Neural correlates of successful emotion recognition in healthy elderly: a multimodal imaging study.

The ageing process is associated with reduced emotional recognition (ER) performance. The ER ability is an essential part of non-verbal communication, and its role is crucial for proper social functioning. Here, using the 'Cambridge Centre for Ageing and Neuroscience cohort sample', we investigated when ER, measured using a facial emotion recognition test, begins to consistently decrease along the lifespan. Moreover, using structural and functional MRI data, we identified the neural correlates associated with ER maintenance in the age groups showing early signs of ER decline (N = 283; age range: 58-89 years). The ER performance was positively correlated with greater volume in the superior parietal lobule, higher white matter integrity in the corpus callosum and greater functional connectivity in the mid-cingulate area. Our results suggest that higher ER accuracy in older people is associated with preserved gray and white matter volumes in cognitive or interconnecting areas, subserving brain regions directly involved in emotional processing.

BIANCA-MS: An optimized tool for automated multiple sclerosis lesion segmentation.

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 individual 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.

Oxford brain health clinic: protocol and research database.

INTRODUCTION: Despite major advances in the field of neuroscience over the last three decades, the quality of assessments available to patients with memory problems in later life has barely changed. At the same time, a large proportion of dementia biomarker research is conducted in selected research samples that often poorly reflect the demographics of the population of patients who present to memory clinics. The Oxford Brain Health Clinic (BHC) is a newly developed clinical assessment service with embedded research in which all patients are offered high-quality clinical and research assessments, including MRI, as standard. METHODS AND ANALYSIS: Here we describe the BHC protocol, including aligning our MRI scans with those collected in the UK Biobank. We evaluate rates of research consent for the first 108 patients (data collection ongoing) and the ability of typical psychiatry-led NHS memory-clinic patients to tolerate both clinical and research assessments. ETHICS AND DISSEMINATION: Our ethics and consenting process enables patients to choose the level of research participation that suits them. This generates high rates of consent, enabling us to populate a research database with high-quality data that will be disseminated through a national platform (the Dementias Platform UK data portal).

Automated detection of cerebral microbleeds on MR images using knowledge distillation framework.

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.

Shared imaging markers of fatigue across multiple sclerosis, aquaporin-4 antibody neuromyelitis optica spectrum disorder and MOG antibody disease.

Fatigue is frequently reported by patients with multiple sclerosis, aquaporin-4-antibody neuromyelitis optica spectrum disorder and myelin-oligodendrocyte-glycoprotein antibody disease; thus they could share a similar pathophysiological mechanism. In this cross-sectional cohort study, we assessed the association of fatigue with resting-state functional MRI, diffusion and structural imaging measures across these three disorders. Sixteen patients with multiple sclerosis, 17 with aquaporin-4-antibody neuromyelitis optica spectrum disorder and 17 with myelin-oligodendrocyte-glycoprotein antibody disease assessed, outside of relapses, at the Oxford Neuromyelitis Optica Service underwent Modified Fatigue Impact Scale, Hospital Anxiety and Depression Scale and Expanded Disability Status Scale scoring. A 3T brain and spinal cord MRI was used to derive cortical, deep grey and white matter volumetrics, lesions volume, fractional anisotropy, brain functional connectivity metrics, cervical spinal cord cross-sectional area, spinal cord magnetic transfer ratio and average functional connectivity between the ventral and the dorsal horns of the cervical cord. Linear relationships between MRI measures and total-, cognitive- and physical-fatigue scores were assessed. All analyses were adjusted for correlated clinical regressors. No significant differences in baseline clinical characteristics, fatigue, depression and anxiety questionnaires and disability measures were seen across the three diseases, except for older age in patients with aquaporin-4-antibody neuromyelitis optica spectrum disorder (P = 0.0005). In the total cohort, median total-fatigue score was 35.5 (range 3-72), and 42% of patients were clinically fatigued. A positive correlation existed between the total-fatigue score and functional connectivity of the executive/fronto-temporal network in the in left middle temporal gyrus (P = 0.033) and between the physical-fatigue score and functional connectivity of the sensory-motor network (P = 0.032) in both pre- and post-central gyri. A negative relationship was found between the total-fatigue score and functional connectivity of the salience network (P = 0.023) and of the left fronto-parietal network (P = 0.026) in the right supramarginal gyrus and left superior parietal lobe. No clear relationship between fatigue subscores and the average functional connectivity of the spinal cord was found. Cognitive-fatigue scores were positively associated with white matter lesion volume (P = 0.018) and negatively associated with white matter fractional anisotropy (P = 0.032). Structural, diffusion and functional connectivity alterations were not influenced by the disease group. Functional and structural imaging metrics associated with fatigue relate to brain rather than spinal cord abnormalities. Salience and sensory-motor networks alterations in relation to fatigue might indicate a disconnection between the perception of the interior body state and activity and the actual behavioural responses and performances (reversible or irreversible). Future research should focus on functional rehabilitative strategies.

