Search

Machine learning (ML) methodologies for detecting Mild Cognitive Impairment (MCI) are progressively gaining prevalence to manage the vast volume of processed information. Nevertheless, the black-box nature of ML algorithms and the heterogeneity within the data may result in varied interpretations across distinct studies. To avoid this, in this proposal, we present the design of a decision support system that integrates a machine learning model represented using the Semantic Web Rule Language (SWRL) in an ontology with specialized knowledge in neuropsychological tests, the NIO ontology. The system’s ability to detect MCI subjects was evaluated on a database of 520 neuropsychological assessments conducted in Spanish and compared with other well-established ML methods. Using the F2 coefficient to minimize false negatives, results indicate that the system performs similarly to other well-established ML methods (F2TE2 = 0.830, only below bagging, F2BAG = 0.832) while exhibiting other significant attributes such as explanation capability and data standardization to a common framework thanks to the ontological part. On the other hand, the system’s versatility and ease of use were demonstrated with three additional use cases: evaluation of new cases even if the acquisition stage is incomplete (the case records have missing values), incorporation of a new database into the integrated system, and use of the ontology capabilities to relate different domains. This makes it a useful tool to support physicians and neuropsychologists in population-based screenings for early detection of MCI.

Abstract Staging amyloid-beta (Aβ) pathophysiology according to the intensity of neurodegeneration could identify individuals at risk for cognitive decline in Alzheimer’s disease (AD). In blood, phosphorylated tau (p-tau) associates with Aβ pathophysiology but an AD-type neurodegeneration biomarker has been lacking. In this multicenter study (n = 1076), we show that brain-derived tau (BD-tau) in blood increases according to concomitant Aβ (“A”) and neurodegeneration (“N”) abnormalities (determined using cerebrospinal fluid biomarkers); We used blood-based A/N biomarkers to profile the participants in this study; individuals with blood-based p-tau+/BD-tau+ profiles had the fastest cognitive decline and atrophy rates, irrespective of the baseline cognitive status. Furthermore, BD-tau showed no or much weaker correlations with age, renal function, other comorbidities/risk factors and self-identified race/ethnicity, compared with other blood biomarkers. Here we show that blood-based BD-tau is a biomarker for identifying Aβ-positive individuals at risk of short-term cognitive decline and atrophy, with implications for clinical trials and implementation of anti-Aβ therapies.

Standard treatment of patients with glioblastoma includes surgical resection of the tumor. The extent of resection (EOR) achieved during surgery significantly impacts prognosis and is used to stratify patients in clinical trials. In this study, we developed a U-Net-based deep-learning model to segment contrast-enhancing tumor on post-operative MRI exams taken within 72 h of resection surgery and used these segmentations to classify the EOR as either maximal or submaximal. The model was trained on 122 multiparametric MRI scans from our institution and achieved a mean Dice score of 0.52 ± 0.03 on an external dataset (n = 248), a performance ­on par with the interrater agreement between expert annotators as reported in literature. We obtained an EOR classification precision/recall of 0.72/0.78 on the internal test dataset (n = 462) and 0.90/0.87 on the external dataset. Furthermore, Kaplan-Meier curves were used to compare the overall survival between patients with maximal and submaximal resection in the internal test dataset, as determined by either clinicians or the model. There was no significant difference between the survival predictions using the model's and clinical EOR classification. We find that the proposed segmentation model is capable of reliably classifying the EOR of glioblastoma tumors on early post-operative MRI scans. Moreover, we show that stratification of patients based on the model's predictions offers at least the same prognostic value as when done by clinicians.

Abstract Background Main aim was assessment of regional blood–brain barrier (BBB) function by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in patients with neuroborreliosis. Secondary aim was to study the correlation of BBB function with biochemical, clinical, and cognitive parameters. Methods Regional ethical committee approved this prospective single-center case–control study. Within 1 month after diagnosis of neuroborreliosis, 55 patients underwent DCE-MRI. The patient group consisted of 25 males and 30 females with mean age 58 years, and the controls were 8 males and 7 females with mean age 57 years. Pharmacokinetic compartment modelling with Patlak fit was applied, providing estimates for capillary leakage rate and blood volume fraction. Nine anatomical brain regions were sampled with auto-generated binary masks. Fatigue, severity of clinical symptoms and findings, and cognitive function were assessed in the acute phase and 6 months after treatment. Results Leakage rates and blood volume fractions were lower in patients compared to controls in the thalamus (p = 0.027 and p = 0.018, respectively), caudate nucleus (p = 0.009 for both), and hippocampus (p = 0.054 and p = 0.009). No correlation of leakage rates with fatigue, clinical disease severity or cognitive function was found. Conclusions In neuroborreliosis, leakage rate and blood volume fraction in the thalamus, caudate nucleus, and hippocampus were lower in patients compared to controls. DCE-MRI provided new insight to pathophysiology of neuroborreliosis, and can serve as biomarker of BBB function and regulatory mechanisms of the neurovascular unit in infection and inflammation. Relevance statement DCE-MRI provided new insight to pathophysiology of neuroborreliosis, and can serve as biomarker of blood–brain barrier function and regulatory mechanisms of the neurovascular unit in infection and inflammation. Key points • Neuroborreliosis is an infection with disturbed BBB function. • Microvessel leakage can be studied with DCE-MRI. • Prospective case–control study showed altered microvessel properties in thalamus, caudate, and hippocampus. Graphical Abstract

