1
|
Romascano D, Rebsamen M, Radojewski P, Blattner T, McKinley R, Wiest R, Rummel C. Cortical thickness and grey-matter volume anomaly detection in individual MRI scans: Comparison of two methods. Neuroimage Clin 2024; 43:103624. [PMID: 38823248 PMCID: PMC11168488 DOI: 10.1016/j.nicl.2024.103624] [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: 02/19/2024] [Revised: 05/21/2024] [Accepted: 05/25/2024] [Indexed: 06/03/2024]
Abstract
Over the past decades, morphometric analysis of brain MRI has contributed substantially to the understanding of healthy brain structure, development and aging as well as to improved characterisation of disease related pathologies. Certified commercial tools based on normative modeling of these metrics are meanwhile available for diagnostic purposes, but they are cost intensive and their clinical evaluation is still in its infancy. Here we have compared the performance of "ScanOMetrics", an open-source research-level tool for detection of statistical anomalies in individual MRI scans, depending on whether it is operated on the output of FreeSurfer or of the deep learning based brain morphometry tool DL + DiReCT. When applied to the public OASIS3 dataset, containing patients with Alzheimer's disease (AD) and healthy controls (HC), cortical thickness anomalies in patient scans were mainly detected in regions that are known as predilection areas of cortical atrophy in AD, regardless of the software used for extraction of the metrics. By contrast, anomaly detections in HCs were up to twenty-fold reduced and spatially unspecific using both DL + DiReCT and FreeSurfer. Progression of the atrophy pattern with clinical dementia rating (CDR) was clearly observable with both methods. DL + DiReCT provided results in less than 25 min, more than 15 times faster than FreeSurfer. This difference in computation time might be relevant when considering application of this or similar methodology as diagnostic decision support for neuroradiologists.
Collapse
Affiliation(s)
- David Romascano
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland; Danish Research Center for Magnetic Resonance, Centre for Functional and Diagnostic Imaging and Research, Copenhagen University Hospital Amager and Hvidovre, Copenhagen, Denmark
| | - Michael Rebsamen
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland
| | - Piotr Radojewski
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland; Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, sitem-insel, Bern, Switzerland
| | - Timo Blattner
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland
| | - Richard McKinley
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland
| | - Roland Wiest
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland; Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, sitem-insel, Bern, Switzerland
| | - Christian Rummel
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, University Hospital Bern, CH-3010 Bern, Switzerland; European Campus Rottal-Inn, Technische Hochschule Deggendorf, Max-Breiherr-Straße 32, D-84347 Pfarrkirchen, Germany.
| |
Collapse
|
2
|
Rebsamen M, Jin BZ, Klail T, De Beukelaer S, Barth R, Rezny-Kasprzak B, Ahmadli U, Vulliemoz S, Seeck M, Schindler K, Wiest R, Radojewski P, Rummel C. Clinical Evaluation of a Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis. Clin Neuroradiol 2023; 33:1045-1053. [PMID: 37358608 PMCID: PMC10654177 DOI: 10.1007/s00062-023-01308-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Accepted: 05/09/2023] [Indexed: 06/27/2023]
Abstract
OBJECTIVE To evaluate the influence of quantitative reports (QReports) on the radiological assessment of hippocampal sclerosis (HS) from MRI of patients with epilepsy in a setting mimicking clinical reality. METHODS The study included 40 patients with epilepsy, among them 20 with structural abnormalities in the mesial temporal lobe (13 with HS). Six raters blinded to the diagnosis assessed the 3T MRI in two rounds, first using MRI only and later with both MRI and the QReport. Results were evaluated using inter-rater agreement (Fleiss' kappa [Formula: see text]) and comparison with a consensus of two radiological experts derived from clinical and imaging data, including 7T MRI. RESULTS For the primary outcome, diagnosis of HS, the mean accuracy of the raters improved from 77.5% with MRI only to 86.3% with the additional QReport (effect size [Formula: see text]). Inter-rater agreement increased from [Formula: see text] to [Formula: see text]. Five of the six raters reached higher accuracies, and all reported higher confidence when using the QReports. CONCLUSION In this pre-use clinical evaluation study, we demonstrated clinical feasibility and usefulness as well as the potential impact of a previously suggested imaging biomarker for radiological assessment of HS.
