Artificial intelligence for classification of temporal lobe epilepsy with ROI-level MRI data: A worldwide ENIGMA-Epilepsy study.

Journal: NeuroImage. Clinical

Volume: 31

Issue: 

Year of Publication: 2021

Affiliated Institutions:  Department of Neurology, Medical University of South Carolina, Charleston, SC, USA. Electronic address: gleichge@musc.edu. Department of Psychiatry, University of North Carolina at Chapel Hill, NC, USA; Department of Computer Science, University of North Carolina at Chapel Hill, NC, USA. Neurology Department, Yale University School of Medicine, New Haven, CT, USA; Department of Molecular and Cellular Therapeutics, The Royal College of Surgeons in Ireland, Dublin, Ireland. Department of Neurology and Neuroimaging Laboratory, University of Campinas - UNICAMP, Campinas, SP, Brazil. Magnetic Resonance Image Core Facility, Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Universitat de Barcelona, Barcelona, Spain; Department of Radiology of Center of Image Diagnosis (CDIC), Hospital Clinic de Barcelona, Barcelona, Spain. Department of Diagnostic and Interventional Neuroradiology, University Hospital Tübingen, Tübingen, Germany. Neuroimaging of Epilepsy Laboratory, Montreal Neurological Institute, McGill University, Montreal, QC, Canada. McConnell Brain Imaging Center, Montreal Neurological Institute, McGill University, Montreal, QC, Canada. Psychiatry and Psychology, Mayo Clinic, Jacksonville, FL, USA. Neuroscience Research Center, Department of Medical and Surgical Sciences, University "Magna Græcia" of Catanzaro, Catanzaro, Italy. Instituto de Neurobiología, Universidad Nacional Autónoma de México, Querétaro, Mexico. Department of Radiology, Royal Melbourne Hospital, University of Melbourne, Melbourne, VIC, Australia. Department of Neurology, Langone School of Medicine, New York University, New York, NY, USA. Trinity College Dublin, School of Medicine, Dublin, Ireland; FutureNeuro SFI Research Centre for Rare and Chronic Neurological Diseases, Dublin, Ireland. Functional Imaging Unit, Department of Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Greifswald, Germany. Department of Clinical and Experimental Epilepsy, UCL Queen Square Institute of Neurology, London, UK. University Medicine Göttingen, Clinical Neurophysiology, Göttingen, Germany. Neuroscience Research Center, Department of Medical and Surgical Sciences, University "Magna Græcia" of Catanzaro, Catanzaro, Italy; Institute of Neurology, University "Magna Græcia" of Catanzaro, Catanzaro, Italy. Department of Radiology, BC Children's Hospital, University of British Columbia, Vancouver, BC, Canada. Neuroscience Department, University of Florence, Florence, Italy. Center for Multimodal Imaging and Genetics, University of California, San Diego, La Jolla, CA, USA. Kuopio University Hospital, Member of EpiCARE ERN, Kuopio, Finland; Institute of Clinical Medicine, Neurology, University of Eastern Finland, Kuopio, Finland. Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool, UK; The Walton Centre NHS Foundation Trust, Liverpool, UK. Department of Psychiatry, University of Maryland School of Medicine, Baltimore, MD, USA. Department of Diagnostic and Interventional Neuroradiology, University Hospital Tübingen, Tübingen, Germany; Department of Clinical Neurophysiology, University Hospital Göttingen, Goettingen, Germany; Department of Neurology and Epileptology, Hertie Institute for Clinical Brain Research, University Hospital Tübingen, Tübingen, Germany. University Medicine Göttingen, Clinical Neurophysiology, Göttingen, Germany; Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool, UK. Institute for Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Greifswald, Germany; Institute for Diagnostic and Interventional Radiology, Pediatric and Neuroradiology, University Medical Centre Rostock, Rostock, Germany. Pediatric Neurology, Neurogenetics and Neurobiology Unit and Laboratories, Children's Hospital A. Meyer-University of Florence, Florence, Italy; Functional and Epilepsy Neurosurgery Unit, Neurosurgery Department, Children's Hospital A. Meyer-University of Florence, Florence, Italy. Department of Neurology and Epileptology, Hertie Institute for Clinical Brain Research, University Hospital Tübingen, Tübingen, Germany. 'Mario Serio' Department of Clinical and Experimental Medica Sciences, University of Florence, Florence, Italy. Department of Biomedical, Metabolic, and Neural Sciences, University of Modena and Reggio Emilia, Modena, Italy; Neurology Unit, OCB Hospital, AOU Modena, Modena, Italy. Department of Neuroscience, Monash University, Melbourne, VIC, Australia; The Department of Medicine (The Royal Melbourne Hospital), The University of Melbourne, Parkville, VIC, Australia; Department of Neurology, Alfred Health, Melbourne, VIC, Australia. Magnetic Resonance Image Core Facility, Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Universitat de Barcelona, Barcelona, Spain. Department of Psychiatry, University of California San Diego, La Jolla, CA, USA. Division of Neuroscience, King's College London, London, UK. Instituto de Neurobiología, Universidad Nacional Autónoma de México, Querétaro, Mexico; Montreal Neurological Institute and Hospital, McGill University, Montreal, QC, Canada. Department of Epileptology, University Hospital Bonn, Bonn, Germany. Radiology and Research Administration, Henry Ford Health System, Detroit, MI, USA; School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran. SA MRC Unit on Risk & Resilience in Mental Disorders, Department of Psychiatry & Neuroscience Institute, University of Cape Town, Cape Town, South Africa. IRCCS Istituto 'G. Gaslini', Genova, Italy; Department of Neurosciences, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, University of Genova, Genova, Italy. Department of Neurosciences, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, University of Genova, Genova, Italy; School of Computing, Newcastle University, Newcastle Upon Tyne, UK. Institute of Translational and Clinical Research, Newcastle University, Newcastle Upon Tyne, UK. Department of Neurology, Epilepsy Center, University Medicine Greifswald, Greifswald, Germany. Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK; Neuroradiological Academic Unit, UCL Queen Square Institute of Neurology, University College London, London, UK. Institute of Experimental Epileptology and Cognition Research, University of Bonn, Bonn, Germany. Cognitive Science Department, School of Informatics, Xiamen University, Xiamen, China. Imaging Genetics Center, Mark and Mary Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California, Marina del Rey, CA, USA. UCL Queen Square Institute of Neurology, London, UK; Chalfont Centre for Epilepsy, Bucks, UK. Department of Neurology, Medical University of South Carolina, Charleston, SC, USA.

