Search Results (47)

Brain magnetic resonance imaging (MRI) is highly susceptible to motion artifacts that degrade fine structural details and undermine quantitative analysis. Conventional U-Net-based deep learning approaches for motion artifact reduction typically operate only in the image domain and are often trained on data with simplified motion patterns, thereby limiting physical plausibility and generalization. We propose Sim-DDNet, a simulation-data-based dual-domain network that combines k-space-based motion simulation with a joint image-k-space reconstruction architecture. Motion-corrupted data were generated from T2-weighted Alzheimer’s Disease Neuroimaging Initiative brain MR scans using a k-space replacement scheme with three to five random rotational and translational events per volume, yielding 69,283 paired samples (49,852/6969/12,462 for training/validation/testing). Sim-DDNet integrates a real-valued U-Net-like image branch and a complex-valued k-space branch using cross attention, FiLM-based feature modulation, soft data consistency, and composite loss comprising L1, structural similarity index measure (SSIM), perceptual, and k-space-weighted terms. On the independent test set, Sim-DDNet achieved a peak signal-to-noise ratio of 31.05 dB, SSIM of 0.85, and gradient magnitude similarity deviation of 0.077, consistently outperforming U-Net and U-Net++ across all three metrics while producing less blurring, fewer residual ghost/streak artifacts, and reduced hallucination of non-existent structures. These results indicate that dual-domain, data-consistency-aware learning, which explicitly exploits k-space information, is a promising approach for physically plausible motion artifact correction in brain MRI. Full article

Transitioning from theoretical learning to practical application remains a significant challenge for students in medical and veterinary science education, particularly in the context of medical imaging and ultrasound interpretation. Traditional lecture-based methods offer limited support for developing the spatial reasoning and technical skills required for ultrasound pregnancy diagnosis. This study evaluates the effectiveness of an interactive mixed reality (MR) training tool, Ewe Scan, delivered through the Apple Vision Pro, compared to traditional lecture-based instruction. Forty-two undergraduate students were randomly assigned to either a lecture-trained or MR-trained group and assessed immediately after training and again after six weeks. Results showed that MR-trained students significantly outperformed their lecture-trained peers in both immediate comprehension and retention over time, particularly in ultrasound interpretation skills. The MR-trained group also reported higher levels of engagement, confidence, and satisfaction with their training experience. These findings suggest that MR-based learning enhances educational outcomes by improving spatial understanding, increasing active engagement, and supporting knowledge retention. Integrating MR simulations into ultrasound education offers a scalable, ethical, and effective alternative to traditional training methods, contributing to advancements in medical imagery education. Full article

Background: Respiratory-induced target displacement remains a major challenge for achieving accurate and safe augmented-reality-guided thoracoabdominal percutaneous puncture. Existing approaches often suffer from system latency, dependence on intraoperative imaging, or the absence of intelligent timing assistance; Methods: We developed a mixed-reality (MR) surgical navigation system that incorporates Adaptive Kalman-filter-based respiratory prediction module and visual gating cues. The system was evaluated using a dynamic respiratory motion simulation platform. The Kalman filter performs real-time state estimation and short-term prediction of optically tracked respiratory motion, enabling simultaneous compensation for MR model drift and forecasting of the end-inhalation window to trigger visual guidance; Results: Compared with the uncompensated condition, the proposed system reduced dynamic registration error from (3.15 ± 1.23) mm to (2.11 ± 0.58) mm (p < 0.001). Moreover, the predicted guidance window occurred approximately 142 ms in advance with >92% accuracy, providing preparation time for needle insertion; Conclusions: The integrated MR system effectively suppresses respiratory-induced model drift and offers intelligent timing guidance for puncture execution. Full article