Collapse
Affiliation(s)
- Michael Rebsamen
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 10, 3010, Bern, Switzerland
- Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland
| | - Baudouin Zongxin Jin
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 10, 3010, Bern, Switzerland
- Sleep-Wake-Epilepsy-Center, Department of Neurology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Tomas Klail
- University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Sophie De Beukelaer
- University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Rike Barth
- Sleep-Wake-Epilepsy-Center, Department of Neurology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Beata Rezny-Kasprzak
- University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Uzeyir Ahmadli
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 10, 3010, Bern, Switzerland
| | - Serge Vulliemoz
- EEG and Epilepsy Unit, Department of Clinical Neurosciences, Geneva University Hospitals and Faculty of Medicine, University of Geneva, Geneva, Switzerland
| | - Margitta Seeck
- EEG and Epilepsy Unit, Department of Clinical Neurosciences, Geneva University Hospitals and Faculty of Medicine, University of Geneva, Geneva, Switzerland
| | - Kaspar Schindler
- Sleep-Wake-Epilepsy-Center, Department of Neurology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Roland Wiest
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 10, 3010, Bern, Switzerland
- Swiss Institute for Translational and Entrepreneurial Medicine, sitem-insel, Bern, Switzerland
| | - Piotr Radojewski
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 10, 3010, Bern, Switzerland.
- Swiss Institute for Translational and Entrepreneurial Medicine, sitem-insel, Bern, Switzerland.
| | - Christian Rummel
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Freiburgstrasse 10, 3010, Bern, Switzerland
| |
Collapse
|
3
|
Bou Assi E, Schindler K, de Bézenac C, Denison T, Desai S, Keller SS, Lemoine É, Rahimi A, Shoaran M, Rummel C. From basic sciences and engineering to epileptology: A translational approach. Epilepsia 2023; 64 Suppl 3:S72-S84. [PMID: 36861368 DOI: 10.1111/epi.17566] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 02/23/2023] [Accepted: 02/28/2023] [Indexed: 03/03/2023]
Abstract
Collaborative efforts between basic scientists, engineers, and clinicians are enabling translational epileptology. In this article, we summarize the recent advances presented at the International Conference for Technology and Analysis of Seizures (ICTALS 2022): (1) novel developments of structural magnetic resonance imaging; (2) latest electroencephalography signal-processing applications; (3) big data for the development of clinical tools; (4) the emerging field of hyperdimensional computing; (5) the new generation of artificial intelligence (AI)-enabled neuroprostheses; and (6) the use of collaborative platforms to facilitate epilepsy research translation. We highlight the promise of AI reported in recent investigations and the need for multicenter data-sharing initiatives.
Collapse
Affiliation(s)
- Elie Bou Assi
- Department of Neuroscience, Université de Montréal, Montréal, Canada
- Centre de Recherche du CHUM (CRCHUM), Montréal, Canada
| | - Kaspar Schindler
- Department of Neurology, Inselspital, Sleep-Wake-Epilepsy-Center, Bern University Hospital, Bern University, Bern, Switzerland
| | - Christophe de Bézenac
- Department of Pharmacology and Therapeutics, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool, UK
- The Walton Centre NHS Foundation Trust, Liverpool, UK
| | - Timothy Denison
- MRC Brain Network Dynamics Unit, University of Oxford, Oxford, UK
- Department of Engineering Science, University of Oxford, Oxford, UK
| | | | - Simon S Keller
- Department of Pharmacology and Therapeutics, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, Liverpool, UK
- The Walton Centre NHS Foundation Trust, Liverpool, UK
| | - Émile Lemoine
- Centre de Recherche du CHUM (CRCHUM), Montréal, Canada
- Institute of Biomedical Engineering, Polytechnique Montréal, Montréal, Canada
| | | | - Mahsa Shoaran
- Institute of Electrical and Micro Engineering, Neuro-X Institute, EPFL, Lausanne, Switzerland
| | - Christian Rummel
- Support Center for Advanced Neuroimaging (SCAN), University Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| |
