ORCID Profile
0000-0002-0540-9353
Current Organisation
University of Oxford
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Cold Spring Harbor Laboratory
Date: 26-07-2020
DOI: 10.1101/2020.07.24.219485
Abstract: White matter hyperintensities (WMHs) have been associated with various cerebrovascular and neurodegenerative diseases. Reliable quantification of WMHs is essential for understanding their clinical impact in normal and pathological populations. Automated segmentation of WMHs is highly challenging due to heterogeneity in WMH characteristics between deep and periventricular white matter, presence of artefacts and differences in the pathology and demographics of populations. In this work, we propose an ensemble triplanar network that combines the predictions from three different planes of brain MR images to provide an accurate WMH segmentation. Also, the network uses anatomical information regarding WMH spatial distribution in loss functions for improving the efficiency of segmentation and to overcome the contrast variations between deep and periventricular WMHs. We evaluated our method on 5 datasets, of which 3 are part of a publicly available dataset (training data for MICCAI WMH Segmentation Challenge 2017 - MWSC 2017) consisting of subjects from three different cohorts. On evaluating our method separately in deep and periventricular regions, we observed robust and comparable performance in both regions. Our method performed better than most of the existing methods, including FSL BIANCA, and on par with the top ranking deep learning method of MWSC 2017.
Publisher: Center for Open Science
Date: 21-10-2022
Abstract: It is commonly asserted that MRI-derived lesion masks outperform CT-derived lesion masks in lesion-mapping analysis. However, no quantitative analysis has been conducted to support or refute this claim. This study reports an objective comparison of lesion-mapping analyses based on CT- and MRI-derived lesion masks to clarify how input imaging type may ultimately impact analysis results.Routine CT and MRI data were collected from 85 acute stroke survivors. These data were employed to create binarized lesion masks and conduct lesion-mapping analyses on simulated behavioral data. Following standard lesion-mapping analysis methodology, each voxel or region of interest (ROI) were considered as the underlying “target” within CT and MRI data independently. The resulting thresholded z-maps were compared between matched CT- and MRI-based analyses. Paired MRI- and CT-derived lesion masks were found to exhibit good agreement in location, overlap, and size. In single-voxel simulations, MRI-based lesion mapping was able to include more voxels than CT-based analyses, but CT-based analysis results were closer to the underlying target voxel. Simulated lesion symptom mapping results yielded by paired CT and MRI lesion symptom mapping analyses demonstrated good agreement in terms of Dice coefficient when systematic differences in cluster size and lesion overlay are considered. In ROI-level simulations, both CT and MRI-derived analyses yielded low Dice similarity coefficients but no significant differences in performance were identified between modalities.Overall, these results suggest that CT- and MRI-based lesion mapping analyses produce comparable results. This finding is critically important as it suggests that future studies can and should employ CT-derived lesion masks if these scans are available within the appropriate time-window.
Publisher: Springer International Publishing
Date: 2021
Publisher: Cold Spring Harbor Laboratory
Date: 21-05-2018
DOI: 10.1101/327205
Abstract: White matter hyperintensities (WMH), also known as white matter lesions, are localised white matter areas that appear hyperintense on MRI scans. WMH commonly occur in the ageing population, and are often associated with several factors such as cognitive disorders, cardiovascular risk factors, cerebrovascular and neurodegenerative diseases. Despite the fact that some links between lesion location and parametric factors such as age have already been established, the relationship between voxel-wise spatial distribution of lesions and these factors is not yet well understood. Hence, it would be of clinical importance to model the distribution of lesions at the population-level and quantitatively analyse the effect of various factors on the lesion distribution model. In this work we compare various methods, including our proposed method, to generate voxel-wise distributions of WMH within a population with respect to various factors. Our proposed Bayesian spline method models the spatio-temporal distribution of WMH with respect to a parametric factor of interest, in this case age, within a population. Our probabilistic model takes as input the lesion segmentation binary maps of subjects belonging to various age groups and provides a population-level parametric lesion probability map as output. We used a spline representation to ensure a degree of smoothness in space and the dimension associated with the parameter, and formulated our model using a Bayesian framework. We tested our algorithm output on simulated data and compared our results with those obtained using various existing methods with different levels of algorithmic and computational complexity. We then compared the better performing methods on a real dataset, consisting of 1000 subjects of the UK Biobank, ided in two groups based on hypertension diagnosis. Finally, we applied our method on a clinical dataset of patients with vascular disease. On simulated dataset, the results from our algorithm showed a mean square error (MSE) value of 7.27 × 10 −5 , which was lower than the MSE value reported in the literature, with the advantage of being robust and computationally efficient. In the UK Biobank data, we found that the lesion probabilities are higher for the hypertension group compared to the non-hypertension group and further verified this finding using a statistical t-test. Finally, when applying our method on patients with vascular disease, we observed that the overall probability of lesions is significantly higher in later age groups, which is in line with the current literature.
