Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study

Show full item record



Permalink

http://hdl.handle.net/10138/346055

Citation

Mäkelä , T , Öman , O , Hokkinen , L M I , Wilppu , U , Salli , E , Savolainen , S & Kangasniemi , M 2022 , ' Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study ' , Journal of Digital Imaging , vol. 35 , no. 3 , pp. 551-563 . https://doi.org/10.1007/s10278-022-00611-0

Title: Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study
Author: Mäkelä, Teemu; Öman, Olli; Hokkinen, Lasse M I; Wilppu, Ulla; Salli, Eero; Savolainen, Sauli; Kangasniemi, Marko
Contributor organization: HUS Medical Imaging Center
Department of Diagnostics and Therapeutics
Department of Physics
Helsinki In Vivo Animal Imaging Platform (HAIP)
Sauli Savolainen / Principal Investigator
Clinicum
Date: 2022-06
Language: eng
Number of pages: 13
Belongs to series: Journal of Digital Imaging
ISSN: 0897-1889
DOI: https://doi.org/10.1007/s10278-022-00611-0
URI: http://hdl.handle.net/10138/346055
Abstract: In stroke imaging, CT angiography (CTA) is used for detecting arterial occlusions. These images could also provide information on the extent of ischemia. The study aim was to develop and evaluate a convolutional neural network (CNN)-based algorithm for detecting and segmenting acute ischemic lesions from CTA images of patients with suspected middle cerebral artery stroke. These results were compared to volumes reported by widely used CT perfusion-based RAPID software (IschemaView). A 42-layer-deep CNN was trained on 50 CTA volumes with manually delineated targets. The lower bound for predicted lesion size to reliably discern stroke from false positives was estimated. The severity of false positives and false negatives was reviewed visually to assess the clinical applicability and to further guide the method development. The CNN model corresponded to the manual segmentations with voxel-wise sensitivity 0.54 (95% confidence interval: 0.44-0.63), precision 0.69 (0.60-0.76), and Sorensen-Dice coefficient 0.61 (0.52-0.67). Stroke/nonstroke differentiation accuracy 0.88 (0.81-0.94) was achieved when only considering the predicted lesion size (i.e., regardless of location). By visual estimation, 46% of cases showed some false findings, such as CNN highlighting chronic periventricular white matter changes or beam hardening artifacts, but only in 9% the errors were severe, translating to 0.91 accuracy. The CNN model had a moderately strong correlation to RAPID-reported T-max > 10 s volumes (Pearson's r = 0.76 (0.58-0.86)). The results suggest that detecting anterior circulation ischemic strokes from CTA using a CNN-based algorithm can be feasible when accompanied with physiological knowledge to rule out false positives.
Subject: Computed tomography angiography
Convolutional neural networks
DEEP
Machine learning
Stroke
TIME
3126 Surgery, anesthesiology, intensive care, radiology
114 Physical sciences
Peer reviewed: Yes
Rights: cc_by
Usage restriction: openAccess
Self-archived version: publishedVersion


Files in this item

Total number of downloads: Loading...

Files Size Format View
M_kel_2022_Arti ... cCTAngiographyLesionSe.pdf 2.354Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record