Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning

Anthony J Winder; Matthias Wilms; Kimberly Amador; Fabian Flottmann; Jens Fiehler; Nils D Forkert

doi:10.3389/fnins.2022.1009654

Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning

Front Neurosci. 2022 Nov 4:16:1009654. doi: 10.3389/fnins.2022.1009654. eCollection 2022.

Authors

Anthony J Winder^{1

2}, Matthias Wilms^{3

4

5}, Kimberly Amador^{1

2}, Fabian Flottmann⁶, Jens Fiehler⁶, Nils D Forkert^{1

2

5

7}

Affiliations

¹ Department of Radiology, University of Calgary, Calgary, AB, Canada.
² Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada.
³ Department of Paediatrics, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
⁴ Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
⁵ Alberta Children's Hospital Research Institute, University of Calgary, Calgary, AB, Canada.
⁶ Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
⁷ Department of Clinical Neurosciences, University of Calgary, Calgary, AB, Canada.

Abstract

Predicting follow-up lesions from baseline CT perfusion (CTP) datasets in acute ischemic stroke patients is important for clinical decision making. Deep convolutional networks (DCNs) are assumed to be the current state-of-the-art for this task. However, many DCN classifiers have not been validated against the methods currently used in research (random decision forests, RDF) and clinical routine (Tmax thresholding). Specialized DCNs have even been designed to extract complex temporal features directly from spatiotemporal CTP data instead of using standard perfusion parameter maps. However, the benefits of applying deep learning to source or deconvolved CTP data compared to perfusion parameter maps have not been formally investigated so far. In this work, a modular UNet-based DCN is proposed that separates temporal feature extraction from tissue outcome prediction, allowing for both model validation using perfusion parameter maps as well as end-to-end learning from spatiotemporal CTP data. 145 retrospective datasets comprising baseline CTP imaging, perfusion parameter maps, and follow-up non-contrast CT with manual lesion segmentations were assembled from acute ischemic stroke patients treated with intravenous thrombolysis alone (IV; n = 43) or intra-arterial mechanical thrombectomy (IA; n = 102) with or without combined IV. Using the perfusion parameter maps as input, the proposed DCN (mean Dice: 0.287) outperformed the RDF (0.262) and simple Tmax-thresholding (0.249). The performance of the proposed DCN was approximately equal using features optimized from the deconvolved residual curves (0.286) compared to perfusion parameter maps (0.287), while using features optimized from the source concentration-time curves (0.296) provided the best tissue outcome predictions.

Keywords: brain ischemia; deep learning; ischemic stroke; perfusion CT; precision medicine; prediction; stroke.