1
|
Eilertsen H, Menon CS, Law ZK, Chen C, Bath PM, Steiner T, Desborough MJ, Sandset EC, Sprigg N, Al-Shahi Salman R. Haemostatic therapies for stroke due to acute, spontaneous intracerebral haemorrhage. Cochrane Database Syst Rev 2023; 10:CD005951. [PMID: 37870112 PMCID: PMC10591281 DOI: 10.1002/14651858.cd005951.pub5] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/24/2023]
Abstract
BACKGROUND Outcome after acute spontaneous (non-traumatic) intracerebral haemorrhage (ICH) is influenced by haematoma volume. ICH expansion occurs in about 20% of people with acute ICH. Early haemostatic therapy might improve outcome by limiting ICH expansion. This is an update of a Cochrane Review first published in 2006, and last updated in 2018. OBJECTIVES To examine 1. the effects of individual classes of haemostatic therapies, compared with placebo or open control, in adults with acute spontaneous ICH, and 2. the effects of each class of haemostatic therapy according to the use and type of antithrombotic drug before ICH onset. SEARCH METHODS We searched the Cochrane Stroke Trials Register, CENTRAL (2022, Issue 8), MEDLINE Ovid, and Embase Ovid on 12 September 2022. To identify further published, ongoing, and unpublished randomised controlled trials (RCTs), we scanned bibliographies of relevant articles and searched international registers of RCTs in September 2022. SELECTION CRITERIA We included RCTs of any haemostatic intervention (i.e. procoagulant treatments such as clotting factor concentrates, antifibrinolytic drugs, platelet transfusion, or agents to reverse the action of antithrombotic drugs) for acute spontaneous ICH, compared with placebo, open control, or an active comparator. DATA COLLECTION AND ANALYSIS We used standard Cochrane methods. Our primary outcome was death/dependence (modified Rankin Scale (mRS) 4 to 6) by day 90. Secondary outcomes were ICH expansion on brain imaging after 24 hours, all serious adverse events, thromboembolic adverse events, death from any cause, quality of life, mood, cognitive function, Barthel Index score, and death or dependence measured on the Extended Glasgow Outcome Scale by day 90. MAIN RESULTS We included 20 RCTs involving 4652 participants: nine RCTs of recombinant activated factor VII (rFVIIa) versus placebo/open control (1549 participants), eight RCTs of antifibrinolytic drugs versus placebo/open control (2866 participants), one RCT of platelet transfusion versus open control (190 participants), and two RCTs of prothrombin complex concentrates (PCC) versus fresh frozen plasma (FFP) (47 participants). Four (20%) RCTs were at low risk of bias in all criteria. For rFVIIa versus placebo/open control for spontaneous ICH with or without surgery there was little to no difference in death/dependence by day 90 (risk ratio (RR) 0.88, 95% confidence interval (CI) 0.74 to 1.05; 7 RCTs, 1454 participants; low-certainty evidence). We found little to no difference in ICH expansion between groups (RR 0.81, 95% CI 0.56 to 1.16; 4 RCTs, 220 participants; low-certainty evidence). There was little to no difference in all serious adverse events and death from any cause between groups (all serious adverse events: RR 0.81, 95% CI 0.30 to 2.22; 2 RCTs, 87 participants; very low-certainty evidence; death from any cause: RR 0.78, 95% CI 0.56 to 1.08; 8 RCTs, 1544 participants; moderate-certainty evidence). For antifibrinolytic drugs versus placebo/open control for spontaneous ICH, there was no difference in death/dependence by day 90 (RR 1.00, 95% CI 0.93 to 1.07; 5 RCTs, 2683 participants; high-certainty evidence). We found a slight reduction in ICH expansion with antifibrinolytic drugs for spontaneous ICH compared to placebo/open control (RR 0.86, 95% CI 0.76 to 0.96; 8 RCTs, 2866 participants; high-certainty evidence). There was little to no difference in all serious adverse events and death from any cause between groups (all serious adverse events: RR 1.02, 95% CI 0.75 to 1.39; 4 RCTs, 2599 participants; high-certainty evidence; death