Introduction Loss of blood-brain barrier (BBB) integrity is hypothesised to be one of the earliest microvascular signs of Alzheimer’s disease (AD). Existing BBB integrity imaging methods involve contrast agents or ionising radiation, and pose limitations in terms of cost and logistics. Arterial spin labelling (ASL) perfusion MRI has been recently adapted to map the BBB permeability non-invasively. The DEveloping BBB-ASL as a non-Invasive Early biomarker (DEBBIE) consortium aims to develop this modified ASL-MRI technique for patient-specific and robust BBB permeability assessments. This article outlines the study design of the DEBBIE cohorts focused on investigating the potential of BBB-ASL as an early biomarker for AD (DEBBIE-AD).Methods and analysis DEBBIE-AD consists of a multicohort study enrolling participants with subjective cognitive decline, mild cognitive impairment and AD, as well as age-matched healthy controls, from 13 cohorts. The precision and accuracy of BBB-ASL will be evaluated in healthy participants. The clinical value of BBB-ASL will be evaluated by comparing results with both established and novel AD biomarkers. The DEBBIE-AD study aims to provide evidence of the ability of BBB-ASL to measure BBB permeability and demonstrate its utility in AD and AD-related pathologies.Ethics and dissemination Ethics approval was obtained for 10 cohorts, and is pending for 3 cohorts. The results of the main trial and each of the secondary endpoints will be submitted for publication in a peer-reviewed journal.

IntroductionEfforts to develop cost-effective approaches for detecting amyloid pathology in Alzheimer's disease (AD) have gained significant momentum with a focus on biomarker classification. Recent research has explored non-invasive and readily accessible biomarkers, including magnetic resonance imaging (MRI) biomarkers and some AD risk factors.MethodsIn this comprehensive study, we leveraged a diverse dataset, encompassing participants with varying cognitive statuses from multiple sources, including cohorts from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and our in-house Dementia Disease Initiation (DDI) cohort. As brain amyloid plaques have been proposed as sufficient for AD diagnosis, our primary aim was to assess the effectiveness of multimodal biomarkers in identifying amyloid plaques, using deep machine learning methodologies.ResultsOur findings underscore the robustness of the utilized methods in detecting amyloid beta positivity across multiple cohorts. Additionally, we investigated the potential of demographic data to enhance MRI-based amyloid detection. Notably, the inclusion of demographic risk factors significantly improved our models' ability to detect amyloid-beta positivity, particularly in early-stage cases, exemplified by an average area under the ROC curve of 0.836 in the unimpaired DDI cohort.DiscussionThese promising, non-invasive, and cost-effective predictors of MRI biomarkers and demographic variables hold the potential for further refinement through considerations like APOE genotype and plasma markers.

Introduction: The link between neurodegenerative disease and stroke is well established and there is a need to understand pre-morbid brain anatomy to explain between-subject differences. Ventricular volume is one robust biomarker of neurodegeneration. Given the clinical dominance of Computed Tomography head scans, this study has the following aims:Aim-1: Test whether an automated lateral ventricle volume estimate from head CT will correlate with pre-stroke modified Rankin Scale (mRS); Aim-2: Determine if the CT-based lateral ventricle volume estimate is independently associated with cognitive performance post-stroke using the Trails A and B test scores. Methods: A total of N= 532 stroke (482 ischaemic and 61 hemorrhagic) participants were accessed from the Nor-COAST study across 5 stroke centres. Using an external data source of N=89 head CT scans, a deep learning neural network was trained to segment the lateral ventricles based on a 3- dimensional no-new U-Net architecture (data not shown). The lateral ventricle segmentation tool was tested, validated, and then applied for use on Nor-COAST data. In Aim 1, we tested for an association between lateral ventricle volume (dependent variable) and demographic and select stroke clinical variables in a regression model. Two other regression models (Aim 2A & 2B) were performed: we tested whether Trails A and Trails B completion times were associated with lateral ventricle volume after accounting for age, sex, education, and pre-stroke mRS. Results: Aim-1: we found that increased ventricle volume was associated with pre-stroke mRS. Sex and hemorrhage status were also corrected with ventricle volume, while age and diabetes status were not (adjusted R-squared=0.09, 525 degrees of freedom [df]).Aim-2A: Trails A was associated with ventricle volume, as well as age, education, and pre-stroke mRS, while sex was not (adj-R-squared=0.25 with df=398).Aim-2B: Trails B score was associated with lateral ventricle volume, with similar influences from covariates as Aim-2A (adj-R-squared=0.32 with df=290). Discussion: This study provides evidence that automated volumetric lateral ventricle assessment can be incorporated into analyses that characterise pre-stroke impairment and post-stroke cognitive performance.

