Biology subjects

Pieciak, T.

Publications and source records attributed to Pieciak, T..

7 recordsLinked to original sources

bioRxiv2026

Clinical relevance of diffusion tensor imaging-based parameters estimated with deep learning: the effect of model retraining

Deep learning (DL)-based approaches have recently become powerful tools for characterizing microstructural properties of brain tissue from diffusion-weighted magnetic resonance imaging data. These techniques enable depicting microstructural features with significantly reduced acquisition schemes while preserving relatively high image-quality metrics compared with non-DL-based approaches. Learning-based methods have increasingly been applied to diffusion tensor imaging (DTI) and more advanced multi-compartmental biophysical models, with the potential to facilitate multiparameter analyses of brain microstructure in clinical settings. However, independently trained DL models-while maintaining image-quality properties-do not appear to preserve the statistical properties of groupwise analyses across independently trained models. In this study, we systematically evaluate the statistical properties of DL-based DTI parameters across independently trained neural networks under the same architecture to preserve group-level effects in bipolar disorder. We examine the impact of model retraining and its dependence on reducing the number of gradient directions compared with the nonlinear least-squares (NLLS) procedure. Our results show that initializing model weights randomly from a uniform distribution, while keeping the network architecture and training hyperparameters the identical in the experiment, leads to significant variation in the statistical properties of DTI measures inferred from independently trained models. The analyses showed that the true positive rate in groupwise analysis using the DL-based DTI parameters ranges from 0\% to 100\% compared with the NLLS-based analysis. As the number of gradient directions increased, the NLLS procedure yielded more stable groupwise statistical results, whereas independently trained DL models showed greater variability despite similar image-quality agreement with reference maps. The results indicate that the DTI maps retrieved from a single trained network should be treated with great caution before drawing clinical conclusions.

neuroscience↗

bioRxiv2026

A multi-b-value test-retest diffusion MRI brain dataset for model validation and reproducibility assessment

Transparent assessment of diffusion magnetic resonance imaging (dMRI) techniques with empirical verification of confounding factors requires adequately designed protocols and collected datasets. Publicly available diffusion-weighted MR datasets often provide limited sampling across b-values, making it difficult to study optimal acquisition protocols or the relationships between different processes occurring in brain tissue. In this work, we introduce a new densely sampled longitudinal test-retest diffusion-weighted MR dataset of the brain. Our dataset was collected from eleven healthy volunteers, each scanned four times: two sessions on consecutive days, which form the test data, followed by two additional sessions completed one week later (retest data). The data were acquired using twenty-two b-values ranging from 10 to 3000 s/mm2, along with structural T1-weighted scans. Potential applications of the dataset include, but are not limited to, assessing longitudinal reproducibility and reliability of quantitative metrics, evaluating robust and outlier-resistant estimation techniques, investigating experimental factors affecting estimation procedures, and verifying optimal acquisition protocols for different signal models. The dataset is publicly available in raw and fully preprocessed variants.

neuroscience↗

bioRxiv2025

Reproducibility and reliability of Free-Water-corrected Diffusion Tensor Imaging of the brain: Revisited

Diffusion tensor imaging (DTI) corrected for the free-water (FW) enables the separation of a hindered Gaussian-like profile from an isotropic component, which represents diffusion found in cerebrospinal and interstitial fluids within the extracellular space of grey and white matter. The assessment of the reproducibility and reliability properties of FW-corrected DTI is a crucial factor in demonstrating the potential clinical utility of this refinement, particularly considering the examinations across multiple medical centres. This paper explores the variability, reliability, and separability properties of free-water volume fraction (FWVF) and FW-corrected DTI-based measures in healthy human brain white matter using publicly available test-retest databases acquired in 1) intra-scanner, 2) intra-scanner longitudinal and 3) inter-scanner settings under varying acquisition schemes. Three different estimation techniques to retrieve the FW-corrected DTI parameters tailored to single- or multiple-shell diffusion-sensitizing magnetic resonance (MR) acquisitions are investigated: i) a direct optimization of bi-tensor signal representation in the variational framework, ii) the region contraction-based approach, and iii) the spherical means technique combined with a correction of diffusion-weighted MR signal prior to DTI estimation. We found the previous suggestion (Hum. Brain Mapp., 38(1), 2017, 10.1002/hbm.23350) that the FW correction to DTI in a single-shell diffusion-weighted MR acquisition improves the repeatability and reliability of DTI-based measures may be data- and methodology-dependent, and does not generalise to multiple-shell scenario. Our experiments have shown that the most reliable and repeatable/reproducible measures, while preserving a moderate separability property, are fractional anisotropy and axial diffusivity estimated in a multiple-shell variant under a combined FW-correction scheme. On the contrary, our results show evidence that the least reliable measures are the mean diffusivity estimated using any FW-correction procedure, as well as the FWVF parameter itself. These results can be used to establish the direction for selecting the most attractive FW-correction DTI scheme for clinical applications in terms of the variability-reliability-separability criterion.

bioengineering↗

bioRxiv2025

Validation of ten federated learning strategies for multi-contrast image-to-image MRI data synthesis from heterogeneous sources