from any cause: RR 1.02, 95% CI 0.89 to 1.18; 8 RCTs, 2866 participants; high-certainty evidence). There was little to no difference in quality of life, mood, or cognitive function (quality of life: mean difference (MD) 0, 95% CI -0.03 to 0.03; 2 RCTs, 2349 participants; mood: MD 0.30, 95% CI -1.98 to 2.57; 2 RCTs, 2349 participants; cognitive function: MD -0.37, 95% CI -1.40 to 0.66; 1 RCTs, 2325 participants; all high-certainty evidence). Platelet transfusion likely increases death/dependence by day 90 compared to open control for antiplatelet-associated ICH (RR 1.29, 95% CI 1.04 to 1.61; 1 RCT, 190 participants; moderate-certainty evidence). We found little to no difference in ICH expansion between groups (RR 1.32, 95% CI 0.91 to 1.92; 1 RCT, 153 participants; moderate-certainty evidence). There was little to no difference in all serious adverse events and death from any cause between groups (all serious adverse events: RR 1.46, 95% CI 0.98 to 2.16; 1 RCT, 190 participants; death from any cause: RR 1.42, 95% CI 0.88 to 2.28; 1 RCT, 190 participants; both moderate-certainty evidence). For PCC versus FFP for anticoagulant-associated ICH, the evidence was very uncertain about the effect on death/dependence by day 90, ICH expansion, all serious adverse events, and death from any cause between groups (death/dependence by day 90: RR 1.21, 95% CI 0.76 to 1.90; 1 RCT, 37 participants; ICH expansion: RR 0.54, 95% CI 0.23 to 1.22; 1 RCT, 36 participants; all serious adverse events: RR 0.27, 95% CI 0.02 to 3.74; 1 RCT, 5 participants; death from any cause: RR 0.49, 95% CI 0.16 to 1.56; 2 RCTs, 42 participants; all very low-certainty evidence). AUTHORS' CONCLUSIONS In this updated Cochrane Review including 20 RCTs involving 4652 participants, rFVIIa likely results in little to no difference in reducing death or dependence after spontaneous ICH with or without surgery; antifibrinolytic drugs result in little to no difference in reducing death or dependence after spontaneous ICH, but result in a slight reduction in ICH expansion within 24 hours; platelet transfusion likely increases death or dependence after antiplatelet-associated ICH; and the evidence is very uncertain about the effect of PCC compared to FFP on death or dependence after anticoagulant-associated ICH. Thirteen RCTs are ongoing and are likely to increase the certainty of the estimates of treatment effect.
Collapse
Affiliation(s)
- Helle Eilertsen
- Department of Geriatric Medicine, Oslo University Hospital, Oslo, Norway
- Faculty of Medicine, Institute of Clinical Medicine, University of Oslo, Oslo, Norway
| | | | - Zhe Kang Law
- Department of Medicine, Faculty of Medicine, Universiti Kebangsaan Malaysia Medical Centre, Kuala Lumpur, Malaysia
| | - Chen Chen
- The George Institute for Global Health, Faculty of Medicine, UNSW, Sydney, Australia
- The George Institute for Global Health, Beijing, China
- Department of Neurology, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Philip M Bath
- Stroke Medicine, University of Nottingham, Nottingham, UK
| | - Thorsten Steiner
- Klinikum Frankfurt Höchst, Frankfurt, Germany
- Department of Neurology, Heidelberg University Hospital, Heidelberg, Germany
| | - Michael Jr Desborough
- Department of Clinical Haematology, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Else C Sandset
- Department of Neurology, Oslo University Hospital Ullevål, Oslo, Norway
- The Norwegian Air Ambulance Foundation, Oslo, Norway
| | - Nikola Sprigg
- Stroke Medicine, University of Nottingham, Nottingham, UK
| | | |
Collapse
|
2
|
Sundaresan V, Arthofer C, Zamboni G, Murchison AG, Dineen RA, Rothwell PM, Auer DP, Wang C, Miller KL, Tendler BC, Alfaro-Almagro F, Sotiropoulos SN, Sprigg N, Griffanti L, Jenkinson M. Automated detection of cerebral microbleeds on MR images using knowledge distillation framework. Front Neuroinform 2023; 17:1204186. [PMID: 37492242 PMCID: PMC10363739 DOI: 10.3389/fninf.2023.1204186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Accepted: 06/19/2023] [Indexed: 07/27/2023] Open