Collapse
|
4
|
Kiersnowski OC, Winston GP, Caciagli L, Biondetti E, Elbadri M, Buck S, Duncan JS, Thornton JS, Shmueli K, Vos SB. Quantitative susceptibility mapping identifies hippocampal and other subcortical grey matter tissue composition changes in temporal lobe epilepsy. Hum Brain Mapp 2023; 44:5047-5064. [PMID: 37493334 PMCID: PMC10502681 DOI: 10.1002/hbm.26432] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 07/04/2023] [Accepted: 07/07/2023] [Indexed: 07/27/2023] Open
Abstract
Temporal lobe epilepsy (TLE) is associated with widespread brain alterations. Using quantitative susceptibility mapping (QSM) alongside transverse relaxation rate (R 2 * ), we investigated regional brain susceptibility changes in 36 patients with left-sided (LTLE) or right-sided TLE (RTLE) secondary to hippocampal sclerosis, and 27 healthy controls (HC). We compared three susceptibility calculation methods to ensure image quality. Correlations of susceptibility andR 2 * with age of epilepsy onset, frequency of focal-to-bilateral tonic-clonic seizures (FBTCS), and neuropsychological test scores were examined. Weak-harmonic QSM (WH-QSM) successfully reduced noise and removed residual background field artefacts. Significant susceptibility increases were identified in the left putamen in the RTLE group compared to the LTLE group, the right putamen and right thalamus in the RTLE group compared to HC, and a significant susceptibility decrease in the left hippocampus in LTLE versus HC. LTLE patients who underwent epilepsy surgery showed significantly lower left-versus-right hippocampal susceptibility. SignificantR 2 * changes were found between TLE and HC groups in the amygdala, putamen, thalamus, and in the hippocampus. Specifically, decreased R2 * was found in the left and right hippocampus in LTLE and RTLE, respectively, compared to HC. Susceptibility andR 2 * were significantly correlated with cognitive test scores in the hippocampus, globus pallidus, and thalamus. FBTCS frequency correlated positively with ipsilateral thalamic and contralateral putamen susceptibility and withR 2 * in bilateral globi pallidi. Age of onset was correlated with susceptibility in the hippocampus and putamen, and withR 2 * in the caudate. Susceptibility andR 2 * changes observed in TLE groups suggest selective loss of low-myelinated neurons alongside iron redistribution in the hippocampi, predominantly ipsilaterally, indicating QSM's sensitivity to local pathology. Increased susceptibility andR 2 * in the thalamus and putamen suggest increased iron content and reflect disease severity.
Collapse
Affiliation(s)
- Oliver C. Kiersnowski
- Department of Medical Physics and Biomedical EngineeringUniversity College LondonLondonUK
| | - Gavin P. Winston
- Department of Clinical and Experimental EpilepsyUniversity College LondonLondonUK
- Department of Medicine, Division of NeurologyQueen's UniversityKingstonCanada
| | - Lorenzo Caciagli
- Department of Clinical and Experimental EpilepsyUniversity College LondonLondonUK
- Department of BioengineeringUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Emma Biondetti
- Department of Medical Physics and Biomedical EngineeringUniversity College LondonLondonUK
- Department of Neuroscience, Imaging and Clinical SciencesInstitute for Advanced Biomedical Technologies, “D'Annunzio” University of Chieti‐PescaraChietiItaly
| | - Maha Elbadri
- Department of NeurologyQueen Elizabeth HospitalBirminghamUK
| | - Sarah Buck
- Department of Clinical and Experimental EpilepsyUniversity College LondonLondonUK
| | - John S. Duncan
- Department of Clinical and Experimental EpilepsyUniversity College LondonLondonUK
| | - John S. Thornton
- Neuroradiological Academic UnitUCL Queen Square Institute of Neurology, University College LondonLondonUK
| | - Karin Shmueli
- Department of Medical Physics and Biomedical EngineeringUniversity College LondonLondonUK
| | - Sjoerd B. Vos
- Neuroradiological Academic UnitUCL Queen Square Institute of Neurology, University College LondonLondonUK
- Centre for Microscopy, Characterisation, and AnalysisThe University of Western AustraliaNedlandsAustralia
- Centre for Medical Image Computing, Computer Science departmentUniversity College LondonLondonUK
