Icometrix (Belgium)

In a retrospective multicentre cohort study, we explored the association between brain atrophy and multiple sclerosis (MS) disability using different MRI scanners and protocols at multiple sites. Relapse-onset MS patients were included if they had two clinical MRIs 12 months apart and ≥2 Expanded Disability Status Scale (EDSS) scores. Percentage brain volume change (PBVC), percentage grey matter change (PGMC), fluid-attenuated inversion recovery (FLAIR) lesion volume change, whole brain volume (BV), grey matter volume (GMV), FLAIR lesion volume and T1 hypointense lesion volume were assessed by icobrain. Disability was measured by EDSS scores and 6-month confirmed disability progression (CDP). Of the 260 relapse-onset MS patients included, 204 (78%) MRI pairs were performed in the same scanner and 56 (22%) pairs were from different scanners. 93% of patients were on treatment and mean PBVC was -0.26% (±0.52). During the median follow-up of 2.8 years from the second MRI, median EDSS change was 0.0 and 12% patients experienced 6-month CDP. Cross-sectional BV and GMV at the later MRI showed a trend for association with CDP (HR 0.99; 95% CI 0.98 to 1.00; p=0.06). Only BV at the later MRI was associated with EDSS score (β -0.03, SE 0.01, p<0.001) and the rate of EDSS change over time (β -0.001, SE 0.0003, p=0.02). There was no association between longitudinal PBVC or PGMC and CDP or EDSS (p>0.05). In this highly treated MS cohort with low disability accrual, only cross-sectional BV showed an association with future EDSS scores, while no MRI metric predicted 6-month CDP. These findings highlight the limitations of current clinical MRI measures in predicting disability worsening in real-world settings.

To examine the relation of optical coherence tomography (OCT) measures to MRI brain volumetrics in patients with pediatric-onset multiple sclerosis (POMS).

Multiple sclerosis (MS) is a devastating immune-mediated disorder of the central nervous system resulting in progressive disability accumulation. As there is no cure available yet for MS, the primary therapeutic objective is to reduce relapses and to slow down disability progression as early as possible during the disease to maintain and/or improve health-related quality of life. However, optimizing treatment for people with MS (pwMS) is complex and challenging due to the many factors involved and in particular, the high degree of clinical and sub-clinical heterogeneity in disease progression among pwMS. In this paper, we discuss these many different challenges complicating treatment optimization for pwMS as well as how a shift towards a more pro-active, data-driven and personalized medicine approach could potentially improve patient outcomes for pwMS. We describe how the 'Clinical Impact through AI-assisted MS Care' (CLAIMS) project serves as a recent example of how to realize such a shift towards personalized treatment optimization for pwMS through the development of a platform that offers a holistic view of all relevant patient data and biomarkers, and then using this data to enable AI-supported prognostic modelling.

Ischemic stroke segmentation at an acute stage is vital in assessing the severity of patients' impairment and guiding therapeutic decision-making for reperfusion. Although many deep learning studies have shown attractive performance in medical segmentation, it is difficult to use these models trained on public data with private hospitals' datasets. Here, we demonstrate an ensemble model that employs two different multimodal approaches for generalization, a more effective way to perform on external datasets. First, after we jointly train a segmentation model on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) MR modalities, the model is inferred on the DWI images. Second, a channel-wise segmentation model is trained by concatenating the DWI and ADC images as input, and then is inferred using both MR modalities. Before training with ischemic stroke data, we utilized BraTS 2021, a public brain tumor dataset, for transfer learning. An extensive ablation study evaluates which strategy learns better representations for ischemic stroke segmentation. In our study, nnU-Net well-known for robustness is selected as our baseline model. Our proposed method is evaluated on three different datasets: the Asan Medical Center (AMC) I and II, and the 2022 Ischemic Stroke Lesion Segmentation (ISLES). Our experiments are widely validated over a large, multi-center, and multi-scanner dataset with a huge amount of 846 scans. Not only stroke lesion models can benefit from transfer learning using brain tumor data, but combining the MR modalities using different training schemes also highly improves segmentation performance. The method achieved a top-1 ranking in the ongoing ISLES'22 challenge and performed particularly well on lesion-wise metrics of interest to neuroradiologists, achieving a Dice coefficient of 78.69% and a lesion-wise F1 score of 82.46%. Also, the method was relatively robust on the AMC I (Dice, 60.35%; lesion-wise F1, 68.30%) and II (Dice; 74.12%; lesion-wise F1, 67.53%) datasets in different settings. The high segmentation accuracy of our proposed method could improve radiologists' ability to detect ischemic stroke lesions in MRI images. Our model weights and inference code are available on https://github.com/MDOpx/ISLES22-model-inference .