Introduction: Alzheimer's disease (AD) and cerebral small vessel disease (SVD) frequently coexist, and increasing evidence suggest that microvascular changes may be related to AD pathology. SVD is however heterogeneously expressed on magnetic resonance imaging (MRI), and several novel methods can determine different aspects of vascular pathology. These methods need to be explored properly in clinical AD cohorts to better understand the link between AD and SVD, and could possibly be included in the staging and diagnostics of AD. Methods: 588 subjects were included from the Norwegian Dementia Disease initiation (DDI) cohort, longitudinal data was available for 285 subjects. Subjects underwent clinical examination including lumbar puncture, and were classified according to the A/T/N-system into the following groups: A-/T-/N- (N=208), A-/T+/N± (N=11), A+/T-/N- (N=75)and A+/T+/N±(N=157) according to positive (+) or negative (-) values of cerebrospinal fluid (CSF) amyloid-β42/40-ratio (A), phosphorylated-tau (T) and total-tau (N)). We used Peak width of skeletonized mean diffusivity (PSMD), a novel MRI Diffusion Tensor Imaging (DTI) method for determination of global SVD-burden based on an automated algorithm (5). We used a mixed linear regression model to determine baseline and longitudinal differences in PSMD across A/T/N-classified subjects in a predementia cohort, adjusted for subject and scanner as a random effect. Results: Compared to A-/T-/N- at baseline, we found significantly larger SVD burden in A+/T-/N- compared to A-/T-/N- (p

IntroductionRadiological assessment is necessary to diagnose spontaneous intracerebral hemorrhage (ICH) and traumatic brain injury intracranial hemorrhage (TBI-bleed). Artificial intelligence (AI) deep learning tools provide a means for decision support. This study evaluates the hemorrhage segmentations produced from three-dimensional deep learning AI model that was developed using non-contrast computed tomography (CT) imaging data external to the current study.MethodsNon-contrast CT imaging data from 1263 patients were accessed across seven data sources (referred to as sites) in Norway and Sweden. Patients were included based on ICH, TBI-bleed, or mild TBI diagnosis. Initial non-contrast CT images were available for all participants. Hemorrhage location frequency maps were generated. The number of estimated haematoma clusters was correlated with the total haematoma volume. Ground truth expert annotations were available for one ICH site; hence, a comparison was made with the estimated haematoma volumes. Segmentation volume estimates were used in a receiver operator characteristics (ROC) analysis for all samples (i.e., bleed detected) and then specifically for one site with few TBI-bleed cases.ResultsThe hemorrhage frequency maps showed spatial patterns of estimated lesions consistent with ICH or TBI-bleed presentations. There was a positive correlation between the estimated number of clusters and total haematoma volume for each site (correlation range: 0.45–0.74; each p-value < 0.01) and evidence of ICH between-site differences. Relative to hand-drawn annotations for one ICH site, the VIOLA-AI segmentation mask achieved a median Dice Similarity Coefficient of 0.82 (interquartile range: 0.78 and 0.83), resulting in a small overestimate in the haematoma volume by a median of 0.47 mL (interquartile range: 0.04 and 1.75 mL). The bleed detection ROC analysis for the whole sample gave a high area-under-the-curve (AUC) of 0.92 (with sensitivity and specificity of 83.28% and 95.41%); however, when considering only the mild head injury site, the TBI-bleed detection gave an AUC of 0.70.DiscussionAn open-source segmentation tool was used to visualize hemorrhage locations across multiple data sources and revealed quantitative hemorrhage site differences. The automated total hemorrhage volume estimate correlated with a per-participant hemorrhage cluster count. ROC results were moderate-to-high. The VIOLA-AI tool had promising results and might be useful for various types of intracranial hemorrhage.

Abstract Cortical microstructure is influenced by circadian rhythm and sleep deprivation, yet the precise underpinnings of these effects remain unclear. The ratio between T1-weighted and T2-weighted magnetic resonance images (T1w/T2w ratio) has been linked to myelin levels and dendrite density and may offer novel insight into the intracortical microstructure of the sleep deprived brain. Here, we examined intracortical T1w/T2w ratio in 41 healthy young adults (26 women) before and after 32 h of either sleep deprivation (n = 18) or a normal sleep-wake cycle (n = 23). Linear models revealed significant group differences in T1w/T2w ratio change after 32 h in four clusters, including bilateral effects in the insular, cingulate, and superior temporal cortices, comprising regions involved in attentional, auditory and pain processing. Across clusters, the sleep deprived group showed an increased T1w/T2w ratio, while the normal sleep-wake group exhibited a reduced ratio. These changes were not explained by in-scanner head movement, and 95% of the effects across clusters remained significant after adjusting for cortical thickness and hydration. Compared with a normal sleep-wake cycle, 32 h of sleep deprivation yields intracortical T1w/T2w ratio increases. While the intracortical changes detected by this study could reflect alterations in myelin or dendritic density, or both, histological analyses are needed to clarify the precise underlying cortical processes.

