1
|
Campanioni S, Veiga C, Prieto-González JM, González-Nóvoa JA, Busto L, Martinez C, Alberte-Woodward M, García de Soto J, Pouso-Diz J, Fernández Ceballos MDLÁ, Agis-Balboa RC. Explainable machine learning on baseline MRI predicts multiple sclerosis trajectory descriptors. PLoS One 2024; 19:e0306999. [PMID: 39012871 PMCID: PMC11251627 DOI: 10.1371/journal.pone.0306999] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Accepted: 06/26/2024] [Indexed: 07/18/2024] Open
Abstract
Multiple sclerosis (MS) is a multifaceted neurological condition characterized by challenges in timely diagnosis and personalized patient management. The application of Artificial Intelligence (AI) to MS holds promises for early detection, accurate diagnosis, and predictive modeling. The objectives of this study are: 1) to propose new MS trajectory descriptors that could be employed in Machine Learning (ML) regressors and classifiers to predict patient evolution; 2) to explore the contribution of ML models in discerning MS trajectory descriptors using only baseline Magnetic Resonance Imaging (MRI) studies. This study involved 446 MS patients who had a baseline MRI, at least two measurements of Expanded Disability Status Scale (EDSS), and a 1-year follow-up. Patients were divided into two groups: 1) for model development and 2) for evaluation. Three descriptors: β1, β2, and EDSS(t), were related to baseline MRI parameters using regression and classification XGBoost models. Shapley Additive Explanations (SHAP) analysis enhanced model transparency by identifying influential features. The results of this study demonstrate the potential of AI in predicting MS progression using the proposed patient trajectories and baseline MRI scans, outperforming classic Multiple Linear Regression (MLR) methods. In conclusion, MS trajectory descriptors are crucial; incorporating AI analysis into MRI assessments presents promising opportunities to advance predictive capabilities. SHAP analysis enhances model interpretation, revealing feature importance for clinical decisions.
Collapse
Affiliation(s)
- Silvia Campanioni
- Galicia Sur Health Research Institute (IIS Galicia Sur), Cardiovascular Research Group, Vigo, Spain
| | - César Veiga
- Galicia Sur Health Research Institute (IIS Galicia Sur), Cardiovascular Research Group, Vigo, Spain
| | - José María Prieto-González
- Health Research Institute of Santiago de Compostela (IDIS), Translational Research in Neurological Diseases Group, Santiago University Hospital Complex, SERGAS-USC, Santiago de Compostela, Spain
- Neuro Epigenetics Lab, Health Research Institute of Santiago de Compostela (IDIS), Santiago University Hospital Complex, Santiago de Compostela, Spain
- Neurology Service, Santiago University Hospital Complex, Santiago de Compostela, Spain
| | - José A. González-Nóvoa
- Galicia Sur Health Research Institute (IIS Galicia Sur), Cardiovascular Research Group, Vigo, Spain
| | - Laura Busto
- Galicia Sur Health Research Institute (IIS Galicia Sur), Cardiovascular Research Group, Vigo, Spain
| | - Carlos Martinez
- Galicia Sur Health Research Institute (IIS Galicia Sur), Cardiovascular Research Group, Vigo, Spain
| | - Miguel Alberte-Woodward
- Health Research Institute of Santiago de Compostela (IDIS), Translational Research in Neurological Diseases Group, Santiago University Hospital Complex, SERGAS-USC, Santiago de Compostela, Spain
- Neuro Epigenetics Lab, Health Research Institute of Santiago de Compostela (IDIS), Santiago University Hospital Complex, Santiago de Compostela, Spain
- Neurology Service, Santiago University Hospital Complex, Santiago de Compostela, Spain
| | - Jesús García de Soto
- Health Research Institute of Santiago de Compostela (IDIS), Translational Research in Neurological Diseases Group, Santiago University Hospital Complex, SERGAS-USC, Santiago de Compostela, Spain
- Neuro Epigenetics Lab, Health Research Institute of Santiago de Compostela (IDIS), Santiago University Hospital Complex, Santiago de Compostela, Spain
- Neurology Service, Santiago University Hospital Complex, Santiago de Compostela, Spain
| | - Jessica Pouso-Diz
- Health Research Institute of Santiago de Compostela (IDIS), Translational Research in Neurological Diseases Group, Santiago University Hospital Complex, SERGAS-USC, Santiago de Compostela, Spain