A comparison of lesion mapping analyses based on CT versus MR imaging in stroke.

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 significant variance in location, overlap, and size. In ROI-level simulations, both CT and MRI-derived analyses yielded low Dice similarity coefficients, but CT analyses yielded a significantly higher proportion of results which overlapped with target ROIs. 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 moderate agreement in terms of Dice coefficient when systematic differences in cluster size and lesion overlay are considered. Overall, these results suggest that CT and MR-derived lesion-symptom mapping results do not reliably differ in accuracy. This finding is critically important as it suggests that future studies can employ CT-derived lesion masks if these scans are available within the appropriate time-window.

Normative models for neuroimaging markers: Impact of model selection, sample size and evaluation criteria.

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 sample size. Further, we evaluate linear and non-linear 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 hippocampal volumes in the age range of 45 to 80 years, as an example application. Based on these distributions we repeatedly simulated samples for sizes between 50 and 50,000 data points, and for each simulated sample 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 (1st, 5th, 10th) as these are the most clinically relevant. Our results quantify the expected decreasing trend in variance of the volume estimates with increasing sample size. However, bias in the volume estimates only decreases a modest amount, without much improvement at large sample sizes. The uncertainty of model performance is substantial for what would often be considered large samples in a neuroimaging context and rises dramatically at the ends of the age range, where fewer data points exist. Flexible models perform better across sample sizes, especially for non-linear ground truth. Surprisingly large samples 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, caution is needed when attempting to go near the ends of the age range captured by the source data set and, as is a well known general principle, extrapolation beyond the age range should always be avoided. To help with such evaluations of normative models we have made our code available to guide researchers developing or utilising normative models.

Adapting UK Biobank imaging for use in a routine memory clinic setting: The Oxford Brain Health Clinic.

The Oxford Brain Health Clinic (BHC) is a joint clinical-research service that provides memory clinic patients and clinicians access to high-quality assessments not routinely available, including brain MRI aligned with the UK Biobank imaging study (UKB). In this work we present how we 1) adapted the UKB MRI acquisition protocol to be suitable for memory clinic patients, 2) modified the imaging analysis pipeline to extract measures that are in line with radiology reports and 3) explored the alignment of measures from BHC patients to the largest brain MRI study in the world (ultimately 100,000 participants). Adaptations of the UKB acquisition protocol for BHC patients include dividing the scan into core and optional sequences (i.e., additional imaging modalities) to improve patients' tolerance for the MRI assessment. We adapted the UKB structural MRI analysis pipeline to take into account the characteristics of a memory clinic population (e.g., high amount of white matter hyperintensities and hippocampal atrophy). We then compared the imaging derived phenotypes (IDPs) extracted from the structural scans to visual ratings from radiology reports, non-imaging factors (age, cognition) and to reference distributions derived from UKB data. Of the first 108 BHC attendees (August 2020-November 2021), 92.5 % completed the clinical scans, 88.0 % consented to use of data for research, and 43.5 % completed the additional research sequences, demonstrating that the protocol is well tolerated. The high rates of consent to research makes this a valuable real-world quality research dataset routinely captured in a clinical service. Modified tissue-type segmentation with lesion masking greatly improved grey matter volume estimation. CSF-masking marginally improved hippocampal segmentation. The IDPs were in line with radiology reports and showed significant associations with age and cognitive performance, in line with the literature. Due to the age difference between memory clinic patients of the BHC (age range 65-101 years, average 78.3 years) and UKB participants (44-82 years, average 64 years), additional scans on elderly healthy controls are needed to improve reference distributions. Current and future work aims to integrate automated quantitative measures in the radiology reports and evaluate their clinical utility.

Reliability of multi-site UK Biobank MRI brain phenotypes for the assessment of neuropsychiatric complications of SARS-CoV-2 infection: The COVID-CNS travelling heads study.