Current guidelines for CT perfusion (CTP) in acute stroke suggest acquiring scans with a minimal duration of 60-70 s. But even then, CTP analysis can be affected by truncation artifacts. Conversely, shorter acquisitions are still widely used in clinical practice and may, sometimes, be sufficient to reliably estimate lesion volumes. We aim to devise an automatic method that detects scans affected by truncation artifacts. Shorter scan durations are simulated from the ISLES'18 dataset by consecutively removing the last CTP time-point until reaching a 10 s duration. For each truncated series, perfusion lesion volumes are quantified and used to label the series as unreliable if the lesion volumes considerably deviate from the original untruncated ones. Afterwards, nine features from the arterial input function (AIF) and the vascular output function (VOF) are derived and used to fit machine-learning models with the goal of detecting unreliably truncated scans. Methods are compared against a baseline classifier solely based on the scan duration, which is the current clinical standard. The ROC-AUC, precision-recall AUC and the F1-score are measured in a 5-fold cross-validation setting. The best performing classifier obtained an ROC-AUC of 0.982, precision-recall AUC of 0.985 and F1-score of 0.938. The most important feature was the AIFcoverage, measured as the time difference between the scan duration and the AIF peak. When using the AIFcoverage to build a single feature classifier, an ROC-AUC of 0.981, precision-recall AUC of 0.984 and F1-score of 0.932 were obtained. In comparison, the baseline classifier obtained an ROC-AUC of 0.954, precision-recall AUC of 0.958 and F1-Score of 0.875. Machine learning models fed with AIF and VOF features accurately detected unreliable stroke lesion measurements due to insufficient acquisition duration. The AIFcoverage was the most predictive feature of truncation and identified unreliable short scans almost as good as machine learning. We conclude that AIF/VOF based classifiers are more accurate than the scans' duration for detecting truncation. These methods could be transferred to perfusion analysis software in order to increase the interpretability of CTP outputs.

The choroid plexus (ChP) produces and is bathed in the cerebrospinal fluid (CSF), which in aging and Alzheimer's disease (AD) shows extensive proteomic alterations including evidence of inflammation. Considering inflammation hampers functions of the involved tissues, the CSF abnormalities reported in these conditions are suggestive of ChP injury. Indeed, several studies document ChP damage in aging and AD, which nevertheless remains to be systematically characterized. We here report that the changes elicited in the CSF by AD are consistent with a perturbed aging process and accompanied by aberrant accumulation of inflammatory signals and metabolically active proteins in the ChP. Magnetic resonance imaging (MRI) imaging shows that these molecular aberrancies correspond to significant remodeling of ChP in AD, which correlates with aging and cognitive decline. Collectively, our preliminary post-mortem and in vivo findings reveal a repertoire of ChP pathologies indicative of its dysfunction and involvement in the pathogenesis of AD. HIGHLIGHTS: Cerebrospinal fluid changes associated with aging are perturbed in Alzheimer's disease Paradoxically, in Alzheimer's disease, the choroid plexus exhibits increased cytokine levels without evidence of inflammatory activation or infiltrates In Alzheimer's disease, increased choroid plexus volumes correlate with age and cognitive performance.

Early diagnosis of COVID-19 is required to provide the best treatment to our patients, to prevent the epidemic from spreading in the community, and to reduce costs associated with the aggravation of the disease. We developed a decision tree model to evaluate the impact of using an artificial intelligence-based chest computed tomography (CT) analysis software (icolung, icometrix) to analyze CT scans for the detection and prognosis of COVID-19 cases. The model compared routine practice where patients receiving a chest CT scan were not screened for COVID-19, with a scenario where icolung was introduced to enable COVID-19 diagnosis. The primary outcome was to evaluate the impact of icolung on the transmission of COVID-19 infection, and the secondary outcome was the in-hospital length of stay. Using EUR 20000 as a willingness-to-pay threshold, icolung is cost-effective in reducing the risk of transmission, with a low prevalence of COVID-19 infections. Concerning the hospitalization cost, icolung is cost-effective at a higher value of COVID-19 prevalence and risk of hospitalization. This model provides a framework for the evaluation of AI-based tools for the early detection of COVID-19 cases. It allows for making decisions regarding their implementation in routine practice, considering both costs and effects.