Abstract
Introduction Cerebral microbleeds (CMBs) are associated with white matter damage, and various neurodegenerative and cerebrovascular diseases. CMBs occur as small, circular hypointense lesions on T2*-weighted gradient recalled echo (GRE) and susceptibility-weighted imaging (SWI) images, and hyperintense on quantitative susceptibility mapping (QSM) images due to their paramagnetic nature. Accurate automated detection of CMBs would help to determine quantitative imaging biomarkers (e.g., CMB count) on large datasets. In this work, we propose a fully automated, deep learning-based, 3-step algorithm, using structural and anatomical properties of CMBs from any single input image modality (e.g., GRE/SWI/QSM) for their accurate detections. Methods In our method, the first step consists of an initial candidate detection step that detects CMBs with high sensitivity. In the second step, candidate discrimination step is performed using a knowledge distillation framework, with a multi-tasking teacher network that guides the student network to classify CMB and non-CMB instances in an offline manner. Finally, a morphological clean-up step further reduces false positives using anatomical constraints. We used four datasets consisting of different modalities specified above, acquired using various protocols and with a variety of pathological and demographic characteristics. Results On cross-validation within datasets, our method achieved a cluster-wise true positive rate (TPR) of over 90% with an average of <2 false positives per subject. The knowledge distillation framework improves the cluster-wise TPR of the student model by 15%. Our method is flexible in terms of the input modality and provides comparable cluster-wise TPR and better cluster-wise precision compared to existing state-of-the-art methods. When evaluating across different datasets, our method showed good generalizability with a cluster-wise TPR >80 % with different modalities. The python implementation of the proposed method is openly available.
Collapse
Affiliation(s)
- Vaanathi Sundaresan
- Department of Computational and Data Sciences, Indian Institute of Science, Bengaluru, Karnataka, India
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Christoph Arthofer
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- National Institute for Health and Care Research (NIHR) Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
| | - Giovanna Zamboni
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- Dipartimento di Scienze Biomediche, Metaboliche e Neuroscienze, Universitá di Modena e Reggio Emilia, Modena, Italy
| | - Andrew G. Murchison
- Department of Neuroradiology, Oxford University Hospitals National Health Service (NHS) Foundation Trust, Oxford, United Kingdom
| | - Robert A. Dineen
- National Institute for Health and Care Research (NIHR) Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
- Radiological Sciences, Mental Health and Clinical Neurosciences, School of Medicine, University of Nottingham, Nottingham, United Kingdom
| | - Peter M. Rothwell
- Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Dorothee P. Auer
- National Institute for Health and Care Research (NIHR) Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
- Radiological Sciences, Mental Health and Clinical Neurosciences, School of Medicine, University of Nottingham, Nottingham, United Kingdom
| | - Chaoyue Wang
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Karla L. Miller
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Benjamin C. Tendler
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Fidel Alfaro-Almagro
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Stamatios N. Sotiropoulos
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- National Institute for Health and Care Research (NIHR) Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
| | - Nikola Sprigg
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
| | - Ludovica Griffanti
