Deep learning based ischemic lesion markers on non-contrast head CT compared to CTP and DWI

Authors

Abstract

BackgroundQuantification of ischemic brain tissue on non-contrast CT (NCCT) in acute ischemic stroke is challenging in the acute setting. PurposeTo compare the spatial overlap and imaging marker agreement of acute ischemic regions of interest (ROIs) using deep-learning NCCT (DLNCCT) versus manual NCCT, CTP, and DWI-based ischemic segmentations. MethodsWe trained a deep learning model to segment ischemic ROIs using manual lesion annotations on admission NCCTs (DLNCCT). DLNCCT ischemic ROIs were compared with manual NCCT delineation, CTP (rCBF<30%/38%), and DWI within 5 hours after the NCCT or after recanalization in four external test sets. Spatial overlap was measured using the Dice Similarity Coefficient (DSC; mean{+/-}SD). For each ROI, we derived: average density (HU); modified net water uptake (mNWU in %); total volume (mL); and hypodense (<26HU) volume (mL), and assessed agreement via Bland-Altman (mean difference [95%CI]) and concordance correlation coefficient (CCC) analysis. Results218 training (n=104/89/25 male/female/unknown, mean age 68{+/-}14 years) and 762 test cases (n=243/206/313 male/female/unknown, mean age 70{+/-}15 years) were used. Spatial overlap was 0.30{+/-}0.30 between DLNCCT and manual segmentation, 0.22{+/-}0.25 between DLNCCT and DWI, 0.10{+/-}0.19/0.14{+/-}0.21 between DLNCCT and CTP (rCBF<30%/<38%), and 0.15{+/-}0.22/0.21{+/-}0.24 between CTP (rCBF<30%/<38%) and DWI. DLNCCT vs. DWI mean differences of ischemic ROI derived imaging markers were -1HU (95%CI:-7;6) for average density (CCC:0.71), 4.9% (95%CI:-7.0;16.8) for mNWU (CCC:0.35), -16mL (95%CI:-108;76) for total volume (CCC:0.57), and -4mL (95%CI:-31;23) for hypodense lesion volume (CCC: 0.75). ConclusionSpatial overlap and agreement of imaging markers between DLNCCT and DWI ischemic ROIs were comparable to CTP and DWI. Summary StatementIschemic injury on NCCT is identified and quantified by a deep-learning model with accuracy similar to CTP and DWI in stroke patients with a large vessel occlusion. Key results- Deep-learning models can segment ischemic brain tissue on NCCT. - Ischemic regions identified by our model demonstrate comparable overlap with ischemic core segmentation on CTP (Dice: 0.21{+/-}0.24) and DWI (Dice: 0.22{+/-}0.25). - Deep learning NCCT showed high agreement with follow-up DWI in determining the hypodense (<26 HU) lesion volume (mean difference -4mL [95%CI:-31;23], CCC: 0.75).

Tags

Topics