Virginia F. J. Newcombe

Virginia F. J. Newcombe

Auto-generated profile, based on publicly available information

Virginia F. J. Newcombe

Department of Medicine, University of Cambridge, Cambridge, UK

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2017 in Medical Image Analysis
Verified
Journal Article
Open access
KKKonstantinos Kamnitsas
Konstantinos Kamnitsas
CLChristian Ledig
Christian Ledig
VNVirginia F.J. Newcombe
Virginia F.J. Newcombe
JSJoanna P. Simpson
Joanna P. Simpson
AKAndrew D. Kane
Andrew D. Kane
BGBen Glocker
Ben Glocker
We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation. The devised architecture is the result of an in-depth analysis of the limitations of current networks proposed for similar applications. To overcome the computational burden of processing 3D medical scans, we have devised an efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data. Further, we analyze the development of deeper, thus more discriminative 3D CNNs. In order to incorporate both local and larger contextual information, we employ a dual pathway architecture that processes the input images at multiple scales simultaneously. For post-processing of the network's soft segmentation, we use a 3D fully connected Conditional Random Field which effectively removes false positives. Our pipeline is extensively evaluated on three challenging tasks of lesion segmentation in multi-channel MRI patient data with traumatic brain injuries, brain tumours, and ischemic stroke. We improve on the state-of-the-art for all three applications, with top ranking performance on the public benchmarks BRATS 2015 and ISLES 2015. Our method is computationally efficient, which allows its adoption in a variety of research and clinical settings. The source code of our implementation is made publicly available.

1 December 2017 in The Lancet Neurology
Verified
Journal Article
Closed access
AMAndrew I R Maas
Andrew I R Maas
DMDavid K Menon
David K Menon
PAP David Adelson
P David Adelson
NANada Andelic
Nada Andelic
MBMichael J Bell
Michael J Bell
FZFabrizio Zumbo
Fabrizio Zumbo

1 October 2019 in The Lancet Neurology
Verified
Journal Article
Open access
ESEwout W Steyerberg
Ewout W Steyerberg
EWEveline Wiegers
Eveline Wiegers
CSCharlie Sewalt
Charlie Sewalt
ABAndras Buki
Andras Buki
GCGiuseppe Citerio
Giuseppe Citerio
TZTommaso Zoerle
Tommaso Zoerle
The burden of traumatic brain injury (TBI) poses a large public health and societal problem, but the characteristics of patients and their care pathways in Europe are poorly understood. We aimed to characterise patient case-mix, care pathways, and outcomes of TBI. CENTER-TBI is a Europe-based, observational cohort study, consisting of a core study and a registry. Inclusion criteria for the core study were a clinical diagnosis of TBI, presentation fewer than 24 h after injury, and an indication for CT. Patients were differentiated by care pathway and assigned to the emergency room (ER) stratum (patients who were discharged from an emergency room), admission stratum (patients who were admitted to a hospital ward), or intensive care unit (ICU) stratum (patients who were admitted to the ICU). Neuroimages and biospecimens were stored in repositories and outcome was assessed at 6 months after injury. We used the IMPACT core model for estimating the expected mortality and proportion with unfavourable Glasgow Outcome Scale Extended (GOSE) outcomes in patients with moderate or severe TBI (Glasgow Coma Scale [GCS] score ≤12). The core study was registered with ClinicalTrials.gov, number NCT02210221, and with Resource Identification Portal (RRID: SCR_015582). Data from 4509 patients from 18 countries, collected between Dec 9, 2014, and Dec 17, 2017, were analysed in the core study and from 22 782 patients in the registry. In the core study, 848 (19%) patients were in the ER stratum, 1523 (34%) in the admission stratum, and 2138 (47%) in the ICU stratum. In the ICU stratum, 720 (36%) patients had mild TBI (GCS score 13-15). Compared with the core cohort, the registry had a higher proportion of patients in the ER (9839 [43%]) and admission (8571 [38%]) strata, with more than 95% of patients classified as having mild TBI. Patients in the core study were older than those in previous studies (median age 50 years [IQR 30-66], 1254 [28%] aged >65 years), 462 (11%) had serious comorbidities, 772 (18%) were taking anticoagulant or antiplatelet medication, and alcohol was contributory in 1054 (25%) TBIs. MRI and blood biomarker measurement enhanced characterisation of injury severity and type. Substantial inter-country differences existed in care pathways and practice. Incomplete recovery at 6 months (GOSE <8) was found in 207 (30%) patients in the ER stratum, 665 (53%) in the admission stratum, and 1547 (84%) in the ICU stratum. Among patients with moderate-to-severe TBI in the ICU stratum, 623 (55%) patients had unfavourable outcome at 6 months (GOSE <5), similar to the proportion predicted by the IMPACT prognostic model (observed to expected ratio 1·06 [95% CI 0·97-1·14]), but mortality was lower than expected (0·70 [0·62-0·76]). Patients with TBI who presented to European centres in the core study were older than were those in previous observational studies and often had comorbidities. Overall, most patients presented with mild TBI. The incomplete recovery of many patients should motivate precision medicine research and the identification of best practices to improve these outcomes. European Union 7th Framework Programme, the Hannelore Kohl Stiftung, OneMind, and Integra LifeSciences Corporation.