Publisher: Cold Spring Harbor Laboratory
Date: 23-09-2021
DOI: 10.1101/2021.09.21.21263298
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 (withindataset results), and showed good generalisability across datasets, providing a consistent accuracy of over 80%, even when evaluated across different modalities.
Publisher: Cold Spring Harbor Laboratory
Date: 23-09-2022
DOI: 10.1101/2022.09.22.509002
Abstract: Modelling population reference curves or normative modelling is increasingly used with the advent of large neuroimaging studies. In this paper we assess the performance of fitting methods from the perspective of clinical applications and investigate the influence of the s le size. Further, we evaluate linear and nonlinear models for percentile curve estimation and highlight how the bias-variance trade-off manifests in typical neuroimaging data. We created plausible ground truth distributions of hippoc al volumes in the age range of 45 to 80 years, as an ex le application. Based on these distributions we repeatedly simulated s les for sizes between 50 and 50,000 data points, and for each simulated s le we fitted a range of normative models. We compared the fitted models and their variability across repetitions to the ground truth, with specific focus on the outer percentiles (1 th , 5 th , 10 th ) as these are the most clinically relevant. Our results quantify the expected decreasing trend in variance of the volume estimates with increasing s le size. However, bias in the volume estimates only decreases a modest amount, without much improvement at large s le sizes. The uncertainty of model performance is substantial for what would often be considered large s les in a neuroimaging context and rises dramatically at the ends of the age range, where fewer data points exist. Flexible models perform better across s le sizes, especially for nonlinear ground truth. Surprisingly large s les of several thousand data points are needed to accurately capture outlying percentiles across the age range for applications in research and clinical settings. Performance evaluation methods should assess both, bias and variance. Furthermore, extreme caution is needed when attempting to extrapolate beyond the age range included in the source dataset. To help with such evaluations of normative models we have made our code available to guide researchers developing or utilising normative models.
Publisher: Wiley
Date: 02-08-2023
DOI: 10.1002/HBM.26424
Abstract: In this work we present BIANCA‐MS, a novel tool for brain white matter lesion segmentation in multiple sclerosis (MS), able to generalize across both the wide spectrum of MRI acquisition protocols and the heterogeneity of manually labeled data. BIANCA‐MS is based on the original version of BIANCA and implements two innovative elements: a harmonized setting, tested under different MRI protocols, which avoids the need to further tune algorithm parameters to each dataset and a cleaning step developed to improve consistency in automated and manual segmentations, thus reducing unwanted variability in output segmentations and validation data. BIANCA‐MS was tested on three datasets, acquired with different MRI protocols. First, we compared BIANCA‐MS to other widely used tools. Second, we tested how BIANCA‐MS performs in separate datasets. Finally, we evaluated BIANCA‐MS performance on a pooled dataset where all MRI data were merged. We calculated the overlap using the DICE spatial similarity index (SI) as well as the number of false positive/negative clusters (nFPC/nFNC) in comparison to the manual masks processed with the cleaning step. BIANCA‐MS clearly outperformed other available tools in both high‐ and low‐resolution images and provided comparable performance across different scanning protocols, sets of modalities and image resolutions. BIANCA‐MS performance on the pooled dataset (SI: 0.72 ± 0.25, nFPC: 13 ± 11, nFNC: 4 ± 8) were comparable to those achieved on each in idual dataset (median across datasets SI: 0.72 ± 0.28, nFPC: 14 ± 11, nFNC: 4 ± 8). Our findings suggest that BIANCA‐MS is a robust and accurate approach for automated MS lesion segmentation.
