Biology subjects

Tourdias, T.

Publications and source records attributed to Tourdias, T..

9 recordsLinked to original sources

bioRxiv2025

Generating Synthetic MR Perfusion Maps from DWI and FLAIR in Acute Ischemic Stroke using Deep Learning

BackgroundMagnetic resonance imaging (MRI) is critical for acute stroke triage, but time-consuming, and often requires contrast injection for perfusion imaging. This study aimed to synthesize T-map perfusion maps from routinely available, non-contrast DWI and FLAIR using deep generative models. We hypothesized that relevant perfusion information could be inferred from these modalities to streamline imaging and reduce reliance on dynamic susceptibility contrast perfusion. MethodsAcute MRI data from 355 patients with anterior circulation stroke, including dynamic susceptibility contrast perfusion, were retrospectively collected from two European centers (Heidelberg: 2010-2018; Bordeaux: 2021-2022). Six versions of a denoising diffusion probabilistic model (DDPM) and a GAN architecture were trained to generate synthetic T-max perfusion maps from DWI, FLAIR, and infarct core mask as inputs. Performance was assessed by comparing synthetic and ground truth T-max maps using image similarity metrics. Regions with T-max >6s were compared using Dice coefficients, and mismatch volume distributions were analyzed. An ablation study quantified the contribution of each input. ResultsThe best performance was achieved by a DDPM with a 2.5D architecture using DWI, FLAIR, infarct core mask, and a perfusion-weighted loss function. It produced synthetic perfusion T-max maps with high similarity to ground truth under 110 seconds. The model showed strong spatial overlap for T-max >6s regions in internal validation (average Dice = 0.82, SD = 0.08), and external validation average (Dice 0.59, SD = 0.13), respectively. Synthetic maps closely matched ground-truth mismatch distributions, capturing key perfusion patterns. The infarct core mask played a critical role in model performance, alongside DWI and FLAIR inputs. ConclusionsWe propose a non-invasive, scalable framework to generate synthetic T-max perfusion maps from non-contrast MRI. This approach could expand access to perfusion data in acute stroke, shorten imaging protocols, and accelerate treatment decisions by eliminating the need for contrast-enhanced acquisition. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=200 SRC="FIGDIR/small/684079v2_ufig1.gif" ALT="Figure 1"> View larger version (94K): org.highwire.dtl.DTLVardef@164235forg.highwire.dtl.DTLVardef@14e5489org.highwire.dtl.DTLVardef@190214eorg.highwire.dtl.DTLVardef@17a9e3a_HPS_FORMAT_FIGEXP M_FIG C_FIG

neuroscience↗

bioRxiv2025

DeepDisco: A Deep Learning Tool for Rapid Brain Connectivity Estimation

DeepDisco is a cross-platform software that uses deep learning to rapidly predict brain connectivity maps from binary regions or lesions. It offers a user-friendly and scriptable interface, making indirect connectivity analysis accessible for large datasets and scalable for AI frameworks.

neuroscience↗

bioRxiv2024

MRI R2* captures inflammation in disconnected brain structures after stroke: a translational study

Ischemic strokes disrupt brain networks, leading to remote effects in key regions like the thalamus, a critical hub for brain functions. However, non-invasive methods to quantify these remote consequences still need to be explored. This study aimed to demonstrate that MRI-derived R2* changes can capture iron accumulation linked with inflammation secondary to stroke-induced disconnection. In order to link remote R2* changes to stroke-induced disconnection, we first conducted a secondary analysis of 156 prospectively included stroke patients who underwent MRI at baseline and 1-year follow-up. We mapped fibers disconnected by baseline infarcts to compare the R2* changes over 1 year according to the disconnectivity status in specific thalamic nuclei groups. We also identified the predictors of elevated R2* at 1 year in a multivariate context through linear regressions. In parallel, to understand the biological underpinning of the remote R2* changes, we set up a translational mouse model through photothrombotic induction of focal cortical infarcts or sham procedures in 110 C57BL/6J mice. We explored the mice through combinations of in vivo MRI at 72h, 2-, 4-, and 8-weeks, histology, qPCR for gene expression, mass spectrometry for iron concentration quantification, and additional ex vivo high-resolution diffusion tensor imaging. In stroke patients, we found a significant increase of R2* within severely disconnected medial and lateral thalamic nuclei groups from baseline to 1 year. At the same time, no change occurred if these structures were not disconnected. We also showed that the disconnectivity status at baseline was a significant predictor of R2* at follow-up, independently from confounders, establishing a direct and independent relationship between baseline disconnection and the subsequent R2* increase within the associated locations. In mice, we recapitulated the patients conditions by observing increased R2* in the stroke groups, specifically within the disconnected thalamic nuclei. Such remote and focal R2* changes peaked at 2 weeks, preceding and correlating with longer-term atrophy at 8 weeks. We established that the remote R2* increase was spatially and temporally correlated with a significant increase of chemically determined iron load bound to ferritin within activated microglial cells. This study provides critical evidence that R2* is a sensitive marker of inflammation secondary to network disconnection, potentially informing future neuroprotective strategies targeting remote brain regions after stroke.