Diffusion tensor imaging (DTI) can detect microstructural changes of white matter in multiple sclerosis (MS) and might clarify mechanisms responsible for disability. Thus, we aimed to compare DTI metrics in relapsing-remitting MS patients (RRMS) with healthy controls (HCs), and explore the correlations between DTI metrics, total brain white matter (TBWM) and white matter lesion (WML) with clinical parameters compared to volumetric measures. 37 RRMS patients and 19 age/sex-matched HCs were included. All participants had clinical assessments, structural and diffusion scans on a 3T MRI. Volumetric and white matter DTI metrics; fractional anisotropy (FA), mean, radial and axial diffusivities (MD, RD and AD) were estimated and correlated with clinical parameters. The mean group differences were calculated using t-tests, and univariate correlations with Pearson correlation coefficients. Compared to HCs, statistically significant increases in MD (+3.6%), RD (+4.8%), AD (+2.7%) and a decrease in FA (-4.3%) for TBWM in RRMS was observed (p < .01). MD and RD in TBWM and AD in WML correlated moderately with disability status. Volumetric segmentation indicated a decrease in the total brain volume, GM and WM(-5%) with a reciprocal increase in CSF(+26%) in RRMS(p < .01). Importantly, DTI parameters showed a medium correlation with cognitive domains in contrast to white matter-related volumetric measurements in RRMS(Pearson correlation, p < .05). Our study shows a correlation of DTI metrics with clinical symptoms of MS, in particular cognition. More generally, these findings indicated that DTI is a useful and unique technique for evaluating the clinical features of white matter disease and warrants further investigation into its clinical role.

Abstract BackgroundMagnetic Resonance Imaging (MRI) has become part of clinical routine for diagnosis of neurodegenerative brain disorders. Acquisitions are performed at multiple centers, using multiple imaging systems and is therefore subjected to intra‐ and inter‐scanner variability. Detailed analysis of brain volumetry differences between MRI systems and scan‐rescan acquisitions can provide useful information to correct for different MRI scanner effects in future multi‐center longitudinal studies.MethodThe study population (n=10) consisted of five cognitively healthy controls and five patients belonging to different stages of the AD continuum. Subjects underwent brain MRI acquisitions on three different MRI systems with harmonized scan parameters: Philips Achieva dStream 1.5T, Philips Ingenia 3T and GE Discovery MR750w 3T. Sequences were harmonized by keeping acquisition parameters similar (Table 1). To test intra‐scanner variability, each participant underwent two subsequent MRI scans (between‐scan repositioning time 3‐5 minutes) per imaging system, repeated on three different MRI systems within two hours to test inter‐scanner variability. A total of 60 MRI scans were acquired for downstream comparative analysis. Brain volumes, including whole brain, (cortical) gray matter, hippocampal volumes, lateral ventricles, frontal, temporal and parietal cortices were computed with icobrain dm (v5.0). Coefficients of variation (CV), absolute volume differences (AVD), Dice similarity coefficients (DSC) and intraclass correlation coefficients (ICC) were computed to assess within‐ and between‐scanner agreement.ResultThe intra‐scanner CVs over all volumes were 0.948% for Discovery MR750w, 1.050% for Achieva and 1.152% for Ingenia. The inter‐scanner CVs were 3.016% for all‐scanner comparisons, 2.044% for Ingenia vs. Achieva, 3.191% for Achieva vs. GE and 3.326% for Ingenia vs. GE. The AVDs and ICCs were in line with the CV values. The intra‐scanner DSCs (mean±SD) over all volumes were 0.917±0.011 for Discovery MR750w, 0.917±0.010 for Achieva and 0.917±0.015 for Ingenia. The inter‐scanner DSCs were 0.898±0.017 for all‐scanner comparisons, 0.912±0.012 for Ingenia vs. Achieva, 0.888±0.013 for Achieva vs. Discovery MR750w and 0.893±0.015 for Ingenia vs. Discovery MR750w (Table 2, 3, Figure 1).ConclusionThe variability results show an excellent agreement (CV&lt;2%) for within‐scanner and a good agreement (CV&lt;5%) for between‐scanner comparisons in terms of clinical relevance, indicating that MRI acquisition harmonization is beneficial for automated MRI volumetry software.