Abstract
Introduction: Final infarct volume (FIV) is a commonly used imaging endpoint in stroke trials. The aim of this study was to investigate the potential of an automated masking pipeline (Brain Intensity AbNormality Classification Algorithm - BIANCA) on detecting ischemic stroke lesions of follow-up imaging on patients with acute ischemic stroke. Methods: Patients were retrospectively selected from a prospectively acquired mechanical thrombectomy (MT) database from January to July 2019, and were included if they had a follow-up magnetic resonance imaging DWI within 72h from procedure available. Masks were generated on B1000 imaging by clinical research stroke personnel and then compared with volumes delineated by a fully automated supervised method for lesion detection, based on a k-nearest neighbor (k-NN) algorithm. Results: Seventy patients were included. Human FIV measurements mean was comparable with BIANCA [67.7±73.2 vs 71.8±67 (p<0.05)]. Dice similarity index showed to be 0.710 whilst the ICC was 0.960 (p<0.05). Conclusion: The automated masking pipeline measurement showed to behighlysimilar to a standardized protocol of FIV estimation at a busy neuroendovascular center and could be used in trials with large numbers of patients.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.