- Neuro Epigenetics Lab, Health Research Institute of Santiago de Compostela (IDIS), Santiago University Hospital Complex, Santiago de Compostela, Spain
- Neurology Service, Santiago University Hospital Complex, Santiago de Compostela, Spain
| | - María de los Ángeles Fernández Ceballos
- Health Research Institute of Santiago de Compostela (IDIS), Translational Research in Neurological Diseases Group, Santiago University Hospital Complex, SERGAS-USC, Santiago de Compostela, Spain
- Neuro Epigenetics Lab, Health Research Institute of Santiago de Compostela (IDIS), Santiago University Hospital Complex, Santiago de Compostela, Spain
- Neurology Service, Santiago University Hospital Complex, Santiago de Compostela, Spain
| | - Roberto Carlos Agis-Balboa
- Health Research Institute of Santiago de Compostela (IDIS), Translational Research in Neurological Diseases Group, Santiago University Hospital Complex, SERGAS-USC, Santiago de Compostela, Spain
- Neuro Epigenetics Lab, Health Research Institute of Santiago de Compostela (IDIS), Santiago University Hospital Complex, Santiago de Compostela, Spain
- Neurology Service, Santiago University Hospital Complex, Santiago de Compostela, Spain
| |
Collapse
|
2
|
Biddle G, Beck RT, Raslan O, Ebinu J, Jenner Z, Hamer J, Hacein-Bey L, Apperson M, Ivanovic V. Autoimmune diseases of the spine and spinal cord. Neuroradiol J 2024; 37:285-303. [PMID: 37394950 PMCID: PMC11138326 DOI: 10.1177/19714009231187340] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/04/2023] Open
Abstract
Magnetic resonance imaging (MRI) and clinicopathological tools have led to the identification of a wide spectrum of autoimmune entities that involve the spine. A clearer understanding of the unique imaging features of these disorders, along with their clinical presentations, will prove invaluable to clinicians and potentially limit the need for more invasive procedures such as tissue biopsies. Here, we review various autoimmune diseases affecting the spine and highlight salient imaging features that distinguish them radiologically from other disease entities.
Collapse
Affiliation(s)
- Garrick Biddle
- Radiology Department, University of California Davis School of Medicine, Sacramento, CA, USA
| | - Ryan T Beck
- Neuroradiology, Radiology Department, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Osama Raslan
- Radiology Department, University of California Davis School of Medicine, Sacramento, CA, USA
| | - Julius Ebinu
- Neurosurgery Department, University of California Davis School of Medicine, Sacramento, CA, USA
| | - Zach Jenner
- Radiology Department, University of California Davis School of Medicine, Sacramento, CA, USA
| | - John Hamer
- Neuroradiology, Radiology Department, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Lotfi Hacein-Bey
- Radiology Department, University of California Davis School of Medicine, Sacramento, CA, USA
| | - Michelle Apperson
- Neurology Department, University of California Davis School of Medicine, Sacramento, CA, USA
| | - Vladimir Ivanovic
- Neuroradiology, Radiology Department, Medical College of Wisconsin, Milwaukee, WI, USA
| |
Collapse
|
3
|
Rathmann E, Hemkemeier P, Raths S, Grothe M, Mankertz F, Hosten N, Flessa S. Changes in MRI Workflow of Multiple Sclerosis after Introduction of an AI-Software: A Qualitative Study. Healthcare (Basel) 2024; 12:978. [PMID: 38786390 PMCID: PMC11121325 DOI: 10.3390/healthcare12100978] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2024] [Revised: 04/30/2024] [Accepted: 05/08/2024] [Indexed: 05/25/2024] Open
Abstract
The purpose of this study was to explore the effects of the integration of machine learning into daily radiological diagnostics, using the example of the machine learning software mdbrain® (Mediaire GmbH, Germany) in the diagnostic MRI workflow of patients with multiple sclerosis at the University Medicine Greifswald. The data were assessed through expert interviews, a comparison of analysis times with and without the machine learning software, as well as a process analysis of MRI workflows. Our results indicate a reduction in the screen-reading workload, improved decision-making regarding contrast administration, an optimized workflow, reduced examination times, and facilitated report communication with colleagues and patients. Our results call for a broader and quantitative analysis.