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Human Brain Activity, Department of Psychiatry, University of Oxford, Oxford, United Kingdom
| | - Mark Jenkinson
- Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- South Australian Health and Medical Research Institute, Adelaide, SA, Australia
- Australian Institute for Machine Learning, School of Computer Science, The University of Adelaide, Adelaide, SA, Australia
| |
Collapse
|
3
|
Pszczolkowski S, Sprigg N, Woodhouse LJ, Gallagher R, Swienton D, Law ZK, Casado AM, Roberts I, Werring DJ, Al-Shahi Salman R, England TJ, Morgan PS, Bath PM, Dineen RA. Effect of Tranexamic Acid Administration on Remote Cerebral Ischemic Lesions in Acute Spontaneous Intracerebral Hemorrhage: A Substudy of a Randomized Clinical Trial. JAMA Neurol 2022; 79:468-477. [PMID: 35311937 PMCID: PMC8938900 DOI: 10.1001/jamaneurol.2022.0217] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
Importance Hyperintense foci on diffusion-weighted imaging (DWI) that are spatially remote from the acute hematoma occur in 20% of people with acute spontaneous intracerebral hemorrhage (ICH). Tranexamic acid, a hemostatic agent that is under investigation for treating acute ICH, might increase DWI hyperintense lesions (DWIHLs). Objective To establish whether tranexamic acid compared with placebo increased the prevalence or number of remote cerebral DWIHLs within 2 weeks of ICH onset. Design, Setting, and Participants This prospective nested magnetic resonance imaging (MRI) substudy of a randomized clinical trial (RCT) recruited participants from the multicenter, double-blind, placebo-controlled, phase 3 RCT (Tranexamic Acid for Hyperacute Primary Intracerebral Hemorrhage [TICH-2]) from July 1, 2015, to September 30, 2017, and conducted follow-up to 90 days after participants were randomized to either the tranexamic acid or placebo group. Participants had acute spontaneous ICH and included TICH-2 participants who provided consent to undergo additional MRI scans for the MRI substudy and those who had clinical MRI data that were compatible with the brain MRI protocol of the substudy. Data analyses were performed on an intention-to-treat basis on January 20, 2020. Interventions The tranexamic acid group received 1 g in 100-mL intravenous bolus loading dose, followed by 1 g in 250-mL infusion within 8 hours of ICH onset. The placebo group received 0.9% saline within 8 hours of ICH onset. Brain MRI scans, including DWI, were performed within 2 weeks. Main Outcomes and Measures Prevalence and number of remote DWIHLs were compared between the treatment groups using binary logistic regression adjusted for baseline covariates. Results A total of 219 participants (mean [SD] age, 65.1 [13.8] years; 126 men [57.5%]) who had brain MRI data were included. Of these participants, 96 (43.8%) were randomized to receive tranexamic acid and 123 (56.2%) were randomized to receive placebo. No baseline differences in demographic characteristics and clinical or imaging features were found between the groups. There was no increase for the tranexamic acid group compared with the placebo group in DWIHL prevalence (20 of 96 [20.8%] vs 28 of 123 [22.8%]; odds ratio [OR], 0.71; 95% CI, 0.33-1.53; P = .39) or mean (SD) number of DWIHLs (1.75 [1.45] vs 1.81 [1.71]; mean difference [MD], -0.08; 95% CI, -0.36 to 0.20; P = .59). In an exploratory analysis, participants who were randomized within 3 hours of ICH onset or those with chronic infarcts appeared less likely to have DWIHLs if they received tranexamic acid. Participants with probable cerebral amyloid angiopathy appeared more likely to have DWIHLs if they received tranexamic acid. Conclusions and Relevance This substudy of an RCT found no evidence of increased prevalence or number of remote DWIHLs after tranexamic acid treatment in acute ICH. These findings provide reassurance for ongoing and future trials that tranexamic acid for acute ICH is unlikely to induce cerebral ischemic events. Trial Registration isrctn.org Identifier: ISRCTN93732214.