23 May 2017
Verified
Book Chapter
Open access
PDF file
KKKonstantinos Kamnitsas
Konstantinos Kamnitsas
CBChristian Baumgartner
Christian Baumgartner
CLChristian Ledig
Christian Ledig
VNVirginia Newcombe
Virginia Newcombe
JSJoanna Simpson
Joanna Simpson
BGBen Glocker
Ben Glocker
Significant advances have been made towards building accurate automatic segmentation systems for a variety of biomedical applications using machine learning. However, the performance of these systems often degrades when they are applied on new data that differ from the training data, for example, due to variations in imaging protocols. Manually annotating new data for each test domain is not a feasible solution. In this work we investigate unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more robust to differences in the input data, and which does not require any annotations on the test domain. Specifically, we derive domain-invariant features by learning to counter an adversarial network, which attempts to classify the domain of the input data by observing the activations of the segmentation network. Furthermore, we propose a multi-connected domain discriminator for improved adversarial training. Our system is evaluated using two MR databases of subjects with traumatic brain injuries, acquired using different scanners and imaging protocols. Using our unsupervised approach, we obtain segmentation accuracies which are close to the upper bound of supervised domain adaptation.

24 April 2012 in Annals of Neurology
Verified
Journal Article
Closed access
PDF file
DFDavinia Fernández-Espejo
Davinia Fernández-Espejo
ASAndrea Soddu
Andrea Soddu
DCDamian Cruse
Damian Cruse
EPEva M. Palacios
Eva M. Palacios
CJCarme Junque
Carme Junque
AOAdrian M. Owen
Adrian M. Owen

1 June 2020 in EBioMedicine
Verified
Journal Article
Open access
Endre CzeiterEndre Czeiter
Endre Czeiter
KAKrisztina Amrein
Krisztina Amrein
BGBenjamin Y. Gravesteijn
Benjamin Y. Gravesteijn
FLFiona Lecky
Fiona Lecky
DMDavid K. Menon
David K. Menon
ABAndrás Büki
András Büki
Serum biomarkers may inform and improve care in traumatic brain injury (TBI). We aimed to correlate serum biomarkers with clinical severity, care path and imaging abnormalities in TBI, and explore their incremental value over clinical characteristics in predicting computed tomographic (CT) abnormalities. We analyzed six serum biomarkers (S100B, NSE, GFAP, UCH-L1, NFL and t-tau) obtained <24 h post-injury from 2867 patients with any severity of TBI in the Collaborative European NeuroTrauma Effectiveness Research (CENTER-TBI) Core Study, a prospective, multicenter, cohort study. Univariable and multivariable logistic regression analyses were performed. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC) with 95% confidence intervals. All biomarkers scaled with clinical severity and care path (ER only, ward admission, or ICU), and with presence of CT abnormalities. GFAP achieved the highest discrimination for predicting CT abnormalities (AUC 0•89 [95%CI: 0•87-0•90]), with a 99% likelihood of better discriminating CT-positive patients than clinical characteristics used in contemporary decision rules. In patients with mild TBI, GFAP also showed incremental diagnostic value: discrimination increased from 0•84 [95%CI: 0•83-0•86] to 0•89 [95%CI: 0•87-0•90] when GFAP was included. Results were consistent across strata, and injury severity. Combinations of biomarkers did not improve discrimination compared to GFAP alone. Currently available biomarkers reflect injury severity, and serum GFAP, measured within 24 h after injury, outperforms clinical characteristics in predicting CT abnormalities. Our results support the further development of serum GFAP assays towards implementation in clinical practice, for which robust clinical assay platforms are required. CENTER-TBI study was supported by the European Union 7th Framework program (EC grant 602150).