2
|
Negro A, Tortora M, Gemini L, de Falco A, Somma F, d’Agostino V. Neurological manifestations of COVID-19: a retrospective observational study based on 1060 patients with a narrative review. Acta Radiol 2022; 64:1950-1957. [PMID: 36451533 PMCID: PMC9720471 DOI: 10.1177/02841851221138557] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
Abstract
Background In the past two decades, three coronavirus epidemics have been reported. Coronavirus disease 2019 (COVID-19) is caused by a severe acute respiratory syndrome (SARS)-like coronavirus (SARS-CoV-2). In most patients, the disease is characterized by interstitial pneumonia, but features can affect other organs. Purpose To document the radiological features of the patients and to perform a narrative review of the literature. Material and Methods We conducted a retrospective, single-center study on 1060 consecutive hospitalized patients with COVID-19 at our institution. According to the inclusion criteria, we selected patients to be studied in more radiological detail. All images were obtained as per standard of care protocols. We performed a statistic analysis to describe radiological features. We then presented a systematic review of the main and conventional neuroimaging findings in COVID-19. Results Of 1060 patients hospitalized for COVID-19 disease, 15% (159) met the eligibility criteria. Of these, 16 (10%) did not undergo radiological examinations for various reasons, while 143 (90%) were examined. Of these 143 patients, 48 (33.6%) had positive neuroimaging. We found that the most frequent pathology was acute ischemic stroke (n=16, 33.3%). Much less frequent were Guillain–Barre syndrome (n=9, 18.8%), cerebral venous thrombosis (n=7, 14.6%), encephalitis or myelitis (n=6, 12.5%), intracranial hemorrhage and posterior hemorrhagic encephalopathy syndrome (n=4, 8.3%), exacerbation of multiple sclerosis (n=4, 8.3%), and Miller–Fisher syndrome (n=2, 4.2%). Conclusion Our data are coherent with the published literature. Knowledge of these patterns will make clinicians consider COVID-19 infection when unexplained neurological findings are encountered.
Collapse
Affiliation(s)
- Alberto Negro
- Department of Neuroradiology, Ospedale del Mare, Naples, Italy
| | - Mario Tortora
- Department of Advanced Biomedical Sciences, University “Federico II,” Naples, Italy
| | - Laura Gemini
- Department of Advanced Biomedical Sciences, University “Federico II,” Naples, Italy
| | | | - Francesco Somma
- Department of Neuroradiology, Ospedale del Mare, Naples, Italy
| | | |
Collapse
|
4
|
La Rosa F, Wynen M, Al-Louzi O, Beck ES, Huelnhagen T, Maggi P, Thiran JP, Kober T, Shinohara RT, Sati P, Reich DS, Granziera C, Absinta M, Bach Cuadra M. Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: Emerging machine learning techniques and future avenues. Neuroimage Clin 2022; 36:103205. [PMID: 36201950 PMCID: PMC9668629 DOI: 10.1016/j.nicl.2022.103205] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Revised: 09/09/2022] [Accepted: 09/16/2022] [Indexed: 12/14/2022]
Abstract
The current diagnostic criteria for multiple sclerosis (MS) lack specificity, and this may lead to misdiagnosis, which remains an issue in present-day clinical practice. In addition, conventional biomarkers only moderately correlate with MS disease progression. Recently, some MS lesional imaging biomarkers such as cortical lesions (CL), the central vein sign (CVS), and paramagnetic rim lesions (PRL), visible in specialized magnetic resonance imaging (MRI) sequences, have shown higher specificity in differential diagnosis. Moreover, studies have shown that CL and PRL are potential prognostic biomarkers, the former correlating with cognitive impairments and the latter with early disability progression. As machine learning-based methods have achieved extraordinary performance in the assessment of conventional imaging biomarkers, such as white matter lesion segmentation, several automated or semi-automated methods have been proposed as well for CL, PRL, and CVS. In the present review, we first introduce these MS biomarkers and their imaging methods. Subsequently, we describe the corresponding machine learning-based methods that were proposed to tackle these clinical questions, putting them into context with respect to the challenges they are facing, including non-standardized MRI protocols, limited datasets, and moderate inter-rater variability. We conclude by presenting the current limitations that prevent their broader deployment and suggesting future research directions.
Collapse
Key Words
- ms, multiple sclerosis
- mri, magnetic resonance imaging
- dl, deep learning
- ml, machine learning
- cl, cortical lesions
- prl, paramagnetic rim lesions
- cvs, central vein sign
- wml, white matter lesions
- flair, fluid-attenuated inversion recovery
- mprage, magnetization prepared rapid gradient-echo
- gm, gray matter
- wm, white matter
- psir, phase-sensitive inversion recovery
- dir, double inversion recovery
- mp2rage, magnetization-prepared 2 rapid gradient echoes
- sels, slowly evolving/expanding lesions
- cnn, convolutional neural network
- xai, explainable ai
- pv, partial volume
Collapse
Affiliation(s)
- Francesco La Rosa
- Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; CIBM Center for Biomedical Imaging, Switzerland; Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
| | - Maxence Wynen
- CIBM Center for Biomedical Imaging, Switzerland; ICTeam, UCLouvain, Louvain-la-Neuve, Belgium; Louvain Inflammation Imaging Lab (NIL), Institute of Neuroscience (IoNS), UCLouvain, Brussels, Belgium; Radiology Department, Lausanne University and University Hospital, Switzerland
| | - Omar Al-Louzi
- Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA; Department of Neurology, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Erin S Beck
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA
| | - Till Huelnhagen
- Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; Radiology Department, Lausanne University and University Hospital, Switzerland; Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland
| | - Pietro Maggi
- Louvain Inflammation Imaging Lab (NIL), Institute of Neuroscience (IoNS), UCLouvain, Brussels, Belgium; Department of Neurology, Cliniques universitaires Saint-Luc, Université catholique de Louvain, Brussels, Belgium; Department of Neurology, CHUV, Lausanne, Switzerland
| | - Jean-Philippe Thiran
- Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; CIBM Center for Biomedical Imaging, Switzerland; Radiology Department, Lausanne University and University Hospital, Switzerland
| | - Tobias Kober
- Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland; Radiology Department, Lausanne University and University Hospital, Switzerland; Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland
| | - Russell T Shinohara
- Center for Biomedical Image Computing and Analysis (CBICA), Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA; Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania, Philadelphia, PA, USA; Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
| | - Pascal Sati
- Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA; Department of Neurology, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Daniel S Reich
- Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA
| | - Cristina Granziera
- Translational Imaging in Neurology (ThINk) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Switzerland; Neurologic Clinic and Policlinic, MS Center and Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland
| | - Martina Absinta
- IRCCS San Raffaele Hospital and Vita-Salute San Raffaele University, Milan, Italy; Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Meritxell Bach Cuadra
- CIBM Center for Biomedical Imaging, Switzerland; Radiology Department, Lausanne University and University Hospital, Switzerland
| |
Collapse
|