An important step in the analysis of magnetic resonance imaging (MRI) data for neuroimaging is the automated segmentation of white matter hyperintensities (WMHs). Fluid Attenuated Inversion Recovery (FLAIR-weighted) is an MRI contrast that is particularly useful to visualize and quantify WMHs, a hallmark of cerebral small vessel disease and Alzheimer's disease (AD). In order to achieve high spatial resolution in each of the three voxel dimensions, clinical MRI protocols are evolving to a three-dimensional (3D) FLAIR-weighted acquisition. The current study details the deployment of deep learning tools to enable automated WMH segmentation and characterization from 3D FLAIR-weighted images acquired as part of a national AD imaging initiative. Based on data from the ongoing Norwegian Disease Dementia Initiation (DDI) multicenter study, two 3D models-one off-the-shelf from the NVIDIA nnU-Net framework and the other internally developed-were trained, validated, and tested. A third cutting-edge Deep Bayesian network model (HyperMapp3r) was implemented without any de-novo tuning to serve as a comparison architecture. The 2.5D in-house developed and 3D nnU-Net models were trained and validated in-house across five national collection sites among 441 participants from the DDI study, of whom 194 were men and whose average age was (64.91 +/- 9.32) years. Both an external dataset with 29 cases from a global collaborator and a held-out subset of the internal data from the 441 participants were used to test all three models. These test sets were evaluated independently. The ground truth human-in-the-loop segmentation was compared against five established WMH performance metrics. The 3D nnU-Net had the highest performance out of the three tested networks, outperforming both the internally developed 2.5D model and the SOTA Deep Bayesian network with an average dice similarity coefficient score of 0.76 +/- 0.16. Our findings demonstrate that WMH segmentation models can achieve high performance when trained exclusively on FLAIR input volumes that are 3D volumetric acquisitions. Single image input models are desirable for ease of deployment, as reflected in the current embedded clinical research project. The 3D nnU-Net had the highest performance, which suggests a way forward for our need to automate WMH segmentation while also evaluating performance metrics during on-going data collection and model retraining.

Background and purpose: Measuring rectal tumour response to radiation is pivotal to restaging patients and for possibly stratification to a watch-and-wait strategy. Recognizing the importance of the tumour microenvironment, we investigated a less explored quantitative imaging marker assessing tumour blood flow (BF) for its potential to predict overall survival (OS). Materials and methods: 24 rectal cancer patients given curative-intent neoadjuvant radiotherapy underwent a multi-echo dynamic magnetic resonance imaging (MRI) sequence with gadolinium contrast for quantification of tumour BF before either 25x2 Gy (n = 18) with concomitant chemotherapy or 5x5 Gy (n = 6). CD34 staining of excised tumour tissue was performed and baseline blood samples were analysed for lactate dehydrogenase (LDH) and angiopoietin-2 (ANGPT-2). Tumour volumes were measured before and after treatment. After subsequent surgery, ypTN scoring assessed tumour response. Cox regression for 5-year OS analysis and t-test for group comparisons were performed. Results: The change in tumour BF (ΔBF) during neoadjuvant radiotherapy was a significant marker of OS, whereas tumour stage and volume were not related to OS. All patients with >20 % decline in BF were long-term survivors. Separating cases in two groups based on ΔBF revealed that patients with increase or a low decrease had higher baseline LDH (p = 0.032) and ANGPT-2 (p = 0.028) levels. Conclusion: MRI-assessed tumour ΔBF during neoadjuvant treatment is a significant predictor of OS in rectal cancer patients, making ΔBF a potential quantitative imaging biomarker for treatment stratification. Blood LDH and ANGPT-2 indicate that non-responding tumours may have a hypoxic microenvironment resistant to radiotherapy.

IntroductionManagement of patients with brain metastases is often based on manual lesion detection and segmentation by an expert reader. This is a time- and labor-intensive process, and to that end, this work proposes an end-to-end deep learning segmentation network for a varying number of available MRI available sequences.MethodsWe adapt and evaluate a 2.5D and a 3D convolution neural network trained and tested on a retrospective multinational study from two independent centers, in addition, nnU-Net was adapted as a comparative benchmark. Segmentation and detection performance was evaluated by: (1) the dice similarity coefficient, (2) a per-metastases and the average detection sensitivity, and (3) the number of false positives.ResultsThe 2.5D and 3D models achieved similar results, albeit the 2.5D model had better detection rate, whereas the 3D model had fewer false positive predictions, and nnU-Net had fewest false positives, but with the lowest detection rate. On MRI data from center 1, the 2.5D, 3D, and nnU-Net detected 79%, 71%, and 65% of all metastases; had an average per patient sensitivity of 0.88, 0.84, and 0.76; and had on average 6.2, 3.2, and 1.7 false positive predictions per patient, respectively. For center 2, the 2.5D, 3D, and nnU-Net detected 88%, 86%, and 78% of all metastases; had an average per patient sensitivity of 0.92, 0.91, and 0.85; and had on average 1.0, 0.4, and 0.1 false positive predictions per patient, respectively.Discussion/ConclusionOur results show that deep learning can yield highly accurate segmentations of brain metastases with few false positives in multinational data, but the accuracy degrades for metastases with an area smaller than 0.4 cm2.

