1
|
Benzakoun J, Deslys MA, Legrand L, Hmeydia G, Turc G, Hassen WB, Charron S, Debacker C, Naggara O, Baron JC, Thirion B, Oppenheim C. Synthetic FLAIR as a Substitute for FLAIR Sequence in Acute Ischemic Stroke. Radiology 2022; 303:153-159. [PMID: 35014901 DOI: 10.1148/radiol.211394] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
Background In acute ischemic stroke (AIS), fluid-attenuated inversion recovery (FLAIR) is used for treatment decisions when onset time is unknown. Synthetic FLAIR could be generated with deep learning from information embedded in diffusion-weighted imaging (DWI) and could replace acquired FLAIR sequence (real FLAIR) and shorten MRI duration. Purpose To compare performance of synthetic and real FLAIR for DWI-FLAIR mismatch estimation and identification of patients presenting within 4.5 hours from symptom onset. Materials and Methods In this retrospective study, all pretreatment and early follow-up (<48 hours after symptom onset) MRI data sets including DWI (b = 0-1000 sec/mm2) and FLAIR sequences obtained in consecutive patients with AIS referred for reperfusion therapies between January 2002 and May 2019 were included. On the training set (80%), a generative adversarial network was trained to produce synthetic FLAIR with DWI as input. On the test set (20%), synthetic FLAIR was computed without real FLAIR knowledge. The DWI-FLAIR mismatch was evaluated on both FLAIR data sets by four independent readers. Interobserver reproducibility and DWI-FLAIR mismatch concordance between synthetic and real FLAIR were evaluated with κ statistics. Sensitivity and specificity for identification of AIS within 4.5 hours were compared in patients with known onset time by using McNemar test. Results The study included 1416 MRI scans (861 patients; median age, 71 years [interquartile range, 57-81 years]; 375 men), yielding 1134 and 282 scans for training and test sets, respectively. Regarding DWI-FLAIR mismatch, interobserver reproducibility was substantial for real and synthetic FLAIR (κ = 0.80 [95% CI: 0.74, 0.87] and 0.80 [95% CI: 0.74, 0.87], respectively). After consensus, concordance between real and synthetic FLAIR was almost perfect (κ = 0.88; 95% CI: 0.82, 0.93). Diagnostic value for identifying AIS within 4.5 hours did not differ between real and synthetic FLAIR (sensitivity: 107 of 131 [82%] vs 111 of 131 [85%], P = .2; specificity: 96 of 104 [92%] vs 96 of 104 [92%], respectively, P > .99). Conclusion Synthetic fluid-attenuated inversion recovery (FLAIR) had diagnostic performances similar to real FLAIR in depicting diffusion-weighted imaging-FLAIR mismatch and in helping to identify early acute ischemic stroke, and it may accelerate MRI protocols. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Carroll and Hurley in this issue.
Collapse
Affiliation(s)
- Joseph Benzakoun
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Marc-Antoine Deslys
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Laurence Legrand
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Ghazi Hmeydia
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Guillaume Turc
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Wagih Ben Hassen
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Sylvain Charron
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Clément Debacker
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Olivier Naggara
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Jean-Claude Baron
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Bertrand Thirion
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| | - Catherine Oppenheim
- From the Departments of Neuroradiology (J.B., L.L., G.H., W.B.H., O.N., C.O.) and Neurology (G.T., J.C.B.), GHU Paris Psychiatrie et Neurosciences, Site Sainte-Anne, 1 rue Cabanis, 75014 Paris, France; INSERM U1266, Paris, France (J.B., M.A.D., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); Université de Paris, FHU Neurovasc, Paris, France (J.B., L.L., G.T., W.B.H., S.C., C.D., O.N., J.C.B., C.O.); and PARIETAL Team, INRIA, Saclay, France (B.T.)