Collapse
Affiliation(s)
- Stefan Pszczolkowski
- Radiological Sciences, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- National Institute for Health Research Nottingham Biomedical Research Centre, Nottingham, United Kingdom
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
| | - Nikola Sprigg
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- Stroke, Nottingham University Hospitals National Health Service (NHS) Trust, Nottingham, United Kingdom
| | - Lisa J Woodhouse
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
| | - Rebecca Gallagher
- Imaging Department, Leicester Royal Infirmary, Leicester, United Kingdom
| | - David Swienton
- Imaging Department, Leicester Royal Infirmary, Leicester, United Kingdom
| | - Zhe Kang Law
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- National University of Malaysia, Kuala Lumpur, Malaysia
| | - Ana M Casado
- Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom
| | - Ian Roberts
- London School of Hygiene and Tropical Medicine, London, United Kingdom
| | - David J Werring
- Stroke Research Centre, University College London Queen Square Institute of Neurology, London, United Kingdom
| | | | - Timothy J England
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- Department of Stroke, University Hospitals of Derby and Burton NHS Foundation Trust, Derby, United Kingdom
| | - Paul S Morgan
- Radiological Sciences, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- Medical Physics and Clinical Engineering, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
| | - Philip M Bath
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- Stroke, Nottingham University Hospitals National Health Service (NHS) Trust, Nottingham, United Kingdom
| | - Robert A Dineen
- Radiological Sciences, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
- National Institute for Health Research Nottingham Biomedical Research Centre, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
| |
Collapse
|
4
|
Sundaresan V, Arthofer C, Zamboni G, Dineen RA, Rothwell PM, Sotiropoulos SN, Auer DP, Tozer DJ, Markus HS, Miller KL, Dragonu I, Sprigg N, Alfaro-Almagro F, Jenkinson M, Griffanti L. Automated Detection of Candidate Subjects With Cerebral Microbleeds Using Machine Learning. Front Neuroinform 2022; 15:777828. [PMID: 35126079 PMCID: PMC8811357 DOI: 10.3389/fninf.2021.777828] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2021] [Accepted: 12/23/2021] [Indexed: 11/21/2022] Open
Abstract
Cerebral microbleeds (CMBs) appear as small, circular, well defined hypointense lesions of a few mm in size on T2*-weighted gradient recalled echo (T2*-GRE) images and appear enhanced on susceptibility weighted images (SWI). Due to their small size, contrast variations and other mimics (e.g., blood vessels), CMBs are highly challenging to detect automatically. In large datasets (e.g., the UK Biobank dataset), exhaustively labelling CMBs manually is difficult and time consuming. Hence it would be useful to preselect candidate CMB subjects in order to focus on those for manual labelling, which is essential for training and testing automated CMB detection tools on these datasets. In this work, we aim to detect CMB candidate subjects from a larger dataset, UK Biobank, using a machine learning-based, computationally light pipeline. For our evaluation, we used 3 different datasets, with different intensity characteristics, acquired with different scanners. They include the UK Biobank dataset and two clinical datasets with different pathological conditions. We developed and evaluated our pipelines on different types of images, consisting of SWI or GRE images. We also used the UK Biobank dataset to compare our approach with alternative CMB preselection methods using non-imaging factors and/or imaging data. Finally, we evaluated the pipeline's generalisability across datasets. Our method provided subject-level detection accuracy > 80% on all the datasets (within-dataset results), and showed good generalisability across datasets, providing a consistent accuracy of over 80%, even when evaluated across different modalities.
