Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography
| Autor: | Alexander Soler, Carlos Crespo, Natalia Pérez de la Ossa, Marc Ribó, Cristina Granes, Xabier Urra, María Hernández-Pérez, Cristian Marti, Carlos Laredo, Paloma Puyalto, Marta Olivé-Gadea, J. Soler, Patricia Cuadras |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Advanced and Specialized Nursing
middle cerebral artery medicine.medical_specialty medicine.diagnostic_test area under the curve business.industry Deep learning deep learning Computed tomography Software thrombectomy medicine.artery Middle cerebral artery medicine Neurology (clinical) Radiology Artificial intelligence Endovascular treatment Cardiology and Cardiovascular Medicine business patient transfer Large vessel occlusion |
| Zdroj: | Stroke r-IGTP. Repositorio Institucional de Producción Científica del Instituto de Investigación Germans Trias i Pujol instname |
| ISSN: | 1524-4628 0039-2499 |
| DOI: | 10.1161/strokeaha.120.030326 |
| Popis: | Background and Purpose: Reliable recognition of large vessel occlusion (LVO) on noncontrast computed tomography (NCCT) may accelerate identification of endovascular treatment candidates. We aim to validate a machine learning algorithm (MethinksLVO) to identify LVO on NCCT. Methods: Patients with suspected acute stroke who underwent NCCT and computed tomography angiography (CTA) were included. Software detection of LVO (MethinksLVO) on NCCT was tested against the CTA readings of 2 experienced radiologists (NR-CTA). We used a deep learning algorithm to identify clot signs on NCCT. The software image output trained a binary classifier to determine LVO on NCCT. We studied software accuracy when adding National Institutes of Health Stroke Scale and time from onset to the model (MethinksLVO+). Results: From 1453 patients, 823 (57%) had LVO by NR-CTA. The area under the curve for the identification of LVO with MethinksLVO was 0.87 (sensitivity: 83%, specificity: 71%, positive predictive value: 79%, negative predictive value: 76%) and improved to 0.91 with MethinksLVO+ (sensitivity: 83%, specificity: 85%, positive predictive value: 88%, negative predictive value: 79%). Conclusions: In patients with suspected acute stroke, MethinksLVO software can rapidly and reliably predict LVO. MethinksLVO could reduce the need to perform CTA, generate alarms, and increase the efficiency of patient transfers in stroke networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|