| |
Collapse
|
11
|
Avellaneda-Gómez C, Rodríguez Campello A, Giralt Steinhauer E, Gómez González A, Serra Martínez M, de Ceballos Cerrajería P, Zabalza de Torres A, Cuadrado-Godia E, Ois Santiago A, Jiménez-Conde J, Roquer J. Description of stroke mimics after complete neurovascular assessment. Neurologia 2017; 34:7-13. [PMID: 28169020 DOI: 10.1016/j.nrl.2016.10.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2016] [Revised: 10/10/2016] [Accepted: 10/16/2016] [Indexed: 11/17/2022] Open
Abstract
INTRODUCTION A considerable percentage of events initially diagnosed as ischaemic stroke have non-cerebrovascular causes; these are called stroke mimics (SM). Currently available evidence about these events is heterogeneous and comes from studies with small samples. OBJECTIVE The purpose of our study is to identify conditions that may present as SM, define their epidemiological and clinical characteristics, and determine the percentage of cases of SM treated with intravenous fibrinolysis. METHODS Prospective study including all patients admitted to a tertiary university hospital between June 2005 and April 2015 with a diagnosis of acute stroke. We analysed demographic data, cardiovascular risk factors, time from code stroke activation to admission, stroke severity (NIHSS), final destination after discharge, degree of disability (mRS), and treatment. We compared SM and ischaemic strokes. We ruled out patients with intracranial haemorrhage, subarachnoid haemorrhage, or other causes of SM that may be detected on the baseline CT scan. RESULTS Four hundred four of the 4,570 included patients (8.8%) were found to have SM. Patients with SM were younger (70.3 vs. 74, P<.0001), less likely to exhibit cardiovascular risk factors and atrial fibrillation (13 vs. 34%, P<.0001), scored lower on the NIHSS at baseline (2 vs. 4, P<.0001), and included fewer cases of aphasia (9.4 vs. 19.6%, P<.02) and dysphagia (1.2 vs. 17%, P<.0001) than patients with stroke. SM caused fewer code stroke activations (28 vs. 40%, P<.0001). Patients with SM required shorter hospital stays (4.9 vs. 7.8 days, P<.0001), were less frequently admitted to the stroke unit (47 vs. 60%, P<.0001) and more frequently discharged home (95 vs. 62%, P<.0001), and had better outcomes (mRS scores 0-2; 76 vs. 54%, P<.0001). Intravenous fibrinolysis was administered to 4.7% of these patients. Epileptic seizures were the most frequent cause of SM (26%). CONCLUSIONS In our sample, 8.8% of all diagnoses of ischaemic stroke were SM. These events have different demographic, clinical, and prognostic characteristics; epilepsy is the most common aetiology. Despite receiving specialised emergency care, 19 patients with SM (4.7%) were treated with intravenous fibrinolysis.
Collapse
Affiliation(s)
- C Avellaneda-Gómez
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España
| | - A Rodríguez Campello
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España; Grupo de Investigación Neurovascular, Institut Hospital del Mar d'Investigacions Mèdiques (IMIM), Departament de Medicina, Universitat Autònoma de Barcelona, Barcelona, España.
| | - E Giralt Steinhauer
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España; Grupo de Investigación Neurovascular, Institut Hospital del Mar d'Investigacions Mèdiques (IMIM), Departament de Medicina, Universitat Autònoma de Barcelona, Barcelona, España
| | - A Gómez González
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España
| | - M Serra Martínez
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España
| | | | - A Zabalza de Torres
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España
| | - E Cuadrado-Godia
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España; Grupo de Investigación Neurovascular, Institut Hospital del Mar d'Investigacions Mèdiques (IMIM), Departament de Medicina, Universitat Autònoma de Barcelona, Barcelona, España
| | - A Ois Santiago
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España; Grupo de Investigación Neurovascular, Institut Hospital del Mar d'Investigacions Mèdiques (IMIM), Departament de Medicina, Universitat Autònoma de Barcelona, Barcelona, España
| | - J Jiménez-Conde
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España; Grupo de Investigación Neurovascular, Institut Hospital del Mar d'Investigacions Mèdiques (IMIM), Departament de Medicina, Universitat Autònoma de Barcelona, Barcelona, España
| | - J Roquer
- Unidad de Ictus, Servicio de Neurología, Hospital del Mar, Barcelona, España; Grupo de Investigación Neurovascular, Institut Hospital del Mar d'Investigacions Mèdiques (IMIM), Departament de Medicina, Universitat Autònoma de Barcelona, Barcelona, España
| |
Collapse
|