| |
Collapse
|
5
|
Dasgupta D, Finn R, Chari A, Giampiccolo D, de Tisi J, O'Keeffe AG, Miserocchi A, McEvoy AW, Vos SB, Duncan JS. Hippocampal resection in temporal lobe epilepsy: Do we need to resect the tail? Epilepsy Res 2023; 190:107086. [PMID: 36709527 PMCID: PMC10626579 DOI: 10.1016/j.eplepsyres.2023.107086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2022] [Revised: 12/24/2022] [Accepted: 01/09/2023] [Indexed: 01/13/2023]
Abstract
INTRODUCTION Anteromesial temporal lobe resection is the most common surgical technique used to treat drug-resistant mesial temporal lobe epilepsy, particularly when secondary to hippocampal sclerosis. Structural and functional imaging data suggest the importance of sparing the posterior hippocampus for minimising language and memory deficits. Recent work has challenged the view that maximal posterior hippocampal resection improves seizure outcome. This study was designed to assess whether resection of posterior hippocampal atrophy was associated with improved seizure outcome. METHODS Retrospective analysis of a prospective database of all anteromesial temporal lobe resections performed in individuals with hippocampal sclerosis at our epilepsy surgery centre, 2013-2021. Pre- and post-operative MRI were reviewed by 2 neurosurgical fellows to assess whether the atrophic segment, displayed by automated hippocampal morphometry, was resected, and ILAE seizure outcomes were collected at 1 year and last clinical follow-up. Data analysis used univariate and binary logistic regression. RESULTS Sixty consecutive eligible patients were identified of whom 70% were seizure free (ILAE Class 1 & 2) at one year. There was no statistically significant difference in seizure freedom outcomes in patients who had complete resection of atrophic posterior hippocampus or not (Fisher's Exact test statistic 0.69, not significant at p < .05) both at one year, and at last clinical follow-up. In the multivariate analysis only a history of status epilepticus (OR=0.2, 95%CI:0.042-0.955, p = .04) at one year, and pre-operative psychiatric disorder (OR=0.145, 95%CI:0.036-0.588, p = .007) at last clinical follow-up, were associated with a reduced chance of seizure freedom. SIGNIFICANCE Our data suggest that seizure freedom is not associated with whether or not posterior hippocampal atrophy is resected. This challenges the traditional surgical dogma of maximal posterior hippocampal resection in anteromesial temporal lobe resections and is a step further optimising this surgical procedure to maximise seizure freedom and minimise associated language and memory deficits.
Collapse
Affiliation(s)
- Debayan Dasgupta
- Department of Clinical and Experimental Epilepsy, UCL Queen Square Institute of Neurology, University College London, London, UK; Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, Queen Square, London, UK.
| | - Roisin Finn
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, Queen Square, London, UK.
| | - Aswin Chari
- Department of Neurosurgery, Great Ormond Street Hospital, London, UK; Developmental Neuroscience, Great Ormond Street Institute of Child Health, University College London, London, UK.
| | - Davide Giampiccolo
- Department of Clinical and Experimental Epilepsy, UCL Queen Square Institute of Neurology, University College London, London, UK; Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, Queen Square, London, UK; Institute of Neurosciences, Cleveland Clinic London, London, UK.
| | - Jane de Tisi
- Department of Clinical and Experimental Epilepsy, UCL Queen Square Institute of Neurology, University College London, London, UK.
| | - Aidan G O'Keeffe
- School of Mathematical Sciences, University of Nottingham, Nottingham, UK. aidan.o'
| | - Anna Miserocchi
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, Queen Square, London, UK.
| | - Andrew W McEvoy
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, Queen Square, London, UK.
| | - Sjoerd B Vos
- 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; Centre for Microscopy, Characterisation, and Analysis, The University of Western Australia, Nedlands, Australia.
| | - John S Duncan
- Department of Clinical and Experimental Epilepsy, UCL Queen Square Institute of Neurology, University College London, London, UK.
