenuation curve analysis is not standardized and might require input from expert users, hampering clinical application. This study aims to bypass conventional tracer-kinetic analysis with an end-to-end deep learning model to directly categorize patients by stroke core volume from raw, slice-reduced CTP data. (2) Methods: In this retrospective analysis, we included patients with acute ischemic stroke due to proximal occlusion of the anterior circulation who underwent CTP imaging. A novel convolutional neural network was implemented to extract spatial and temporal features from time-resolved imaging data. In a classification task, the network categorized patients into small or large core. In ten-fold cross-validation, the network was repeatedly trained, evaluated, and tested, using the area under the receiver operating characteristic curve (ROC-AUC). A final model was created in an ensemble approach and independently validated on an external dataset. (3) Results: 217 patients were included in the training cohort and 23 patients in the independent test cohort. Median core volume was 32.4 mL and was used as threshold value for the binary classification task. Model performance yielded a mean (SD) ROC-AUC of 0.72 (0.10) for the test folds. External independent validation resulted in an ensembled mean ROC-AUC of 0.61. (4) Conclusions: In this proof-of-concept study, the proposed end-to-end deep learning approach bypasses conventional perfusion analysis and allows to predict dichotomized infarction core volume solely from slice-reduced CTP images without underlying tracer kinetic assumptions. Further studies can easily extend to additional clinically relevant endpoints.Keywords
Funding Information
- the German Research Foundation (DFG) within the Research Training Group GRK 2274
This publication has 31 references indexed in Scilit:
- The Virtual Skeleton Database: An Open Access Repository for Biomedical Research and CollaborationJournal of Medical Internet Research, 2013
- Perfusion CT in Acute Stroke: A Comprehensive Analysis of Infarct and PenumbraRadiology, 2013
- Tracer-kinetic modeling of dynamic contrast-enhanced MRI and CT: a primerJournal of Pharmacokinetics and Pharmacodynamics, 2013
- Rapid identification of a major diffusion/perfusion mismatch in distal internal carotid artery or middle cerebral artery ischemic strokeBMC Neurology, 2012
- Imaging of Stroke: Part 1, Perfusion CT???Overview of Imaging Technique, Interpretation Pearls, and Common PitfallsAmerican Journal of Roentgenology, 2012
- Deconvolution-Based CT and MR Brain Perfusion Measurement: Theoretical Model Revisited and Practical Implementation DetailsInternational Journal of Biomedical Imaging, 2011
- Imaging of acute strokeNature Reviews Neurology, 2010
- Acute Ischemic StrokeNew England Journal of Medicine, 2007
- Pixel-by-pixel deconvolution of bolus-tracking data: optimization and implementationPhysics in Medicine & Biology, 2006
- Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapyThe Lancet, 2000