arXiv subjects

Ekaterina Brui

Publications and source records attributed to Ekaterina Brui.

4 recordsLinked to original sources

arXiv2026

Physics-informed self-supervised generation of digital brain MRI phantoms from weighted images using differentiable MRI simulation

Purpose: To develop a physics-informed, self-supervised framework for generating digital brain MRI phantoms directly from conventional weighted MR images without requiring ground-truth parametric maps or anatomical segmentation. Methods: The framework predicts T1, T2, and proton density (PD) maps from T1-, T2-, and PD-weighted images and reconstructs the input images through an MRI signal model. Three generative architectures (variational autoencoder (VAE), generative adversarial network (GAN), and flow-based model) were compared. Models were pretrained on 3,739 synthetic brain slices generated using digital phantoms and an analytical MRI signal model, followed by fine-tuning on 90 real brain slices from three healthy volunteers. The best-performing architecture was subsequently fine-tuned using the differentiable MR-Zero numerical MRI simulator and evaluated on 30 held-out real slices. Results: The flow-based model demonstrated the highest overall performance and preserved fine anatomical details better than the VAE and GAN. After analytical-model fine-tuning, it achieved MS-SSIM values of 0.955-0.985 and PSNR values of 26.68-32.63 dB across T1-, T2-, and PD-weighted images. Fine-tuning with MR-Zero increased T1-weighted reconstruction quality from 0.955 to 0.977 (MS-SSIM) and from 26.68 to 30.60 dB (PSNR), and provided high robustness of metrics across different MR image weightings. The resulting digital phantoms also enabled simulation of images using previously unseen acquisition protocols. Conclusion: The proposed framework enables physics-informed generation of reusable digital brain MRI phantoms from weighted images using limited real-world data. Combining synthetic pretraining with differentiable numerical MRI simulation provides a practical approach for physically grounded MRI data augmentation without requiring reference parametric maps.

physics.med-ph↗

arXiv2022

CNN-based fully automatic wrist cartilage volume quantification in MR Image

Detection of cartilage loss is crucial for the diagnosis of osteo- and rheumatoid arthritis. A large number of automatic segmentation tools have been reported so far for cartilage assessment in magnetic resonance images of large joints. As compared to knee or hip, wrist cartilage has a more complex structure so that automatic tools developed for large joints are not expected to be operational for wrist cartilage segmentation. In that respect, a fully automatic wrist cartilage segmentation method would be of high clinical interest. We assessed the performance of four optimized variants of the U-Net architecture with truncation of its depth and addition of attention layers (U-Net_AL). The corresponding results were compared to those from a patch-based convolutional neural network (CNN) we previously designed. The segmentation quality was assessed on the basis of a comparative analysis with manual segmentation using several morphological (2D DSC, 3D DSC, precision) and a volumetric metrics. The four networks outperformed the patch-based CNN in terms of segmentation homogeneity and quality. The median 3D DSC value computed with the U-Net_AL (0.817) was significantly larger than the corresponding DSC values computed with the other networks. In addition, the U-Net_AL CNN provided the lowest mean volume error (17%) and the highest Pearson correlation coefficient (0.765) with respect to the ground truth. Of interest, the reproducibility computed from using U-Net_AL was larger than the reproducibility of the manual segmentation. U-net convolutional neural network with additional attention layers provides the best wrist cartilage segmentation performance. In order to be used in clinical conditions, the trained network can be fine-tuned on a dataset representing a group of specific patients. The error of cartilage volume measurement should be assessed independently using a non-MRI method.

eess.IV↗

arXiv2020

Deep learning-based fully automatic segmentation of wrist cartilage in MR images

The study objective was to investigate the performance of a dedicated convolutional neural network (CNN) optimized for wrist cartilage segmentation from 2D MR images. CNN utilized a planar architecture and patch-based (PB) training approach that ensured optimal performance in the presence of a limited amount of training data. The CNN was trained and validated in twenty multi-slice MRI datasets acquired with two different coils in eleven subjects (healthy volunteers and patients). The validation included a comparison with the alternative state-of-the-art CNN methods for the segmentation of joints from MR images and the ground-truth manual segmentation. When trained on the limited training data, the CNN outperformed significantly image-based and patch-based U-Net networks. Our PB-CNN also demonstrated a good agreement with manual segmentation (Sorensen-Dice similarity coefficient (DSC) = 0.81) in the representative (central coronal) slices with large amount of cartilage tissue. Reduced performance of the network for slices with a very limited amount of cartilage tissue suggests the need for fully 3D convolutional networks to provide uniform performance across the joint. The study also assessed inter- and intra-observer variability of the manual wrist cartilage segmentation (DSC=0.78-0.88 and 0.9, respectively). The proposed deep-learning-based segmentation of the wrist cartilage from MRI could facilitate research of novel imaging markers of wrist osteoarthritis to characterize its progression and response to therapy.

physics.med-ph↗

arXiv2017

Small animal whole body imaging with metamaterial-inspired RF coil

Preclinical magnetic resonance imaging often requires the entire body of an animal to be imaged with sufficient quality. This is usually performed by combining regions scanned with small coils with high sensitivity or long scans using large coils with low sensitivity. Here, a metamaterial-inspired design employing of a parallel array of wires operating on the principle of eigenmode hybridization is used to produce a small animal whole-body imaging coil. The coil field distribution responsible for the coil field of view and sensitivity is simulated in an electromagnetic simulation package and the coil geometrical parameters are optimized for the chosen application. A prototype coil is then manufactured and assembled using brass telescopic tubes and copper plates as distributed capacitance, its field distribution is measured experimentally using B1+ mapping technique and found to be in close correspondence with simulated results. The coil field distribution is found to be suitable for whole-body small animal imaging and coil image quality is compared with a number of commercially available coils by whole-body living mice scanning. Signal to noise measurements in living mice show outstanding coil performance compared to commercially available coils with large receptive fields, and rivaling performance compared to small receptive field and high-sensitivity coils. The coil is deemed suitable for whole-body small animal preclinical applications.

physics.ins-det↗