| |
Collapse
|
6
|
Kim D, Lee J, Moon J, Moon T. Interpretable deep learning-based hippocampal sclerosis classification. Epilepsia Open 2022; 7:747-757. [PMID: 36177546 PMCID: PMC9712484 DOI: 10.1002/epi4.12655] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Accepted: 09/26/2022] [Indexed: 12/30/2022] Open
Abstract
OBJECTIVE To evaluate the performance of a deep learning model for hippocampal sclerosis classification on the clinical dataset and suggest plausible visual interpretation for the model prediction. METHODS T2-weighted oblique coronal images of the brain MRI epilepsy protocol performed on patients were used. The training set included 320 participants with 160 no, 100 left and 60 right hippocampal sclerosis, and cross-validation was implemented. The test set consisted of 302 participants with 252 no, 25 left and 25 right hippocampal sclerosis. As the test set was imbalanced, we took an average of the accuracy achieved within each group to measure a balanced accuracy for multiclass and binary classifications. The dataset was composed to include not only healthy participants but also participants with abnormalities besides hippocampal sclerosis in the control group. We visualized the reasons for the model prediction using the layer-wise relevance propagation method. RESULTS When evaluated on the validation of the training set, we achieved multiclass and binary classification accuracy of 87.5% and 88.8% from the voting ensemble of six models. Evaluated on the test sets, we achieved multiclass and binary classification accuracy of 91.5% and 89.76%. The distinctly sparse visual interpretations were provided for each individual participant and group to suggest the contribution of each input voxel to the prediction on the MRI. SIGNIFICANCE The current interpretable deep learning-based model is promising for adapting effectively to clinical settings by utilizing commonly used data, such as MRI, with realistic abnormalities faced by neurologists to support the diagnosis of hippocampal sclerosis with plausible visual interpretation.
Collapse
Affiliation(s)
- Dohyun Kim
- Department of Artificial IntelligenceSungkyunkwan UniversitySuwonSouth Korea
| | - Jungtae Lee
- Application Engineering Team, Memory BusinessSamsung Electronics Co., Ltd.SuwonSouth Korea
| | - Jangsup Moon
- Department of NeurologySeoul National University HospitalSeoulSouth Korea,Department of Genomic MedicineSeoul National University HospitalSeoulSouth Korea
| | - Taesup Moon
- Department of Electrical and Computer EngineeringSeoul National UniversitySeoulSouth Korea,ASRI/INMC/IPAI/AIISSeoul National UniversitySeoulSouth Korea
| |
Collapse
|
7
|
Pemberton HG, Collij LE, Heeman F, Bollack A, Shekari M, Salvadó G, Alves IL, Garcia DV, Battle M, Buckley C, Stephens AW, Bullich S, Garibotto V, Barkhof F, Gispert JD, Farrar G. Quantification of amyloid PET for future clinical use: a state-of-the-art review. Eur J Nucl Med Mol Imaging 2022; 49:3508-3528. [PMID: 35389071 PMCID: PMC9308604 DOI: 10.1007/s00259-022-05784-y] [Citation(s) in RCA: 30] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Accepted: 03/25/2022] [Indexed: 12/15/2022]
Abstract
Amyloid-β (Aβ) pathology is one of the earliest detectable brain changes in Alzheimer's disease (AD) pathogenesis. The overall load and spatial distribution of brain Aβ can be determined in vivo using positron emission tomography (PET), for which three fluorine-18 labelled radiotracers have been approved for clinical use. In clinical practice, trained readers will categorise scans as either Aβ positive or negative, based on visual inspection. Diagnostic decisions are often based on these reads and patient selection for clinical trials is increasingly guided by amyloid status. However, tracer deposition in the grey matter as a function of amyloid load is an inherently continuous process, which is not sufficiently appreciated through binary cut-offs alone. State-of-the-art methods for amyloid PET quantification can generate tracer-independent measures of Aβ burden. Recent research has shown the ability of these quantitative measures to highlight pathological changes at the earliest stages of the AD continuum and generate more sensitive thresholds, as well as improving diagnostic confidence around established binary cut-offs. With the recent FDA approval of aducanumab and more candidate drugs on the horizon, early identification of amyloid burden using quantitative measures is critical for enrolling appropriate subjects to help establish the optimal window for therapeutic intervention and secondary prevention. In addition, quantitative amyloid measurements are used for treatment response monitoring in clinical trials. In clinical settings, large multi-centre studies have shown that amyloid PET results change both diagnosis and patient management and that quantification can accurately predict rates of cognitive decline. Whether these changes in management reflect an improvement in clinical outcomes is yet to be determined and further validation work is required to establish the utility of quantification for supporting treatment endpoint decisions. In this state-of-the-art review, several tools and measures available for amyloid PET quantification are summarised and discussed. Use of these methods is growing both clinically and in the research domain. Concurrently, there is a duty of care to the wider dementia community to increase visibility and understanding of these methods.
Collapse
Affiliation(s)
- Hugh G Pemberton
- GE Healthcare, Amersham, UK.
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK.