Publisher: Cold Spring Harbor Laboratory
Date: 29-07-2020
DOI: 10.1101/2020.07.28.208579
Abstract: Large scale neuroimaging datasets present the possibility of providing normative distributions for a wide variety of neuroimaging markers, which would vastly improve the clinical utility of these measures. However, a major challenge is our current poor ability to integrate measures across different large-scale datasets, due to inconsistencies in imaging and non-imaging measures across the different protocols and populations. Here we explore the harmonisation of white matter hyperintensity (WMH) measures across two major studies of healthy elderly populations, the Whitehall II imaging sub-study and the UK Biobank. We identify pre-processing strategies that maximise the consistency across datasets and utilise multivariate regression to characterise s le differences contributing to study-level differences in WMH variations. We also present a parser to harmonise WMH-relevant non-imaging variables across the two datasets. We show that we can provide highly calibrated WMH measures from these datasets with: (1) the inclusion of a number of specific standardised processing steps and (2) appropriate modelling of s le differences through the alignment of demographic, cognitive and physiological variables. These results open up a wide range of applications for the study of WMHs and other neuroimaging markers across extensive databases of clinical data. We harmonised measures of WMHs across two studies on healthy ageing Specific pre-processing strategies can increase comparability across studies Modelling of biological differences is crucial to provide calibrated measures
Publisher: Routledge
Date: 27-04-2018
Publisher: Cold Spring Harbor Laboratory
Date: 19-05-2021
DOI: 10.1101/2021.05.19.21257316
Abstract: SARS-CoV-2 infection has been shown to damage multiple organs, including the brain. Multiorgan MRI can provide further insight on the repercussions of COVID-19 on organ health but requires a balance between richness and quality of data acquisition and total scan duration. We adapted the UK Biobank brain MRI protocol to produce high-quality images while being suitable as part of a post-COVID-19 multiorgan MRI exam. The analysis pipeline, also adapted from UK Biobank, includes new imaging-derived phenotypes (IDPs) designed to assess the effects of COVID-19. A first application of the protocol and pipeline was performed in 51 COVID-19 patients post-hospital discharge and 25 controls participating in the Oxford C-MORE study. The protocol acquires high resolution T 1 , T 2 -FLAIR, diffusion weighted images, susceptibility weighted images, and arterial spin labelling data in 17 minutes. The automated imaging pipeline derives 1575 IDPs, assessing brain anatomy (including olfactory bulb volume and intensity) and tissue perfusion, hyperintensities, diffusivity, and susceptibility. In the C-MORE data, these quantitative measures were consistent with clinical radiology reports. Our exploratory analysis tentatively revealed that recovered COVID-19 patients had a decrease in frontal grey matter volumes, an increased burden of white matter hyperintensities, and reduced mean diffusivity in the total and normal appearing white matter in the posterior thalamic radiation and sagittal stratum, relative to controls. These differences were generally more prominent in patients who received organ support. Increased T 2 * in the thalamus was also observed in recovered COVID-19 patients, with a more prominent increase for non-critical patients. This initial evidence of brain changes in COVID-19 survivors prompts the need for further investigations. Follow-up imaging in the C-MORE study is currently ongoing, and this protocol is now being used in large-scale studies. The pipeline is widely applicable and will contribute to new analyses to hopefully clarify the medium to long-term effects of COVID-19. UK Biobank brain MRI protocol and pipeline was adapted for multiorgan MRI of COVID-19 High-quality brain MRI data from 5 modalities are acquired in 17 minutes Analysis pipeline derives 1575 IDPs of brain anatomy, perfusion, and microstructure Evidence of brain changes in COVID-19 survivors was found in the C-MORE study This MRI protocol is now being used in multiple large-scale studies on COVID-19
Publisher: Cold Spring Harbor Laboratory
Date: 08-10-2018
DOI: 10.1101/437608
