1
|
Collorone S, Coll L, Lorenzi M, Lladó X, Sastre-Garriga J, Tintoré M, Montalban X, Rovira À, Pareto D, Tur C. Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis. Mult Scler 2024; 30:767-784. [PMID: 38738527 DOI: 10.1177/13524585241249422] [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: 05/14/2024]
Abstract
Artificial intelligence (AI) is the branch of science aiming at creating algorithms able to carry out tasks that typically require human intelligence. In medicine, there has been a tremendous increase in AI applications thanks to increasingly powerful computers and the emergence of big data repositories. Multiple sclerosis (MS) is a chronic autoimmune condition affecting the central nervous system with a complex pathogenesis, a challenging diagnostic process strongly relying on magnetic resonance imaging (MRI) and a high and largely unexplained variability across patients. Therefore, AI applications in MS have the great potential of helping us better support the diagnosis, find markers for prognosis to eventually design more powerful randomised clinical trials and improve patient management in clinical practice and eventually understand the mechanisms of the disease. This topical review aims to summarise the recent advances in AI applied to MRI data in MS to illustrate its achievements, limitations and future directions.
Collapse
Affiliation(s)
- Sara Collorone
- NMR Unit, Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Llucia Coll
- Multiple Sclerosis Centre of Catalonia (Cemcat), Department of Neurology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Marco Lorenzi
- Epione Research Project, Inria Sophia Antipolis, Université Côte d'Azur, Nice, France
| | - Xavier Lladó
- Research Institute of Computer Vision and Robotics, University of Girona, Girona, Spain
| | - Jaume Sastre-Garriga
- Multiple Sclerosis Centre of Catalonia (Cemcat), Department of Neurology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Mar Tintoré
- Multiple Sclerosis Centre of Catalonia (Cemcat), Department of Neurology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Xavier Montalban
- Multiple Sclerosis Centre of Catalonia (Cemcat), Department of Neurology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Àlex Rovira
- Section of Neuroradiology, Department of Radiology (IDI), Vall d'Hebron University Hospital, Barcelona, Spain
- Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Deborah Pareto
- Section of Neuroradiology, Department of Radiology (IDI), Vall d'Hebron University Hospital, Barcelona, Spain
- Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Carmen Tur
- NMR Unit, Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, University College London, London, UK
- Multiple Sclerosis Centre of Catalonia (Cemcat), Department of Neurology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain
| |
Collapse
|
2
|
Barnett M, Wang D, Beadnall H, Bischof A, Brunacci D, Butzkueven H, Brown JWL, Cabezas M, Das T, Dugal T, Guilfoyle D, Klistorner A, Krieger S, Kyle K, Ly L, Masters L, Shieh A, Tang Z, van der Walt A, Ward K, Wiendl H, Zhan G, Zivadinov R, Barnett Y, Wang C. A real-world clinical validation for AI-based MRI monitoring in multiple sclerosis. NPJ Digit Med 2023; 6:196. [PMID: 37857813 PMCID: PMC10587188 DOI: 10.1038/s41746-023-00940-6] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Accepted: 09/29/2023] [Indexed: 10/21/2023] Open
Abstract
Modern management of MS targets No Evidence of Disease Activity (NEDA): no clinical relapses, no magnetic resonance imaging (MRI) disease activity and no disability worsening. While MRI is the principal tool available to neurologists for monitoring clinically silent MS disease activity and, where appropriate, escalating treatment, standard radiology reports are qualitative and may be insensitive to the development of new or enlarging lesions. Existing quantitative neuroimaging tools lack adequate clinical validation. In 397 multi-center MRI scan pairs acquired in routine practice, we demonstrate superior case-level sensitivity of a clinically integrated AI-based tool over standard radiology reports (93.3% vs 58.3%), relative to a consensus ground truth, with minimal loss of specificity. We also demonstrate equivalence of the AI-tool with a core clinical trial imaging lab for lesion activity and quantitative brain volumetric measures, including percentage brain volume loss (PBVC), an accepted biomarker of neurodegeneration in MS (mean PBVC -0.32% vs -0.36%, respectively), whereas even severe atrophy (>0.8% loss) was not appreciated in radiology reports. Finally, the AI-tool additionally embeds a clinically meaningful, experiential comparator that returns a relevant MS patient centile for lesion burden, revealing, in our cohort, inconsistencies in qualitative descriptors used in radiology reports. AI-based image quantitation enhances the accuracy of, and value-adds to, qualitative radiology reporting. Scaled deployment of these tools will open a path to precision management for patients with MS.
Collapse
Affiliation(s)
- Michael Barnett
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
- Department of Neurology, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Dongang Wang
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Heidi Beadnall
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
- Department of Neurology, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Antje Bischof
- Department of Neurology, University Hospital of Muenster, Muenster, Germany
| | - David Brunacci
- Department of Radiology, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Helmut Butzkueven
- Department of Neurology, The Alfred Hospital, Melbourne, VIC, Australia
- Department of Neuroscience, Central Clinical School, Monash University, Melbourne, VIC, Australia
| | - J William L Brown
- Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK
| | - Mariano Cabezas
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Tilak Das
- Department of Radiology, University of Cambridge, Cambridge, UK
| | - Tej Dugal
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Synergy Radiology, Sydney, NSW, Australia
| | - Daniel Guilfoyle
- Department of Neurology, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Alexander Klistorner
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
- Save Sight Institute, University of Sydney, Sydney, NSW, Australia
| | - Stephen Krieger
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Kain Kyle
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Linda Ly
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
| | | | - Andy Shieh
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
| | - Zihao Tang
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Anneke van der Walt
- Department of Radiology, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
- Department of Neurology, The Alfred Hospital, Melbourne, VIC, Australia
| | - Kayla Ward
- Department of Neurology, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Heinz Wiendl
- Department of Neurology, University Hospital of Muenster, Muenster, Germany
| | - Geng Zhan
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | | | - Yael Barnett
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia
- Department of Radiology, St Vincent's Hospital, Sydney, NSW, Australia
| | - Chenyu Wang
- Sydney Neuroimaging Analysis Centre, Sydney, NSW, Australia.
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia.
| |
Collapse
|
3
|
Abstract
PURPOSE OF REVIEW Increasingly, therapeutic strategy in multiple sclerosis (MS) is informed by imaging and laboratory biomarkers, in addition to traditional clinical factors. Here, we review aspects of monitoring the efficacy and risks of disease-modifying therapy (DMT) with both conventional and emerging MRI and laboratory measures. RECENT FINDINGS The adoption of consensus-driven, stable MRI acquisition protocols and artificial intelligence-based, quantitative image analysis is heralding an era of precision monitoring of DMT efficacy. New MRI measures of compartmentalized inflammation, neuro-degeneration and repair complement traditional metrics but require validation before use in individual patients. Laboratory markers of brain cellular injury, such as neurofilament light, are robust outcomes in DMT efficacy trials; their use in clinical practice is being refined. DMT-specific laboratory monitoring for safety is critical and may include lymphocytes, immunoglobulins, autoimmunity surveillance, John Cunningham virus serology and COVID-19 vaccination seroresponse. SUMMARY A biomarker-enhanced monitoring strategy has immediate clinical application, with growing evidence of long-term reductions in disability accrual when both clinically symptomatic and asymptomatic inflammatory activity is fully suppressed; and amelioration of the risks associated with therapy. Emerging MRI and blood-based measures will also become important tools for monitoring agents that target the innate immune system and promote neuro-repair.
Collapse
|