INTRODUCTION: Magnetic resonance imaging (MRI) of the brain could be a key diagnostic and research tool for understanding the neuropsychiatric complications of COVID-19. For maximum impact, multi-modal MRI protocols will be needed to measure the effects of SARS-CoV-2 infection on the brain by diverse potentially pathogenic mechanisms, and with high reliability across multiple sites and scanner manufacturers. Here we describe the development of such a protocol, based upon the UK Biobank, and its validation with a travelling heads study. A multi-modal brain MRI protocol comprising sequences for T1-weighted MRI, T2-FLAIR, diffusion MRI (dMRI), resting-state functional MRI (fMRI), susceptibility-weighted imaging (swMRI), and arterial spin labelling (ASL), was defined in close approximation to prior UK Biobank (UKB) and C-MORE protocols for Siemens 3T systems. We iteratively defined a comparable set of sequences for General Electric (GE) 3T systems. To assess multi-site feasibility and between-site variability of this protocol, N = 8 healthy participants were each scanned at 4 UK sites: 3 using Siemens PRISMA scanners (Cambridge, Liverpool, Oxford) and 1 using a GE scanner (King's College London). Over 2,000 Imaging Derived Phenotypes (IDPs), measuring both data quality and regional image properties of interest, were automatically estimated by customised UKB image processing pipelines (S2 File). Components of variance and intra-class correlations (ICCs) were estimated for each IDP by linear mixed effects models and benchmarked by comparison to repeated measurements of the same IDPs from UKB participants. Intra-class correlations for many IDPs indicated good-to-excellent between-site reliability. Considering only data from the Siemens sites, between-site reliability generally matched the high levels of test-retest reliability of the same IDPs estimated in repeated, within-site, within-subject scans from UK Biobank. Inclusion of the GE site resulted in good-to-excellent reliability for many IDPs, although there were significant between-site differences in mean and scaling, and reduced ICCs, for some classes of IDP, especially T1 contrast and some dMRI-derived measures. We also identified high reliability of quantitative susceptibility mapping (QSM) IDPs derived from swMRI images, multi-network ICA-based IDPs from resting-state fMRI, and olfactory bulb structure IDPs from T1, T2-FLAIR and dMRI data. CONCLUSION: These results give confidence that large, multi-site MRI datasets can be collected reliably at different sites across the diverse range of MRI modalities and IDPs that could be mechanistically informative in COVID brain research. We discuss limitations of the study and strategies for further harmonisation of data collected from sites using scanners supplied by different manufacturers. These acquisition and analysis protocols are now in use for MRI assessments of post-COVID patients (N = 700) as part of the ongoing COVID-CNS study.

Identifying microstructural changes in diffusion MRI; How to circumvent parameter degeneracy.

Biophysical models that attempt to infer real-world quantities from data usually have many free parameters. This over-parameterisation can result in degeneracies in model inversion and render parameter estimation ill-posed. However, in many applications, we are not interested in quantifying the parameters per se, but rather in identifying changes in parameters between experimental conditions (e.g. patients vs controls). Here we present a Bayesian framework to make inference on changes in the parameters of biophysical models even when model inversion is degenerate, which we refer to as Bayesian EstimatioN of CHange (BENCH). We infer the parameter changes in two steps; First, we train models that can estimate the pattern of change in the measurements given any hypothetical direction of change in the parameters using simulations. Next, for any pair of real data sets, we use these pre-trained models to estimate the probability that an observed difference in the data can be explained by each model of change. BENCH is applicable to any type of data and models and particularly useful for biophysical models with parameter degeneracies, where we can assume the change is sparse. In this paper, we apply the approach in the context of microstructural modelling of diffusion MRI data, where the models are usually over-parameterised and not invertible without injecting strong assumptions. Using simulations, we show that in the context of the standard model of white matter our approach is able to identify changes in microstructural parameters from conventional multi-shell diffusion MRI data. We also apply our approach to a subset of subjects from the UK-Biobank Imaging to identify the dominant standard model parameter change in areas of white matter hyperintensities under the assumption that the standard model holds in white matter hyperintensities.

SARS-CoV-2 is associated with changes in brain structure in UK Biobank.

There is strong evidence of brain-related abnormalities in COVID-191-13. However, it remains unknown whether the impact of SARS-CoV-2 infection can be detected in milder cases, and whether this can reveal possible mechanisms contributing to brain pathology. Here we investigated brain changes in 785 participants of UK Biobank (aged 51-81 years) who were imaged twice using magnetic resonance imaging, including 401 cases who tested positive for infection with SARS-CoV-2 between their two scans-with 141 days on average separating their diagnosis and the second scan-as well as 384 controls. The availability of pre-infection imaging data reduces the likelihood of pre-existing risk factors being misinterpreted as disease effects. We identified significant longitudinal effects when comparing the two groups, including (1) a greater reduction in grey matter thickness and tissue contrast in the orbitofrontal cortex and parahippocampal gyrus; (2) greater changes in markers of tissue damage in regions that are functionally connected to the primary olfactory cortex; and (3) a greater reduction in global brain size in the SARS-CoV-2 cases. The participants who were infected with SARS-CoV-2 also showed on average a greater cognitive decline between the two time points. Importantly, these imaging and cognitive longitudinal effects were still observed after excluding the 15 patients who had been hospitalised. These mainly limbic brain imaging results may be the in vivo hallmarks of a degenerative spread of the disease through olfactory pathways, of neuroinflammatory events, or of the loss of sensory input due to anosmia. Whether this deleterious effect can be partially reversed, or whether these effects will persist in the long term, remains to be investigated with additional follow-up.