Collapse
Affiliation(s)
- Eiko Rathmann
- Institute of Radiology and Neuroradiology, University Medicine Greifswald, 17475 Greifswald, Germany or (N.H.)
| | - Pia Hemkemeier
- Department of Business Administration and Health Care Management, Faculty of Law and Economics, University of Greifswald, 17489 Greifswald, Germany (S.F.)
| | - Susan Raths
- Department of Business Administration and Health Care Management, Faculty of Law and Economics, University of Greifswald, 17489 Greifswald, Germany (S.F.)
| | - Matthias Grothe
- Department of Neurology, University Medicine Greifswald, 17475 Greifswald, Germany;
| | - Fiona Mankertz
- Institute of Radiology and Neuroradiology, University Medicine Greifswald, 17475 Greifswald, Germany or (N.H.)
| | - Norbert Hosten
- Institute of Radiology and Neuroradiology, University Medicine Greifswald, 17475 Greifswald, Germany or (N.H.)
| | - Steffen Flessa
- Department of Business Administration and Health Care Management, Faculty of Law and Economics, University of Greifswald, 17489 Greifswald, Germany (S.F.)
| |
Collapse
|
4
|
Naggar A, Laasri K, Kabila B, Izi Z, Allali N, Haddad SE, Chat L. Myelin insults differentials on MRI in children: In the light of an ADEM case. Radiol Case Rep 2024; 19:408-413. [PMID: 38033671 PMCID: PMC10681876 DOI: 10.1016/j.radcr.2023.08.107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2023] [Revised: 08/22/2023] [Accepted: 08/24/2023] [Indexed: 12/02/2023] Open
Abstract
Acute disseminated encephalomyelitis (ADEM) is an acute and rapidly progressive auto-immune demyelinating disorder in the central nervous system. It is a rare disease but is more frequently observed in the pediatric population. We report a case of a monophasic postvaccination ADEM, which presented with paraparesis associated with fever. It showed a favorable evolution under corticosteroids, without recurrence after 3 years of follow-up. The diagnosis was established due to the postvaccination context and the MRI abnormalities characteristics. This case prompted a general discussion about the etiologies of myelin insults in children, especially demyelinating disorders, by shedding the light on their MRI features.
Collapse
Affiliation(s)
- Amine Naggar
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| | - Khadija Laasri
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| | - Badr Kabila
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| | - Zineb Izi
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| | - Nazik Allali
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| | - Siham El Haddad
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| | - Latifa Chat
- Pediatric Radiology Department, Pediatric Teaching Hospital, Mohammed V University, Rabat, Morocco
| |
Collapse
|
5
|
Weidauer S, Hattingen E, Arendt CT. Cervical myelitis: a practical approach to its differential diagnosis on MR imaging. ROFO-FORTSCHR RONTG 2023; 195:1081-1096. [PMID: 37479218 DOI: 10.1055/a-2114-1350] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/23/2023]
Abstract
BACKGROUND Differential diagnosis of non-compressive cervical myelopathy encompasses a broad spectrum of inflammatory, infectious, vascular, neoplastic, neurodegenerative, and metabolic etiologies. Although the speed of symptom onset and clinical course seem to be specific for certain neurological diseases, lesion pattern on MR imaging is a key player to confirm diagnostic considerations. METHODS The differentiation between acute complete transverse myelitis and acute partial transverse myelitis makes it possible to distinguish between certain entities, with the latter often being the onset of multiple sclerosis. Typical medullary MRI lesion patterns include a) longitudinal extensive transverse myelitis, b) short-range ovoid and peripheral lesions, c) polio-like appearance with involvement of the anterior horns, and d) granulomatous nodular enhancement prototypes. RESULTS AND CONCLUSION Cerebrospinal fluid analysis, blood culture tests, and autoimmune antibody testing are crucial for the correct interpretation of imaging findings. The combination of neuroradiological features and neurological and laboratory findings including cerebrospinal fluid analysis improves diagnostic accuracy. KEY POINTS · The differentiation of medullary lesion patterns, i. e., longitudinal extensive transverse, short ovoid and peripheral, polio-like, and granulomatous nodular, facilitates the diagnosis of myelitis.. · Discrimination of acute complete and acute partial transverse myelitis makes it possible to categorize different entities, with the latter frequently being the overture of multiple sclerosis (MS).. · Neuromyelitis optica spectrum disorders (NMOSD) may start as short transverse myelitis and should not be mistaken for MS.. · The combination of imaging features and neurological and laboratory findings including cerebrospinal fluid analysis improves diagnostic accuracy.. · Additional brain imaging is mandatory in suspected demyelinating, systemic autoimmune, infectious, paraneoplastic, and metabolic diseases..