Collapse
Affiliation(s)
- Vaanathi Sundaresan
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
- Oxford-Nottingham Centre for Doctoral Training in Biomedical Imaging, University of Oxford, Oxford, United Kingdom
| | - Christoph Arthofer
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
- NIHR Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
| | - Giovanna Zamboni
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
- Wolfson Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- Dipartimento di Scienze Biomediche, Metaboliche e Neuroscienze, Università di Modena e Reggio Emilia, Modena, Italy
| | - Robert A. Dineen
- NIHR Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
- Radiological Sciences, Mental Health and Clinical Neurosciences, School of Medicine, University of Nottingham, Nottingham, United Kingdom
| | - Peter M. Rothwell
- Wolfson Centre for Prevention of Stroke and Dementia, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Stamatios N. Sotiropoulos
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
- NIHR Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
| | - Dorothee P. Auer
- NIHR Nottingham Biomedical Research Centre, Queen's Medical Centre, University of Nottingham, Nottingham, United Kingdom
- Sir Peter Mansfield Imaging Centre, University of Nottingham, Nottingham, United Kingdom
- Radiological Sciences, Mental Health and Clinical Neurosciences, School of Medicine, University of Nottingham, Nottingham, United Kingdom
| | - Daniel J. Tozer
- Department of Clinical Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Hugh S. Markus
- Department of Clinical Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Karla L. Miller
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
| | - Iulius Dragonu
- Siemens Healthcare Ltd., Research and Collaborations GB & I, Frimley, United Kingdom
| | - Nikola Sprigg
- Stroke Trials Unit, Mental Health and Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom
| | - Fidel Alfaro-Almagro
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
| | - Mark Jenkinson
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
- South Australian Health and Medical Research Institute (SAHMRI), Adelaide, SA, Australia
- Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide, Adelaide, SA, Australia
| | - Ludovica Griffanti
- Nuffield Department of Clinical Neurosciences, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Functional MRI of the Brain, University of Oxford, Oxford, United Kingdom
- Department of Psychiatry, Wellcome Centre for Integrative Neuroimaging, Oxford Centre for Human Brain Activity, University of Oxford, Oxford, United Kingdom
- *Correspondence: Ludovica Griffanti
| |
Collapse
|
5
|
Pszczolkowski S, Law ZK, Gallagher RG, Meng D, Swienton DJ, Morgan PS, Bath PM, Sprigg N, Dineen RA. Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage. Comput Biol Med 2019; 106:126-139. [PMID: 30711800 PMCID: PMC6382492 DOI: 10.1016/j.compbiomed.2019.01.022] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2018] [Revised: 01/24/2019] [Accepted: 01/24/2019] [Indexed: 11/19/2022]
Abstract
BACKGROUND Spontaneous intracerebral haemorrhage (SICH) is a common condition with high morbidity and mortality. Segmentation of haematoma and perihaematoma oedema on medical images provides quantitative outcome measures for clinical trials and may provide important markers of prognosis in people with SICH. METHODS We take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute and early subacute SICH and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on shape and intensity analysis for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation. RESULTS Using Dice scores to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters on 18 patients, we observe that our technique achieves overlap scores that are very similar to those obtained by pairwise expert rater comparison. A further comparison between the proposed method and a state-of-the-art Deep Learning segmentation on a separate set of 32 manually annotated subjects confirms the proposed method can achieve comparable results with very mild computational burden and in a completely training-free and unsupervised way. CONCLUSION Our technique can be a computationally light and effective way to automatically delineate haematoma and oedema extent directly from MR images. Thus, with increasing use of MR images clinically after intracerebral haemorrhage this technique has the potential to inform clinical practice in the future.
Collapse
Affiliation(s)
- Stefan Pszczolkowski
- Stroke Trials Unit, Division of Clinical Neuroscience, University of Nottingham, UK; Radiological Sciences, Division of Clinical Neuroscience, University of Nottingham, UK.
| | - Zhe K Law
- Stroke Trials Unit, Division of Clinical Neuroscience, University of Nottingham, UK; Department of Medicine, National University of Malaysia, Malaysia.
| | - Rebecca G Gallagher
- Department of Neuroradiology, Nottingham University Hospitals, Queen's Medical Centre, Nottingham, UK; Department of Radiology, Royal Derby Hospital, Derby, UK.
| | - Dewen Meng
- Radiological Sciences, Division of Clinical Neuroscience, University of Nottingham, UK.
| | - David J Swienton
- Department of Neuroradiology, Nottingham University Hospitals, Queen's Medical Centre, Nottingham, UK; Imaging Department, Leicester Royal Infirmary, Leicester, UK.
| | - Paul S Morgan
- Medical Physics and Clinical Engineering, Nottingham University Hospitals, Queen's Medical Centre, Nottingham, UK.
| | - Philip M Bath
- Stroke Trials Unit, Division of Clinical Neuroscience, University of Nottingham, UK.
| | - Nikola Sprigg
- Stroke Trials Unit, Division of Clinical Neuroscience, University of Nottingham, UK.
| | - Rob A Dineen
- Radiological Sciences, Division of Clinical Neuroscience, University of Nottingham, UK; NIHR Nottingham BRC, UK.
| |
Collapse
|