Adults with tetralogy of Fallot show specific features of cerebral small vessel disease: the BACH San Donato study.

Life expectancy in adults with congenital heart disease (ACHD) has increased. As these patients grow older, they experience aging-related diseases more than their healthy peers. To better characterize this field, we launched the multi-disciplinary BACH (Brain Aging in Congenital Heart disease) San Donato study, that aimed at investigating signs of brain injury in ACHD. Twenty-three adults with repaired tetralogy of Fallot and 23 age- and sex-matched healthy controls were prospectively recruited and underwent brain magnetic resonance imaging. White matter hyperintensities (WMHs) were segmented using a machine-learning approach and automatically split into periventricular and deep. Cerebral microbleeds were manually counted. A subset of 14 patients were also assessed with an extensive neuropsychological battery. Age was 41.78 ± 10.33 years (mean ± standard deviation) for patients and 41.48 ± 10.28 years for controls (p = 0.921). Albeit not significantly, total brain (p = 0.282) and brain tissue volumes (p = 0.539 for cerebrospinal fluid, p = 0.661 for grey matter, p = 0.793 for white matter) were lower in ACHD, while total volume (p = 0.283) and sub-classes of WMHs (p = 0.386 for periventricular WMHs and p = 0.138 for deep WMHs) were higher in ACHD than in controls. Deep WMHs were associated with poorer performance at the frontal assessment battery (r = -0.650, p = 0.012). Also, patients had a much larger number of microbleeds than controls (median and interquartile range 5 [3-11] and 0 [0-0] respectively; p < 0.001). In this study, adults with tetralogy of Fallot showed specific signs of brain injury, with some clinical implications. Eventually, accurate characterization of brain health using neuroimaging and neuropsychological data would aid in the identification of ACHD patients at risk of cognitive deterioration.

Mapping brain structural differences and neuroreceptor correlates in Parkinson's disease visual hallucinations.

Parkinson's psychosis (PDP) describes a spectrum of symptoms that may arise in Parkinson's disease (PD) including visual hallucinations (VH). Imaging studies investigating the neural correlates of PDP have been inconsistent in their findings, due to differences in study design and limitations of scale. Here we use empirical Bayes harmonisation to pool together structural imaging data from multiple research groups into a large-scale mega-analysis, allowing us to identify cortical regions and networks involved in VH and their relation to receptor binding. Differences of morphometrics analysed show a wider cortical involvement underlying VH than previously recognised, including primary visual cortex and surrounding regions, and the hippocampus, independent of its role in cognitive decline. Structural covariance analyses point to the involvement of the attentional control networks in PD-VH, while associations with receptor density maps suggest neurotransmitter loss may be linked to the cortical changes.

Association of cerebral small vessel disease burden with brain structure and cognitive and vascular risk trajectories in mid-to-late life.

We characterize the associations of total cerebral small vessel disease (SVD) burden with brain structure, trajectories of vascular risk factors, and cognitive functions in mid-to-late life. Participants were 623 community-dwelling adults from the Whitehall II Imaging Sub-study with multi-modal MRI (mean age 69.96, SD = 5.18, 79% men). We used linear mixed-effects models to investigate associations of SVD burden with up to 25-year retrospective trajectories of vascular risk and cognitive performance. General linear modelling was used to investigate concurrent associations with grey matter (GM) density and white matter (WM) microstructure, and whether these associations were modified by cognitive status (Montreal Cognitive Asessment [MoCA] scores of < 26 vs. ≥ 26). Severe SVD burden in older age was associated with higher mean arterial pressure throughout midlife (ß = 3.36, 95% CI [0.42-6.30]), and faster cognitive decline in letter fluency (ß = -0.07, 95% CI [-0.13--0.01]), and verbal reasoning (ß = -0.05, 95% CI [-0.11--0.001]). Moreover, SVD burden was related to lower GM volumes in 9.7% of total GM, and widespread WM microstructural decline (FWE-corrected p < 0.05). The latter association was most pronounced in individuals who demonstrated cognitive impairments on MoCA (MoCA < 26; F3,608 = 2.14, p = 0.007). These findings highlight the importance of managing midlife vascular health to preserve brain structure and cognitive function in old age.