- UCL Queen Square Institute of Neurology, University College London, London, UK.
| | - Lyduine E Collij
- Department of Radiology and Nuclear Medicine, Amsterdam Neurocience, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| | - Fiona Heeman
- Department of Radiology and Nuclear Medicine, Amsterdam Neurocience, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| | - Ariane Bollack
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK
| | - Mahnaz Shekari
- Barcelonaβeta Brain Research Center (BBRC), Pasqual Maragall Foundation, Barcelona, Spain
- Universitat Pompeu Fabra, Barcelona, Spain
- IMIM (Hospital del Mar Medical Research Institute), Barcelona, Spain
| | - Gemma Salvadó
- Barcelonaβeta Brain Research Center (BBRC), Pasqual Maragall Foundation, Barcelona, Spain
- Clinical Memory Research Unit, Department of Clinical Sciences, Lund University, Malmö, Sweden
| | - Isadora Lopes Alves
- Department of Radiology and Nuclear Medicine, Amsterdam Neurocience, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
- Brain Research Center, Amsterdam, The Netherlands
| | - David Vallez Garcia
- Department of Radiology and Nuclear Medicine, Amsterdam Neurocience, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| | - Mark Battle
- GE Healthcare, Amersham, UK
- Clinical Memory Research Unit, Department of Clinical Sciences, Lund University, Malmö, Sweden
| | | | | | | | - Valentina Garibotto
- Division of Nuclear Medicine and Molecular Imaging, University Hospitals of Geneva, Geneva, Switzerland
- NIMTLab, Faculty of Medicine, University of Geneva, Geneva, Switzerland
| | - Frederik Barkhof
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK
- UCL Queen Square Institute of Neurology, University College London, London, UK
- Department of Radiology and Nuclear Medicine, Amsterdam Neurocience, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands
| | - Juan Domingo Gispert
- Barcelonaβeta Brain Research Center (BBRC), Pasqual Maragall Foundation, Barcelona, Spain
- Universitat Pompeu Fabra, Barcelona, Spain
- IMIM (Hospital del Mar Medical Research Institute), Barcelona, Spain
- Centro de Investigación Biomédica en Red Bioingeniería, Biomateriales y Nanomedicina, Madrid, Spain
| | | |
Collapse
|
8
|
Rebsamen M, Radojewski P, McKinley R, Reyes M, Wiest R, Rummel C. A Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis Derived From Deep Learning-Based Segmentation of T1w-MRI. Front Neurol 2022; 13:812432. [PMID: 35250818 PMCID: PMC8894898 DOI: 10.3389/fneur.2022.812432] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2021] [Accepted: 01/06/2022] [Indexed: 11/13/2022] Open
Abstract
PurposeHippocampal volumetry is an important biomarker to quantify atrophy in patients with mesial temporal lobe epilepsy. We investigate the sensitivity of automated segmentation methods to support radiological assessments of hippocampal sclerosis (HS). Results from FreeSurfer and FSL-FIRST are contrasted to a deep learning (DL)-based segmentation method.Materials and MethodsWe used T1-weighted MRI scans from 105 patients with epilepsy and 354 healthy controls. FreeSurfer, FSL, and a DL-based method were applied for brain anatomy segmentation. We calculated effect sizes (Cohen's d) between left/right HS and healthy controls based on the asymmetry of hippocampal volumes. Additionally, we derived 14 shape features from the segmentations and determined the most discriminating feature to identify patients with hippocampal sclerosis by a support vector machine (SVM).ResultsDeep learning-based segmentation of the hippocampus was the most sensitive to detecting HS. The effect sizes of the volume asymmetries were larger with the DL-based segmentations (HS left d= −4.2, right = 4.2) than with FreeSurfer (left= −3.1, right = 3.7) and FSL (left= −2.3, right = 2.5). For the classification based on the shape features, the surface-to-volume ratio was identified as the most important feature. Its absolute asymmetry yielded a higher area under the curve (AUC) for the deep learning-based segmentation (AUC = 0.87) than for FreeSurfer (0.85) and FSL (0.78) to dichotomize HS from other epilepsy cases. The robustness estimated from repeated scans was statistically significantly higher with DL than all other methods.ConclusionOur findings suggest that deep learning-based segmentation methods yield a higher sensitivity to quantify hippocampal sclerosis than atlas-based methods and derived shape features are more robust. We propose an increased asymmetry in the surface-to-volume ratio of the hippocampus as an easy-to-interpret quantitative imaging biomarker for HS.