Physical exercise affects hippocampal structure and function, but the underlying neural mechanisms and the effects of exercise intensity remain incompletely understood. Therefore, we undertook a comprehensive, multi-modal 3T and 7T MRI randomized controlled trial (Netherlands Trial Register - NL5847) in which we randomized 52 young, non-athletic volunteers to a 12-week low- or high-intensity exercise program. Using state-of-the-art methods, we investigated changes in hippocampal volume, as well as changes in vasculature, neuro-metabolites, and peripheral growth factors as potential underpinnings. Cardiorespiratory fitness improved over time (p < 0.001), but no interaction with exercise intensity was found (p = 0.48). Accordingly, we did not observe significant interactions between exercise condition and time on MRI measures (all p > 0.06). However, we found a significant decrease in right hippocampal volume (p < 0.01), an increase in left hippocampal glutathione (p < 0.01), and a decrease of left hippocampal cerebral blood volume (p = 0.01) over time, regardless of exercise condition. Additional exploratory analyses showed that changes in brain-derived neurotrophic factor (p = 0.01), insulin-like growth-factor (p = 0.03), and dorsal anterior cingulate cortex N-acetyl-aspartate levels (p = 0.01) were positively associated with cardiorespiratory fitness changes. Furthermore, a trend toward a positive association of fitness and gray-matter cerebral blood flow (p = 0.06) was found. Our results do not provide evidence for differential effects between high-intensity (aerobic) and low-intensity (toning) exercise on hippocampal structure and function in young adults. However, we show small but significant effects of exercise on hippocampal volume, neurometabolism and vasculature across exercise conditions. Moreover, our exploratory results suggest that exercise might not specifically only benefit hippocampal structure and function, but rather has a more widespread effect. These findings suggest that, in agreement with previous MRI studies demonstrating moderate to strong effects in elderly and diseased populations, but none to only mild effects in young healthy cohorts, the benefits of exercise on the studied brain measures may be age-dependent and restorative rather than stimulatory. Our study highlights the importance of a multi-modal, whole-brain approach to assess macroscopic and microscopic changes underlying exercise-induced brain changes, to better understand the role of exercise as a potential non-pharmacological intervention.

Accurate and reliable whole-brain segmentation is critical to longitudinal neuroimaging studies. We undertake a comparative analysis of two subcortical segmentation methods, Automatic Segmentation (ASEG) and Sequence Adaptive Multimodal Segmentation (SAMSEG), recently provided in the open-source neuroimaging package FreeSurfer 7.1, with regard to reliability, bias, sensitivity to detect longitudinal change, and diagnostic sensitivity to Alzheimer’s disease. First, we assess intra- and inter-scanner reliability for eight bilateral subcortical structures: amygdala, caudate, hippocampus, lateral ventricles, nucleus accumbens, pallidum, putamen and thalamus. For intra-scanner analysis we use a large sample of participants (n = 1629) distributed across the lifespan (age range = 4–93 years) and acquired on a 1.5T Siemens Avanto (n = 774) and a 3T Siemens Skyra (n = 855) scanners. For inter-scanner analysis we use a sample of 24 participants scanned on the day with three models of Siemens scanners: 1.5T Avanto, 3T Skyra and 3T Prisma. Second, we test how each method detects volumetric age change using longitudinal follow up scans (n = 491 for Avanto and n = 245 for Skyra; interscan interval = 1–10 years). Finally, we test sensitivity to clinically relevant change. We compare annual rate of hippocampal atrophy in cognitively normal older adults (n = 20), patients with mild cognitive impairment (n = 20) and Alzheimer’s disease (n = 20). We find that both ASEG and SAMSEG are reliable and lead to the detection of within-person longitudinal change, although with notable differences between age-trajectories for most structures, including hippocampus and amygdala. In summary, SAMSEG yields significantly lower differences between repeated measures for intra- and inter-scanner analysis without compromising sensitivity to changes and demonstrating ability to detect clinically relevant longitudinal changes.

Sleep deprivation influences several critical functions, yet how it affects human brain white matter (WM) is not well understood. The aim of the present work was to investigate the effect of 32 hours of sleep deprivation on WM microstructure compared to changes observed in a normal sleep-wake cycle (SWC). To this end, we utilised diffusion weighted imaging (DWI) including the diffusion tensor model, diffusion kurtosis imaging and the spherical mean technique, a novel biophysical diffusion model. 46 healthy adults (23 sleep deprived vs 23 with normal SWC) underwent DWI across four time points (morning, evening, next day morning and next day afternoon, after a total of 32 hours). Linear mixed models revealed significant group × time interaction effects, indicating that sleep deprivation and normal SWC differentially affect WM microstructure. Voxel-wise comparisons showed that these effects spanned large, bilateral WM regions. These findings provide important insight into how sleep deprivation affects the human brain.