Abstract summary 

Artificial intelligence has recently gained popularity across different medical fields to aid in the detection of diseases based on pathology samples or medical imaging findings. Brain magnetic resonance imaging (MRI) is a key assessment tool for patients with temporal lobe epilepsy (TLE). The role of machine learning and artificial intelligence to increase detection of brain abnormalities in TLE remains inconclusive. We used support vector machine (SV) and deep learning (DL) models based on region of interest (ROI-based) structural (n = 336) and diffusion (n = 863) brain MRI data from patients with TLE with ("lesional") and without ("non-lesional") radiographic features suggestive of underlying hippocampal sclerosis from the multinational (multi-center) ENIGMA-Epilepsy consortium. Our data showed that models to identify TLE performed better or similar (68-75%) compared to models to lateralize the side of TLE (56-73%, except structural-based) based on diffusion data with the opposite pattern seen for structural data (67-75% to diagnose vs. 83% to lateralize). In other aspects, structural and diffusion-based models showed similar classification accuracies. Our classification models for patients with hippocampal sclerosis were more accurate (68-76%) than models that stratified non-lesional patients (53-62%). Overall, SV and DL models performed similarly with several instances in which SV mildly outperformed DL. We discuss the relative performance of these models with ROI-level data and the implications for future applications of machine learning and artificial intelligence in epilepsy care.

Authors & Co-authors:  Gleichgerrcht Ezequiel E Munsell Brent C BC Alhusaini Saud S Alvim Marina K M MKM Bargalló Núria N Bender Benjamin B Bernasconi Andrea A Bernasconi Neda N Bernhardt Boris B Blackmon Karen K Caligiuri Maria Eugenia ME Cendes Fernando F Concha Luis L Desmond Patricia M PM Devinsky Orrin O Doherty Colin P CP Domin Martin M Duncan John S JS Focke Niels K NK Gambardella Antonio A Gong Bo B Guerrini Renzo R Hatton Sean N SN Kälviäinen Reetta R Keller Simon S SS Kochunov Peter P Kotikalapudi Raviteja R Kreilkamp Barbara A K BAK Labate Angelo A Langner Soenke S Larivière Sara S Lenge Matteo M Lui Elaine E Martin Pascal P Mascalchi Mario M Meletti Stefano S O'Brien Terence J TJ Pardoe Heath R HR Pariente Jose C JC Xian Rao Jun J Richardson Mark P MP Rodríguez-Cruces Raúl R Rüber Theodor T Sinclair Ben B Soltanian-Zadeh Hamid H Stein Dan J DJ Striano Pasquale P Taylor Peter N PN Thomas Rhys H RH Elisabetta Vaudano Anna A Vivash Lucy L von Podewills Felix F Vos Sjoerd B SB Weber Bernd B Yao Yi Y Lin Yasuda Clarissa C Zhang Junsong J Thompson Paul M PM Sisodiya Sanjay M SM McDonald Carrie R CR Bonilha Leonardo L

Study Outcome 

Source Link: Visit source

Statistics
Citations :  Abbasi B., Goldenholz D.M. Machine learning applications in epilepsy. Epilepsia. 2019;60:2037–2047.
Authors :  62
Identifiers
Doi : 102765
SSN : 2213-1582
Study Population
Male,Female
Mesh Terms
Artificial Intelligence
Other Terms
Artificial inteligence;Epilepsy;Machine learning;Temporal lobe epilepsy
Study Design
Cross Sectional Study
Study Approach
Country of Study
Mali
Publication Country
Netherlands