Collapse
Affiliation(s)
- Michael Rebsamen
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
- Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland
- *Correspondence: Michael Rebsamen
| | - Piotr Radojewski
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
- Swiss Institute for Translational and Entrepreneurial Medicine, sitem-insel, Bern, Switzerland
| | - Richard McKinley
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Mauricio Reyes
- ARTORG Center for Biomedical Research, University of Bern, Bern, Switzerland
| | - Roland Wiest
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
- Swiss Institute for Translational and Entrepreneurial Medicine, sitem-insel, Bern, Switzerland
| | - Christian Rummel
- Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| |
Collapse
|
9
|
Zhang M, Huang H, Liu W, Tang L, Li Q, Wang J, Huang X, Lin X, Meng H, Wang J, Zhan S, Li B, Luo J. Combined quantitative T2 mapping and [ 18F]FDG PET could improve lateralization of mesial temporal lobe epilepsy. Eur Radiol 2022; 32:6108-6117. [PMID: 35347363 PMCID: PMC9381472 DOI: 10.1007/s00330-022-08707-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2021] [Revised: 02/15/2022] [Accepted: 03/01/2022] [Indexed: 01/19/2023]
Abstract
OBJECTIVES To investigate whether quantitative T2 mapping is complementary to [18F]FDG PET in epileptogenic zone detection, thus improving the lateralization accuracy for drug-resistant mesial temporal lobe epilepsy (MTLE) using hybrid PET/MR. METHODS We acquired routine structural MRI, T2-weighted FLAIR, whole brain T2 mapping, and [18F]FDG PET in 46 MTLE patients and healthy controls on a hybrid PET/MR scanner, followed with computing voxel-based z-score maps of patients in reference to healthy controls. Asymmetry indexes of the hippocampus were calculated for each imaging modality, which then enter logistic regression models as univariate or multivariate for lateralization. Stereoelectroencephalography (SEEG) recordings and clinical decisions were collected as gold standard. RESULTS Routine structural MRI and T2w-FLAIR lateralized 47.8% (22/46) of MTLE patients, and FDG PET lateralized 84.8% (39/46). T2 mapping combined with [18F]FDG PET improved the lateralization accuracy by correctly lateralizing 95.6% (44/46) of MTLE patients. The asymmetry indexes of hippocampal T2 relaxometry and PET exhibit complementary tendency in detecting individual laterality, especially for MR-negative patients. In the quantitative analysis of z-score maps, the ipsilateral hippocampus had significantly lower SUVR (LTLE, p < 0.001; RTLE, p < 0.001) and higher T2 value (LTLE, p < 0.001; RTLE, p = 0.001) compared to the contralateral hippocampus. In logistic regression models, PET/T2 combination resulted in the highest AUC of 0.943 in predicting lateralization for MR-negative patients, followed by PET (AUC = 0.857) and T2 (AUC = 0.843). CONCLUSIONS The combination of quantitative T2 mapping and [18F]FDG PET could improve lateralization for temporal lobe epilepsy. KEY POINTS • Quantitative T2 mapping and18F-FDG PET are complementary in the characterization of hippocampal alterations of MR-negative temporal lobe epilepsy patients. • The combination of quantitative T2 and18F-FDG PET obtained from hybrid PET/MR could improve lateralization for temporal lobe epilepsy.