SARS-CoV-2 is associated with changes in brain structure in UK Biobank.

There is strong evidence for brain-related abnormalities in COVID-19 1-13 . It remains unknown however whether the impact of SARS-CoV-2 infection can be detected in milder cases, and whether this can reveal possible mechanisms contributing to brain pathology. Here, we investigated brain changes in 785 UK Biobank participants (aged 51-81) imaged twice, including 401 cases who tested positive for infection with SARS-CoV-2 between their two scans, with 141 days on average separating their diagnosis and second scan, and 384 controls. The availability of pre-infection imaging data reduces the likelihood of pre-existing risk factors being misinterpreted as disease effects. We identified significant longitudinal effects when comparing the two groups, including: (i) greater reduction in grey matter thickness and tissue-contrast in the orbitofrontal cortex and parahippocampal gyrus, (ii) greater changes in markers of tissue damage in regions functionally-connected to the primary olfactory cortex, and (iii) greater reduction in global brain size. The infected participants also showed on average larger cognitive decline between the two timepoints. Importantly, these imaging and cognitive longitudinal effects were still seen after excluding the 15 cases who had been hospitalised. These mainly limbic brain imaging results may be the in vivo hallmarks of a degenerative spread of the disease via olfactory pathways, of neuroinflammatory events, or of the loss of sensory input due to anosmia. Whether this deleterious impact can be partially reversed, or whether these effects will persist in the long term, remains to be investigated with additional follow up.

Intrinsic network activity reflects the ongoing experience of chronic pain.

Analyses of intrinsic network activity have been instrumental in revealing cortical processes that are altered in chronic pain patients. In a novel approach, we aimed to elucidate how intrinsic functional networks evolve in regard to the fluctuating intensity of the experience of chronic pain. In a longitudinal study with 156 fMRI sessions, 20 chronic back pain patients and 20 chronic migraine patients were asked to continuously rate the intensity of their endogenous pain. We investigated the relationship between the fluctuation of intrinsic network activity with the time course of subjective pain ratings. For chronic back pain, we found increased cortical network activity for the salience network and a local pontine network, as well as decreased network activity in the anterior and posterior default mode network for higher pain intensities. Higher pain intensities in chronic migraine were accompanied with lower activity in a prefrontal cortical network. By taking the perspective of the individual, we focused on the variability of the subjective perception of pain, which include phases of relatively low pain and phases of relatively high pain. The present design of the assessment of ongoing endogenous pain can be a powerful and promising tool to assess the signature of a patient's endogenous pain encoding.

Adapting the UK Biobank Brain Imaging Protocol and Analysis Pipeline for the C-MORE Multi-Organ Study of COVID-19 Survivors.

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 possible 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 T1, T2-FLAIR, diffusion weighted images, susceptibility weighted images, and arterial spin labelling data in 17 min. The automated imaging pipeline derives 1,575 IDPs, assessing brain anatomy (including olfactory bulb volume and intensity) and tissue perfusion, hyperintensities, diffusivity, and susceptibility. In the C-MORE data, IDPs related to atrophy, small vessel disease and olfactory bulbs were consistent with clinical radiology reports. Our exploratory analysis tentatively revealed some group differences between recovered COVID-19 patients and controls, across severity groups, but not across anosmia groups. Follow-up imaging in the C-MORE study is currently ongoing, and this protocol is now being used in other large-scale studies. The protocol, pipeline code and data are openly available and will further contribute to the understanding of the medium to long-term effects of COVID-19.

Comparison of domain adaptation techniques for white matter hyperintensity segmentation in brain MR images.

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 used datasets with variations in intensity profile, lesion characteristics and acquired using different scanners. For the source domain, we considered a dataset consisting of data acquired from 3 different scanners, while the target domain consisted of 2 datasets. We evaluated the domain adaptation techniques on the target domain datasets, and additionally evaluated the performance on the source domain test dataset for the adversarial techniques. For transfer learning, we also studied various training options such as minimal number of unfrozen layers and subjects required for fine-tuning in the target domain. On comparing the performance of different techniques on the target dataset, domain adversarial training of neural network gave the best performance, making the technique promising for robust WMH segmentation.

Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images.

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. In the loss functions the network uses anatomical information regarding WMH spatial distribution in loss functions, to improve 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, and we also submitted our method to MWSC 2017 to be evaluated on the unseen test datasets. 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 methods of MWSC 2017.