The liver is the most frequent organ for metastasis from colorectal cancer, one of the most common tumor types with a poor prognosis. Despite reducing surgical planning time and providing better spatial representation, current methods of 3D modeling of patient-specific liver anatomy are extremely time-consuming. The purpose of this study was to develop a deep learning model trained on an in-house dataset of 84 MRI volumes to rapidly provide fully automated whole liver and liver lesions segmentation from volumetric MRI series. A cascade approach was utilized to address the problem of class imbalance. The trained model achieved an average Dice score for whole liver segmentation of 0.944 ± 0.009 and 0.780 ± 0.119 for liver lesion segmentation. Furthermore, applying this method to a not-annotated dataset creates a complete 3D segmentation in less than 6 s per MRI volume, with a mean segmentation Dice score of 0.994 ± 0.003 for the liver and 0.709 ± 0.171 for tumors compared to manual corrections applied after the inference was achieved. Availability and integration of our method in clinical practice may improve diagnosis and treatment planning in patients with colorectal liver metastasis and open new possibilities for research into liver tumors.

Arterial spin labeling (ASL) has undergone significant development since its inception, with a focus on improving standardization and reproducibility of its acquisition and quantification. In a community-wide effort towards robust and reproducible clinical ASL image processing, we developed the software package ExploreASL, allowing standardized analyses across centers and scanners.The procedures used in ExploreASL capitalize on published image processing advancements and address the challenges of multi-center datasets with scanner-specific processing and artifact reduction to limit patient exclusion. ExploreASL is self-contained, written in MATLAB and based on Statistical Parameter Mapping (SPM) and runs on multiple operating systems. To facilitate collaboration and data-exchange, the toolbox follows several standards and recommendations for data structure, provenance, and best analysis practice.ExploreASL was iteratively refined and tested in the analysis of >10,000 ASL scans using different pulse-sequences in a variety of clinical populations, resulting in four processing modules: Import, Structural, ASL, and Population that perform tasks, respectively, for data curation, structural and ASL image processing and quality control, and finally preparing the results for statistical analyses on both single-subject and group level. We illustrate ExploreASL processing results from three cohorts: perinatally HIV-infected children, healthy adults, and elderly at risk for neurodegenerative disease. We show the reproducibility for each cohort when processed at different centers with different operating systems and MATLAB versions, and its effects on the quantification of gray matter cerebral blood flow.ExploreASL facilitates the standardization of image processing and quality control, allowing the pooling of cohorts which may increase statistical power and discover between-group perfusion differences. Ultimately, this workflow may advance ASL for wider adoption in clinical studies, trials, and practice.

Recently, several magnetic resonance imaging (MRI) studies have reported time-of-day effects on brain structure and function. Due to the possibility that time-of-day effects reflect mechanisms of circadian regulation, the aim of this prospective study was to assess these effects while under strict experimental control of variables that might influence biological clocks, such as caffeine intake and exposure to blue-emitting light. In addition, the current study assessed whether time-of-day effects were driven by changes to extracellular space, by including estimations of non-Gaussian diffusion metrics obtained from diffusion kurtosis imaging, white matter tract integrity and the spherical mean technique, in addition to conventional diffusion tensor imaging -derived parameters. Participants were 47 healthy adults who underwent diffusion-weighted imaging in the morning and evening of the same day. Morning and evening scans were compared using voxel-wise tract based spatial statistics and permutation testing. A day of wakefulness was associated with widespread increases in fractional anisotropy, indices of kurtosis and indices of the axonal water fraction. In addition, wakefulness was associated with widespread decreases in radial diffusivity, both in the single compartment and in extra-axonal space. These results suggest that an increase in the intra-axonal space relative to the extra-axonal volume underlies time-of-day effects in human white matter, which is in line with activity-induced reductions to the extracellular volume. These findings provide important insight into possible mechanisms driving time-of-day effects in MRI.

To meet the need for Parkinson's disease biomarkers and evidence for amount and distribution of pathological changes, MRI diffusion tensor imaging (DTI) has been explored in a number of previous studies. However, conflicting results warrant further investigations. As tissue microstructure, particularly of the grey matter, is heterogeneous, a more precise diffusion model may benefit tissue characterization. The purpose of this study was to analyze the diffusion-based imaging technique restriction spectrum imaging (RSI) and DTI, and their ability to detect microstructural changes within brain regions associated with motor function in Parkinson's disease. Diffusion weighted (DW) MR images of a total of 100 individuals, (46 Parkinson's disease patients and 54 healthy controls) were collected using b-values of 0-4000s/mm2. Output diffusion-based maps were estimated based on the RSI-model combining the full set of DW-images (Cellular Index (CI), Neurite Density (ND)) and DTI-model combining b = 0 and b = 1000 s/mm2 (fractional anisotropy (FA), Axial-, Mean- and Radial diffusivity (AD, MD, RD)). All parametric maps were analyzed in a voxel-wise group analysis, with focus on typical brain regions associated with Parkinson's disease pathology. CI, ND and DTI diffusivity metrics (AD, MD, RD) demonstrated the ability to differentiate between groups, with strongest performance within the thalamus, prone to pathology in Parkinson's disease. Our results indicate that RSI may improve the predictive power of diffusion-based MRI, and provide additional information when combined with the standard diffusivity measurements. In the absence of major atrophy, diffusion techniques may reveal microstructural pathology. Our results suggest that protocols for MRI diffusion imaging may be adapted to more sensitive detection of pathology at different sites of the central nervous system.