neuroscience↗

bioRxiv2024

Benchmarking Stroke Outcome Prediction through Comprehensive Data Analysis - NeuralCup 2023

Stroke remains a leading cause of mortality and long-term disability worldwide, with variable recovery trajectories posing substantial challenges in anticipating post-event care and rehabilitation planning. To address these challenges, we established the NeuralCup consortium to benchmark predictive models of stroke outcome through a collaborative, data-driven approach. This study presents findings from 15 international teams who used a comprehensive dataset including clinical and imaging data, to identify and compare predictors of motor, cognitive, and emotional outcomes one year post-stroke. Our analyses integrated traditional statistical approaches and novel machine learning algorithms to uncover optimal recipes for predicting each domain. The differences in these optimal recipes reflect distinct brain mechanisms in response to different tasks. Key predictors across all domains included infarct characteristics, T1-weighted MRI sequences, and demographic factors. Additionally, integrating FLAIR imaging and white matter tract analysis significantly improved the prediction of cognitive and motor outcomes, respectively. These findings support a multifaceted approach to stroke outcome prediction, underscoring the potential of collaborative data science to develop personalized care strategies that enhance recovery and quality of life for stroke survivors. To encourage further model development and validation, we provide access to the training dataset at http://neuralcup.bcblab.com

neuroscience↗

bioRxiv2023

Dynamic evolution of infarct volumes at MRI in ischemic stroke due to large vessel occlusion

Background and ObjectivesThe typical infarct volume trajectories in stroke patients, categorized as slow or fast progressors, remain largely unknown. This study aimed to reveal the characteristic spatiotemporal evolutions of infarct volumes caused by large vessel occlusion (LVO) and show that such growth charts help anticipate clinical outcomes. MethodsWe conducted a secondary analysis from prospectively collected databases (FRAME, 2017- 2019; ETIS, 2015-2022). We selected acute MRI data from anterior LVO stroke patients with witnessed onset which were divided into training- and independent validation-datasets. In the training-dataset, using Gaussian mixture analysis, we classified the patients into three growth groups based on their rate of infarct growth (diffusion volume / time-to-imaging). Subsequently, we extrapolated pseudo-longitudinal models of infarct growth for each group and generated sequential frequency maps to highlight the spatial distribution of infarct growth. We used these charts to attribute a growth group to the independent patients from the validation-dataset. We compared their 3-month modified Rankin scale (mRS) with the predicted values based on a multivariable regression model from the training-dataset that used growth group as independent variable. ResultsWe included 804 patients (median age, 73.0 years [IQR, 61.2-82.0 years]; 409 men). The training-dataset revealed non-supervised clustering into 11% (74/703) slow, 62% (437/703) intermediate, and 27% (192/703) fast progressors. Infarct volume evolutions were best fitted with a linear (r=0.809; P<.001), cubic (r=0.471; P<.001), and power (r=0.63; P<.001) functions for the slow, intermediate and fast progressors, respectively. Notably, the deep nuclei and insular cortex were rapidly affected in the intermediate and fast groups with further cortical involvement in the fast group. The variable "growth group" significantly predicted 3-month mRS (multivariate OR, 0.51; 95% CI: 0.37-0.72, P<.0001) in the training-dataset, yielding a mean AUC of 0.78 (95% CI: 0.66-0.88) in the independent validation-dataset. ConclusionsWe revealed spatiotemporal archetype dynamic evolutions following large vessel occlusion stroke according to three growth phenotypes called slow, intermediate and fast progressors, providing insight into anticipating clinical outcome. We expect this could help in designing neuroprotective trials aiming at modulating infarct growth prior EVT.

