Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning
Standard
Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning. / Winder, Anthony J; Wilms, Matthias; Amador, Kimberly; Flottmann, Fabian; Fiehler, Jens; Forkert, Nils D.
In: FRONT NEUROSCI-SWITZ, Vol. 16, 1009654, 2022.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Predicting the tissue outcome of acute ischemic stroke from acute 4D computed tomography perfusion imaging using temporal features and deep learning
AU - Winder, Anthony J
AU - Wilms, Matthias
AU - Amador, Kimberly
AU - Flottmann, Fabian
AU - Fiehler, Jens
AU - Forkert, Nils D
N1 - Copyright © 2022 Winder, Wilms, Amador, Flottmann, Fiehler and Forkert.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
U2 - 10.3389/fnins.2022.1009654
DO - 10.3389/fnins.2022.1009654
M3 - SCORING: Journal article
C2 - 36408399
VL - 16
JO - FRONT NEUROSCI-SWITZ
JF - FRONT NEUROSCI-SWITZ
SN - 1662-453X
M1 - 1009654
ER -