Working memory capacity is pivotal for a broad specter of cognitive tasks and develops throughout childhood. This must in part rely on development of neural connections and white matter microstructure maturation, but there is scarce knowledge of specific relations between this and different aspects of working memory. Diffusion tensor imaging (DTI) enables us to study development of brain white matter microstructure. In a longitudinal DTI study of 148 healthy children between 4 and 11 years scanned twice with an on average 1.6 years interval, we characterized change in fractional anisotropy (FA), mean (MD), radial (RD) and axial diffusivity (AD) in 10 major white matter tracts hypothesized to be of importance for working memory. The results showed relationships between change in several tracts and change in visuospatial working memory. Specifically, improvement in visuospatial working memory capacity was significantly associated with decreased MD, RD and AD in inferior longitudinal fasciculus (ILF), inferior fronto-occipital fasciculus (IFOF) and uncinate fasciculus (UF) in the right hemisphere, as well as forceps major (FMaj). No significant relationships were found between change in DTI metrics and change in verbal working memory capacity. These findings yield new knowledge about brain development and corresponding working memory improvements in childhood.

OBJECTIVES: This study evaluates the repeatability of brain perfusion using dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) with a variety of post-processing methods. METHODS: Thirty-two patients with newly diagnosed glioblastoma were recruited. On a 3-T MRI using a dual-echo, gradient-echo spin-echo DSC-MRI protocol, the patients were scanned twice 1 to 5 days apart. Perfusion maps including cerebral blood volume (CBV) and cerebral blood flow (CBF) were generated using two contrast agent leakage correction methods, along with testing normalization to reference tissue, and application of arterial input function (AIF). Repeatability of CBV and CBF within tumor regions and healthy tissues, identified by structural images, was assessed with intra-class correlation coefficients (ICCs) and repeatability coefficients (RCs). Coefficients of variation (CVs) were reported for selected methods. RESULTS: CBV and CBF were highly repeatable within tumor with ICC values up to 0.97. However, both CBV and CBF showed lower ICCs for healthy cortical tissues (up to 0.83), healthy gray matter (up to 0.95), and healthy white matter (WM; up to 0.93). The values of CV ranged from 6% to 10% in tumor and 3% to 11% in healthy tissues. The values of RC relative to the mean value of measurement within healthy WM ranged from 22% to 42% in tumor and 7% to 43% in healthy tissues. These percentages show how much variation in perfusion parameter, relative to that in healthy WM, we expect to observe to consider it statistically significant. We also found that normalization improved repeatability, but AIF deconvolution did not. CONCLUSIONS: DSC-MRI is highly repeatable in high-grade glioma patients.

Heart rate variability (HRV) has become an increasingly popular index of cardiac autonomic control in the biobehavioral sciences due to its relationship with mental illness and cognitive traits. However, the intraindividual stability of HRV in response to sleep and diurnal disturbances, which are commonly reported in mental illness, and its relationship with executive function are not well understood. Here, in 40 healthy adult males we calculated high frequency HRV-an index of parasympathetic nervous system (PNS) activity-using pulse oximetry during brain imaging, and assessed attentional and executive function performance in a subsequent behavioral test session at three time points: morning, evening, and the following morning. Twenty participants were randomly selected for total sleep deprivation whereas the other 20 participants slept as normal. Sleep deprivation and morning-to-night variation did not influence high frequency HRV at either a group or individual level; however, sleep deprivation abolished the relationship between orienting attention performance and HRV. We conclude that a day of wake and a night of laboratory-induced sleep deprivation do not alter supine high frequency HRV in young healthy male adults.