Collapse
Affiliation(s)
- Miao Zhang
- grid.16821.3c0000 0004 0368 8293Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Hui Huang
- grid.16821.3c0000 0004 0368 8293School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Wei Liu
- grid.16821.3c0000 0004 0368 8293Department of Neurosurgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Lihong Tang
- grid.16821.3c0000 0004 0368 8293School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Qikang Li
- grid.16821.3c0000 0004 0368 8293School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Jia Wang
- grid.16821.3c0000 0004 0368 8293School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Xinyun Huang
- grid.16821.3c0000 0004 0368 8293Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Xiaozhu Lin
- grid.16821.3c0000 0004 0368 8293Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Hongping Meng
- grid.16821.3c0000 0004 0368 8293Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Jin Wang
- grid.16821.3c0000 0004 0368 8293Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Shikun Zhan
- grid.16821.3c0000 0004 0368 8293Department of Neurosurgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China
| | - Biao Li
- grid.16821.3c0000 0004 0368 8293Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Jiao Tong University, Shanghai, 200240 China ,Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Ruijin Center, Shanghai, 200025 China
| | - Jie Luo
- grid.16821.3c0000 0004 0368 8293School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240 China
| |
Collapse
|
10
|
Abstract
Innovations and advances in technologies over the past few years have yielded faster and wider diagnostic applications to patients with neurologic diseases. This article focuses on the foreseeable developments of the diagnostic tools available to the neurologist in the next 15 years. Clinical judgment is and will remain the cornerstone of the diagnostic process, assisted by novel technologies, such as artificial intelligence and machine learning. Future neurologists must be educated to develop, cultivate, and rely on their clinical skills, while becoming familiar with novel, often complex, assistive technologies.
Collapse
|
11
|
Pemberton HG, Zaki LAM, Goodkin O, Das RK, Steketee RME, Barkhof F, Vernooij MW. Technical and clinical validation of commercial automated volumetric MRI tools for dementia diagnosis-a systematic review. Neuroradiology 2021; 63:1773-1789. [PMID: 34476511 PMCID: PMC8528755 DOI: 10.1007/s00234-021-02746-3] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2021] [Accepted: 06/02/2021] [Indexed: 12/22/2022]
Abstract
Developments in neuroradiological MRI analysis offer promise in enhancing objectivity and consistency in dementia diagnosis through the use of quantitative volumetric reporting tools (QReports). Translation into clinical settings should follow a structured framework of development, including technical and clinical validation steps. However, published technical and clinical validation of the available commercial/proprietary tools is not always easy to find and pathways for successful integration into the clinical workflow are varied. The quantitative neuroradiology initiative (QNI) framework highlights six necessary steps for the development, validation and integration of quantitative tools in the clinic. In this paper, we reviewed the published evidence regarding regulatory-approved QReports for use in the memory clinic and to what extent this evidence fulfils the steps of the QNI framework. We summarize unbiased technical details of available products in order to increase the transparency of evidence and present the range of reporting tools on the market. Our intention is to assist neuroradiologists in making informed decisions regarding the adoption of these methods in the clinic. For the 17 products identified, 11 companies have published some form of technical validation on their methods, but only 4 have published clinical validation of their QReports in a dementia population. Upon systematically reviewing the published evidence for regulatory-approved QReports in dementia, we concluded that there is a significant evidence gap in the literature regarding clinical validation, workflow integration and in-use evaluation of these tools in dementia MRI diagnosis.
Collapse
Affiliation(s)
- Hugh G Pemberton
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK.
- UCL Queen Square Institute of Neurology, University College London, London, UK.
- Dementia Research Centre, UCL Queen Square Institute of Neurology, University College London, London, UK.
| | - Lara A M Zaki
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, The Netherlands
| | - Olivia Goodkin
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK
- UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Ravi K Das
- Clinical, Educational and Health Psychology, University College London, London, UK
| | - Rebecca M E Steketee
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, The Netherlands
| | - Frederik Barkhof
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK
- UCL Queen Square Institute of Neurology, University College London, London, UK
- Radiology & Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - Meike W Vernooij
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, The Netherlands
- Department of Epidemiology, Erasmus MC University Medical Center, Rotterdam, The Netherlands
| |
Collapse
|
12
|
Pemberton HG, Prados F. Editorial for "MRI Findings of Arachnoiditis, Revisited. Is Classification Needed?". J Magn Reson Imaging 2021; 54:910-911. [PMID: 33713514 DOI: 10.1002/jmri.27597] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Accepted: 03/02/2021] [Indexed: 11/10/2022] Open
Affiliation(s)
- Hugh G Pemberton
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK.,Neuroradiological Academic Unit, UCL Queen Square Institute of Neurology, University College London, London, UK
| | - Ferran Prados
- Centre for Medical Image Computing (CMIC), Department of Medical Physics and Bioengineering, University College London, London, UK.,Nuclear Magnetic Resonance (NMR) Research Unit, Queen Square Multiple Sclerosis Centre, Department of Neuroinflammation, UCL Institute of Neurology, London, UK.,e-Health Centre, Universitat Oberta de Catalunya, Barcelona, Spain
| |
Collapse
|