Abstract: White matter hyperintensities (WMH) or white matter lesions exhibit high variability in their characteristics both at population- and subject-level, making their detection a challenging task. Population-level factors such as age, vascular risk factors and neurode-generative diseases affect lesion load and spatial distribution. At the in idual level, WMH vary in contrast, amount and distribution in different white matter regions. In this work, we aimed to improve BIANCA, the FSL tool for WMH segmentation, in order to better deal with these sources of variability. We worked on two stages of BIANCA by improving the lesion probability map estimation (classification stage) and making the lesion probability map thresholding stage automated and adaptive to local lesion probabilities. Firstly, in order to take into account the effect of population-level factors, we included population-level lesion probabilities, modelled with respect to a parametric factor (e.g. age), in the classification stage. Secondly, we tested BIANCA performance when using four alternative classifiers commonly used in the literature, with respect to K-nearest neighbour algorithm currently used for lesion probability map estimation in BIANCA. Finally, we propose LOCally Adaptive Threshold Estimation (LOCATE), a supervised method for determining optimal local thresholds to apply to the estimated lesion probability map, as an alternative option to global thresholding (i.e. applying the same threshold to the entire lesion probability map). For these experiments we used data from a neurodegenerative cohort and a vascular cohort. We observed that including population-level parametric lesion probabilities with re-spect to age and using alternative machine learning techniques provided negligible im-provement. However, LOCATE provided a substantial improvement in the lesion segmentation performance when compared to the global thresholding currently used in BIANCA. We further validated LOCATE on a cohort of CADASIL (Cerebral autoso-mal dominant arteriopathy with subcortical infarcts and leukoencephalopathy) patients, a genetic form of cerebral small vessel disease characterised by extensive WMH burden, and healthy controls showing that LOCATE adapts well to wide variations in lesion load and spatial distribution.
Publisher: Cold Spring Harbor Laboratory
Date: 24-04-2017
DOI: 10.1101/130385
Abstract: UK Biobank is a large-scale prospective epidemiological study with all data accessible to researchers worldwide. It is currently in the process of bringing back 100,000 of the original participants for brain, heart and body MRI, carotid ultrasound and low-dose bone/fat x-ray. The brain imaging component covers 6 modalities (T1, T2 FLAIR, susceptibility weighted MRI, Resting fMRI, Task fMRI and Diffusion MRI). Raw and processed data from the first 10,000 imaged subjects has recently been released for general research access. To help convert this data into useful summary information we have developed an automated processing and QC (Quality Control) pipeline that is available for use by other researchers. In this paper we describe the pipeline in detail, following a brief overview of UK Biobank brain imaging and the acquisition protocol. We also describe several quantitative investigations carried out as part of the development of both the imaging protocol and the processing pipeline.
Publisher: Springer Science and Business Media LLC
Date: 30-05-2014
Publisher: Cold Spring Harbor Laboratory
Date: 12-03-2021
DOI: 10.1101/2021.03.12.435171
Abstract: Robust automated segmentation of white matter hyperintensities (WMHs) in different datasets (domains) is highly challenging due to differences in acquisition (scanner, sequence), population (WMH amount and location) and limited availability of manual segmentations to train supervised algorithms. In this work we explore various domain adaptation techniques such as transfer learning and domain adversarial learning methods, including domain adversarial neural networks and domain unlearning, to improve the generalisability of our recently proposed triplanar ensemble network, which is our baseline model. We evaluated the domain adaptation techniques on source and target domains consisting of 5 different datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for finetuning in the target domain. On comparing the performance of different techniques on the target dataset, unsupervised domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.
Publisher: Elsevier BV
Date: 03-2023
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Ludovica Griffanti.