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disorder and cause of dementia, and is characterized by amyloid plaques and neurofibrillary tangles. AD has traditionally been considered to primarily affect grey matter, but multiple lines of evidence also indicate white matter (WM) pathology and associated small-vessel cerebrovascular disease (CVD). WM glucose delivery and metabolism may have implications for local tissue integrity, and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) may be helpful to assess neuroglial and axonal function in WM. Hypothesizing that affection of oligodendroglia will be associated with loss of glucose uptake, we aimed to investigate glucose metabolism in MRI white matter hyperintensities (WMHs) and normal-appearing white matter in patients with and without evidence of amyloid plaques. Subjects with mild cognitive impairment or subjective cognitive decline were included and dichotomized according to pathological (Aβ+) or normal (Aβ-) concentrations of cerebrospinal fluid amyloid-β 1-42. A total of fifty subjects were included, of whom thirty subjects were classified as Aβ(+) and twenty subjects as Aβ(-). All subjects were assessed with MRI and FDG-PET. FDG-PET images were corrected for effects of partial voluming and normalized to cerebellar WM, before determining WMH FDG uptake. Although there were no significant differences between the groups in terms of age, WMH volume, number of individual WMHs or WMH distribution, we found significantly lower (p = 0.021) FDG uptake in WMHs in Aβ(+) subjects (mean = 0,662, SD = 0.113) compared to Aβ(-) subjects (mean = 0.596, SD = 0.073). There were no significant group differences in the FDG uptake in normal-appearing white matter. Similar results were obtained without correction for effects of partial voluming. Our findings add to the evidence for a link between Aβ dysmetabolism and white matter pathology in AD.

The diffusion weighted imaging (DWI) technique enables quantification of water mobility for probing microstructural properties of biological tissue, and has become an effective tool for collecting information about the underlying pathology of cancerous tissue. Measurements using multiple b-values have indicated a bi-exponential signal attenuation, ascribed to fast (high ADC) and slow (low ADC) diffusion components. In this empirical study, we investigate the properties of the diffusion time (∆) - dependent components of the diffusion-weighted (DW) signal in a constant b-value experiment. A Xenograft GBM mouse was imaged using ∆ = 11 ms, 20 ms, 40 ms, 60 ms and b=500-4000 s/mm2 in intervals of 500s/mm2. Data was corrected for EPI distortions and the ∆-dependence on the DW signal was measured within three regions of interest (intermediate- and high-density tumor regions and normal appearing brain tissue regions (NAB)). In this empirical study we verify the assumption that the slow decaying component of the DW-signal is non-Gaussian and dependent on ∆, consistent with restricted diffusion of the intracellular space. As the DW-signal as a function of ∆ is specific to restricted diffusion, manipulating ∆ at constant b-value (cb) provides a complementary and direct approach for separating the restricted from the hindered diffusion component. Our results show that only tumor tissue signal of our data demonstrate ∆-dependence, based on a bi-exponential model with a restricted diffusion component, we successfully estimated the restricted ADC, signal volume fraction and cell size within each tumor ROI.

To establish whether reliable voxel-wise assessment of perfusion in cerebral white matter (WM) is possible using arterial spin labeling (ASL) at 3T in a cohort of healthy subjects.Pseudo-continuous ASL (PCASL) with background suppression (BS) optimized for WM measurements was performed at 3T in eight healthy male volunteers aged 25-41. Four different labeling schemes were evaluated by varying the labeling duration (LD) and post-labeling delay (PLD). Eight slices with voxel dimension 3.75x3.75x5 mm3 were acquired from the anterosuperior aspect of the brain, and 400 image/control pairs were collected for each run. Rigid head immobilization was applied using individually fitted thermoplastic masks. For each voxel in the resulting ASL time series, the time needed to reach a 95% significance level for the ASL signal to be higher than zero (paired t-test), was estimated.The four protocols detected between 88% and 95% (after Bonferroni correction: 75% and 88%) of WM voxels at 95% significance level. In the most efficient sequence, 80% was reached after 5 min and 95% after 53 min (after Bonferroni correction 40% and 88% respectively). For all protocols, the fraction of significant WM voxels increased in an asymptotic fashion with increasing scan time. A small subgroup of voxels was shown to not benefit at all from prolonged measurement.Acquisition of a significant ASL signal from a majority of WM voxels is possible within clinically acceptable scan times, whereas full coverage needs prohibitively long scan times, as a result of the asymptotic trajectory.

Elucidating the neurobiological effects of sleep and waking remains an important goal of the neurosciences. Recently, animal studies indicated that sleep is important for cell membrane and myelin maintenance in the brain and that these structures are particularly susceptible to insufficient sleep. Here, we tested the hypothesis that a day of waking and sleep deprivation would be associated with changes in diffusion tensor imaging (DTI) indices of white matter microstructure sensitive to axonal membrane and myelin alterations.Twenty-one healthy adult males underwent DTI in the morning [7:30AM; time point (TP)1], after 14 hours of waking (TP2), and then after another 9 hours of waking (TP3). Whole brain voxel-wise analysis was performed with tract based spatial statistics.A day of waking was associated with widespread increases in white matter fractional anisotropy, which were mainly driven by radial diffusivity reductions, and sleep deprivation was associated with widespread fractional anisotropy decreases, which were mainly explained by reductions in axial diffusivity. In addition, larger decreases in axial diffusivity after sleep deprivation were associated with greater sleepiness. All DTI changes remained significant after adjusting for hydration measures.This is the first DTI study of sleep deprivation in humans. Although previous studies have observed localized changes in DTI indices of cerebral microstructure over the course of a few hours, further studies are needed to confirm widespread DTI changes within hours of waking and to clarify whether such changes in white matter microstructure serve as neurobiological substrates of sleepiness.