Collapse
Affiliation(s)
- Stefan Weidauer
- Institute for Neuroradiology, Goethe University Frankfurt, Frankfurt am Main, Germany
| | - Elke Hattingen
- Institute for Neuroradiology, Goethe University Frankfurt, Frankfurt am Main, Germany
| | | |
Collapse
|
6
|
Magnetic Resonance Imaging of Autoimmune Demyelinating Diseases as a Diagnostic Challenge for Radiologists: Report of Two Cases and Literature Review. Life (Basel) 2022; 12:life12040488. [PMID: 35454978 PMCID: PMC9027326 DOI: 10.3390/life12040488] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Revised: 03/12/2022] [Accepted: 03/25/2022] [Indexed: 11/17/2022] Open
Abstract
The magnetic resonance characteristics of autoimmune demyelinating diseases are complex and represent a challenge for the radiologist. In this study we presented two different cases of detected autoimmune demyelinating diseases: one case of acute disseminated encephalomyelitis and one case of neuromyelitis optica, respectively. Expected and unexpected findings of magnetic resonance imaging examination for autoimmune demyelinating diseases were reported in order to provide a valuable approach for diagnosis. In particular, we highlight, review and discuss the presence of several uncommon imaging findings which could lead to a misinterpretation. The integration of magnetic resonance imaging findings with clinical and laboratory data is necessary to provide a valuable diagnosis.
Collapse
|
7
|
Ramezani M, Ryan F, Sahraian MA, Simani L. The impact of brain lesions on sexual dysfunction in patients with multiple sclerosis: A systematic review of magnetic resonance imaging studies. Mult Scler Relat Disord 2022; 57:103336. [PMID: 35158464 DOI: 10.1016/j.msard.2021.103336] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2021] [Revised: 09/19/2021] [Accepted: 10/14/2021] [Indexed: 10/19/2022]
Abstract
BACKGROUND Sexual dysfunction is common but underestimated clinical symptom in MS patients. A growing body of evidence has been suggested the link between brain lesions and sexual dysfunction (SD) in patients with multiple sclerosis (MS). However, the clinical research investigating this relationship have shown inconsistent results. Here, we aimed to systematically review the magnetic resonance imaging (MRI) studies evaluating the association between the brain lesions and SD in MS patients. METHODS This study was provided according to the recommendations of the preferred reporting items for systematic reviews and meta-analyses statement. A comprehensive systematic search of online databases was performed to find eligible studies up to December 2020. The quality of studies was methodologically assessed using Newcastle-Ottawa Scale score. RESULTS We identified eight articles regarding MS brain lesions and SD through the search strategy. Seven studies showed significant associations between SD and brain lesions. Three studies investigated the brain stem, two studies the insular and occipital region, one study the frontal lobe, prefrontal cortex, and temporal lobe and one study the parietal area. CONCLUSION The results of this systematic review showed that lesions in different brain areas are correlated with SD in MS patients. Plaques in the occipital and hippocampus areas, as well as left insula appear to be related to dysfunction of sexual arousability or lubrication/erection in MS patients. Orgasmic dysfunction in MS patients may be associated with brain lesions in pons, left temporal periventricular, and right occipital areas.
Collapse
Affiliation(s)
- Mahtab Ramezani
- Brain Mapping Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Fari Ryan
- Centre for Research in Neuroscience, The Research Institute of the McGill University Health Center, 1650 Cedar Ave., Montreal, Quebec, Canada
| | - Mohammad Ali Sahraian
- Multiple Sclerosis Research Center, Neuroscience Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Leila Simani
- Skull Base Research Center, Loghman Hakim Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
8
|
Corrêa DG, Hygino da Cruz LC. Reply to the letter to the editor: "impact of SARS-CoV-2 vaccines on the nervous system". Clin Imaging 2021; 82:5-6. [PMID: 34763264 PMCID: PMC8563500 DOI: 10.1016/j.clinimag.2021.10.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2021] [Accepted: 10/29/2021] [Indexed: 11/17/2022]
Affiliation(s)
- Diogo Goulart Corrêa
- Department of Radiology, Clínica de Diagnóstico por Imagem (CDPI), Avenida das Américas, 4666, 302A, 303, 307, 325, 326, Barra da Tijuca, Rio de Janeiro, RJ 2640-102, Brazil; Department of Radiology, Federal Fluminense University, Rua Marquês de Paraná, 303, Centro, Niterói, RJ 24070-035, Brazil.
| | - Luiz Celso Hygino da Cruz
- Department of Radiology, Clínica de Diagnóstico por Imagem (CDPI), Avenida das Américas, 4666, 302A, 303, 307, 325, 326, Barra da Tijuca, Rio de Janeiro, RJ 2640-102, Brazil
| |
Collapse
|