Deep learning (DL)-based image synthesis has recently gained enormous interest in medical imaging, allowing for generating multi-contrast data and therefore, the recovery of missing samples from interrupted or artefact-distorted acquisitions. However, the accuracy of DL models heavily relies on the representativeness of the training datasets naturally characterized by their distributions, experimental setups or preprocessing schemes. These complicate generalizing DL models across multi-site heterogeneous data sets while maintaining the confidentiality of the data. One of the possible solutions is to employ federated learning (FL), which enables the collaborative training of a DL model in a decentralized manner, demanding the involved sites to share only the characteristics of the models without transferring their sensitive medical data. The paper presents a DL-based magnetic resonance (MR) data translation in a FL way. We introduce a new aggregation strategy called FedBAdam that couples two state-of-the-art methods with complementary strengths by incorporating momentum in the aggregation scheme and skipping the batch normalization layers. The work comprehensively validates 10 FL-based strategies for an image-to-image multi-contrast MR translation, considering healthy and tumorous brain scans from five different institutions. Our study has revealed that the FedBAdam shows superior results in terms of mean squared error and structural similarity index over personalized methods, like the FedMRI, and standard FL-based aggregation techniques, such as the FedAvg or FedProx, considering multi-site multi-vendor heterogeneous environment. The FedBAdam has prevented the overfitting of the model and gradually reached the optimal model parameters, exhibiting no oscillations.

bioengineering↗

bioRxiv2022

Free-water volume fraction increases non-linearly with age in the white matter of the healthy human brain

The term free-water volume fraction (FWVF) refers to the cerebrospinal and interstitial fluids in the extracellular space of the white matter (WM) of the brain, which has been demonstrated as a sensitive biomarker that correlates with the cognitive performance and the neuropathological processes modifying the interstitial extracellular spaces. It can be quantified by properly fitting the isotropic compartment of the magnetic resonance (MR) signal in diffusion-sensitized sequences. Using N = 287 healthy subjects aged 25-94, this study examines in detail the evolution of the FWVF in the human brain WM across the adult lifespan, which has been previously reported to exhibit a positive trend. We found evidence of a noticeably non-linear gain after the sixth decade of life, with a region-specific variate and varying change rate of the FWVF parameter with age, at the same time a heteroskedastic pattern across the adult lifespan is suggested. On the other hand, the FW-compensated MR signal leads to a region-dependent flattened age-related evolution of the mean diffusivity (MD) and fractional anisotropy (FA), along with a considerable reduction in their variability, as compared to standard studies conducted over the raw MR signal. This way, our study provides a new perspective on the trajectory-based assessment of the brain and explains the source of the variations observed in FA and MD parameters across the lifespan with previous studies with the standard diffusion tensor imaging.

neuroscience↗

bioRxiv2021

On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types: chronicles of the MEMENTO challenge.

Diffusion MRI (dMRI) has become an invaluable tool to assess the microstructural organization of brain tissue. Depending on the specific acquisition settings, the dMRI signal encodes specific properties of the underlying diffusion process. In the last two decades, several signal representations have been proposed to fit the dMRI signal and decode such properties. Most methods, however, are tested and developed on a limited amount of data, and their applicability to other acquisition schemes remains unknown. With this work, we aimed to shed light on the generalizability of existing dMRI signal representations to different diffusion encoding parameters and brain tissue types. To this end, we organized a community challenge - named MEMENTO, making available the same datasets for fair comparisons across algorithms and techniques. We considered two state-of-the-art diffusion datasets, including single-diffusion-encoding (SDE) spin-echo data from a human brain with over 3820 unique diffusion weightings (the MASSIVE dataset), and double (oscillating) diffusion encoding data (DDE/DODE) of a mouse brain including over 2520 unique data points. A subset of the data sampled in 5 different voxels was openly distributed, and the challenge participants were asked to predict the remaining part of the data. After one year, eight participant teams submitted a total of 80 signal fits. For each submission, we evaluated the mean squared error, the variance of the prediction error and the Bayesian information criteria. Most predictions predicted either multi-shell SDE data (37%) or DODE data (22%), followed by cartesian SDE data (19%) and DDE (18%). Most submissions predicted the signals measured with SDE remarkably well, with the exception of low and very strong diffusion weightings. The prediction of DDE and DODE data seemed more challenging, likely because none of the submissions explicitly accounted for diffusion time and frequency. Next to the choice of the model, decisions on fit procedure and hyperparameters play a major role in the prediction performance, highlighting the importance of optimizing and reporting such choices. This work is a community effort to highlight strength and limitations of the field at representing dMRI acquired with trending encoding schemes, gaining insights into how different models generalize to different tissue types and fiber configurations over a large range of diffusion encodings.

neuroscience↗

bioRxiv2019

Microstructure Diffusion Scalar Measures from Reduced MRI Acquisitions

In diffusion MRI, the Ensemble Average diffusion Propagator (EAP) provides relevant microstructural information and meaningful descriptive maps of the white matter previously obscured by traditional techniques like the Diffusion Tensor. The direct estimation of the EAP, however, requires a dense sampling of the Cartesian q-space. Due to the huge amount of samples needed for an accurate reconstruction, more efficient alternative techniques have been proposed in the last decade. Even so, all of them imply acquiring a large number of diffusion gradients with different b-values. In order to use the EAP in practical studies, scalar measures must be directly derived, being the most common the return-to-origin probability (RTOP) and the return-to-plane and return-to-axis probabilities (RTPP, RTAP).\n\nIn this work, we propose the so-called \"Apparent Measures Using Reduced Acquisitions\" (AMURA) to drastically reduce the number of samples needed for the estimation of diffusion properties. AMURA avoids the calculation of the whole EAP by assuming the diffusion anisotropy is roughly independent from the radial direction. With such an assumption, and as opposed to common multi-shell procedures based on iterative optimization, we achieve closed-form expressions for the measures using information from one single shell. This way, the new methodology remains compatible with standard acquisition protocols commonly used for HARDI (based on just one b-value). We report extensive results showing the potential of AMURA to reveal microstructural properties of the tissues compared to state of the art EAP estimators, and is well above that of Diffusion Tensor techniques. At the same time, the closed forms provided for RTOP, RTPP, and RTAP-like magnitudes make AMURA both computationally efficient and robust.

neuroscience↗