pathology↗

bioRxiv2023

Deep Learning disconnectomes to accelerate and improve long-term predictions for post-stroke symptoms

Deep learning as a truly transformative force is revolutionizing a wide range of fields, making a significant difference in medical imaging, where recent advancements have yielded some truly remarkable outcomes. In a connected brain, maps of white matter damage -- otherwise known as disconnectomes -- are essential for capturing the effects of focal lesions. However, the current tools for obtaining such information are prohibitively slow and not admitted for clinical usage. Here, we have explored the potential of deep-learning models to accurately generate disconnectomes in a population of stroke survivors. We trained a 3D U-Net algorithm to produce deep-disconnectomes from binary lesion masks. This artificial neural network was able to capture most information obtained in conventional disconnectomes, i.e., statistical maps filtering normative white-matter networks, but output a deep-disconnectome 170 times faster - compared to disconnectome computation with the state-of-the-art BCBToolkit software. Moreover, the deep-disconnectomes were challenged to predict cognitive and behavioral outcomes one-year post-stroke. In an additional cohort of N=139 stroke survivors, N=86 neuropsychological scores were predicted from deep-disconnectomes achieving, on average, 85.2% of accuracy and R2= 0.208. The deep-disconnectomes predictivity power outperformed the conventional disconnectome predictions for clinical scores. In summary, we have achieved a significant milestone for clinical neuroimaging by accelerating and ameliorating the creation of disconnectome maps using deep learning. By integrating deep learning into the management of stroke, one of the most prevailing catalysts for acquired disabilities, we deepen our understanding of its impact on the brain. This novel approach may offer potential avenues for acute intervention, ultimately enhancing patients overall quality of life.

neuroscience↗

bioRxiv2023

Lifespan Neurodegeneration Of The Human Brain In Multiple Sclerosis

BackgroundAtrophy related to Multiple Sclerosis (MS) has been found at the early stages of the disease. However, the archetype dynamic trajectories of the neurodegenerative process, even prior to clinical diagnosis, remain unknown. MethodsWe modeled the volumetric trajectories of brain structures across the entire lifespan using 40944 subjects (38295 healthy controls and 2649 MS patients). Then, we estimated the chronological progression of MS by assessing the divergence of lifespan trajectories between normal brain charts and MS brain charts. ResultsChronologically, the first affected structure was the thalamus, then the putamen and the pallidum (3 years later), followed by the ventral diencephalon (7 years after thalamus) and finally the brainstem (9 years after thalamus). To a lesser extent, the anterior cingulate gyrus, insular cortex, occipital pole, caudate and hippocampus were impacted. Finally, the precuneus and accumbens nuclei exhibited a limited atrophy pattern. ConclusionSubcortical atrophy was more pronounced than cortical atrophy. The thalamus was the most impacted structure with a very early divergence in life. It paves the way toward utilization of these lifespan models for future preclinical/prodromal prognosis and monitoring of MS.

neuroscience↗

bioRxiv2018

Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure

We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-the-art algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning, ...), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.

neuroscience↗

bioRxiv2018

Multimodal Hippocampal Subfield Grading For Alzheimer’s Disease Classification

Numerous studies have proposed biomarkers based on magnetic resonance imaging (MRI) to detect and predict the risk of evolution toward Alzheimers disease (AD). While anatomical MRI captures structural alterations, studies demonstrated the ability of diffusion MRI to capture microstructural modifications at an earlier stage. Several methods have focused on hippocampus structure to detect AD. To date, the patch-based grading framework provides the best biomarker based on the hippocampus. However, this structure is complex since the hippocampus is divided into several heterogeneous subfields not equally impacted by AD. Former in-vivo imaging studies only investigated structural alterations of these subfields using volumetric measurements and microstructural modifications with mean diffusivity measurements. The aim of our work is to study the efficiency of hippocampal subfields compared to the whole hippocampus structure with a multimodal patch-based framework that enables to capture subtler structural and microstructural alterations. To this end, we analyze the significance of the different hippocampal subfields for AD diagnosis and prognosis with volumetric, diffusivity measurements and a novel multimodal patch-based grading framework that combines structural and diffusion MRI. The experiments conducted in this work showed that the whole hippocampus provides the most discriminant biomarkers for advanced AD detection while biomarkers applied into subiculum obtain the best results for AD prediction, improving by 2% the accuracy compared to the whole hippocampus.

neuroscience↗