Purpose or Objective: To evaluate the feasibility and clinical utility of integrating sequential PSMA-PET imaging into an offline–online adaptive workflow for response-based dominant intraprostatic lesion (DIL)-boosting high-risk prostate cancer treated with stereotactic ablative radiotherapy (SABR). Materials and Methods: As part of a prospective trial, patients were treated on MR- or CBCT-guided adaptive radiotherapy (ART) systems with prostate/pelvic node 5-fraction SABR (36.25 Gy/25 Gy) with DIL boost (50 Gy). Whereas traditional DIL boost volumes delineate full pre-therapy imaging-defined disease (GTVinitial), this study serially refined DIL boost volumes based on treatment response defined by PSMA-PET scans after neoadjuvant androgen deprivation therapy (nADT, GTVmb1) and fraction 3 SABR (GTVmb2). DIL delineation employed PET-PSMA fusion to CT/MR simulation and was guided by a rule-based %SUVmax threshold approach. Comparisons of GTV volumes and OAR dosimetry were performed between plans using GTVinitial versus GTVmb1/GTVmb2 for DIL boost, for each of the initial cohorts of five patients from the initially treated cohorts. Results: Five patients treated on MR-Linac (n = 3) or CBCT-based ART (n = 2) were analyzed. Three patients exhibited complete imaging response after nADT, omitting GTVmb boosts. Offline GTVmb refinements based on PSMA-PET were seamlessly integrated into ART workflows without introducing additional treatment time. DIL GTV volumes significantly decreased (p = 0.03) from an initial mean of 11.4 cc (GTVinitial) to 4.1 cc (GTVmb1) and 3.0 cc (GTVmb2). Dosimetric analysis showed meaningful reductions in OAR doses: rectal wall D0.035 cc decreased by up to 12 Gy, while bladder wall D0.035 cc and V18.3 Gy reduced from 52.3 Gy and 52.3 cc (Plan_initial) to 42.9 Gy and 24.9 cc (Plan_mb2), respectively. Urethra doses remained stable, with minor reductions. Sigmoid and femoral head doses remained within acceptable limits. Online adaptation efficiently addressed daily anatomical variations, enabling simulation-free plan re-optimization. Conclusion: PSMA-PET-guided adaptive microboosting for HRPCa SABR is feasible and effective. Standard MR-Linac and CBCT systems offer practical alternatives to BgRT platforms, enabling biology-driven dose personalization and potentially reducing toxicity. Full article

Background: Stereotactic body radiation therapy (SBRT) has proven effective in controlling spinal lesions with minimal toxicity, primarily due to its ability to limit spinal cord dose. Recent advances in MR-linac (MRL) technology offer superior spinal cord visualization and real-time gating, which can facilitate dose escalation in spinal tumor treatment while maintaining safety. Purpose: This study aimed to optimize motion management for spine SBRT on an MRL by analyzing patient-specific motion dynamics and evaluating the most effective registration structures. We hypothesized that baseline shifts (BLS) would improve delivery efficiency while maintaining spinal cord dose constraints. The goal was to establish displacement thresholds and assess the role of baseline shift correction adaptative planning in improving treatment delivery efficiency. Methods: Twelve patients underwent two MRI sessions on the MRL. The optimal registration structure was identified, and intrafraction motion was assessed to calculate delivery efficiency. Baseline shift (BLS) simulations were applied for five cases that showed significant motion and suboptimal delivery efficiency, and the dosimetric impact of the BLS was evaluated. The simulated BLS-based plan adaptation was implemented via a segment aperture morphing adapt-to-position workflow. Results: The most stable registration structure was the spinal canal plus three adjacent vertebrae. Cine imaging revealed average intrafraction motion (95th to 5th percentiles) of 0.8 ± 0.5 mm in the right-left (RL) direction, 0.9 ± 0.6 mm in the anterior–posterior (AP) direction, and 0.7 ± 0.5 mm in the SI direction. Simulated BLS improved delivery efficiency to >80% in all but one case, with a ±1 mm displacement threshold tolerance. While target coverage remained consistent after BLS simulation, the spinal cord dose increased by 7–60%, exceeding the 14 Gy constraint in three of the five simulated cases. Conclusions: Cine imaging and BLS can enhance delivery efficiency in spine SBRT but may increase spinal cord dose. These findings underscore the need for careful patient selection, advanced motion management, and patient-specific BLS protocols. Full article

Glutamate, the primary excitatory neurotransmitter in the central nervous system, plays a pivotal role in synaptic signaling, learning, and memory. Abnormal glutamate levels are implicated in various neurological disorders, including epilepsy, Alzheimer’s disease, and ischemic stroke. Despite the utility of magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) in diagnosing such conditions, the development of effective glutamate-sensitive contrast agents remains a challenge. In this study, we present ultrasmall, citric acid-coated superparamagnetic iron oxide nanoparticles (CA-SPIONs) as highly selective and sensitive MRS probes for glutamate detection. These 5 nm magnetite CA-SPIONs exhibit a stable dispersion in physiological buffers and undergo aggregation in the presence of glutamate, significantly enhancing the T₂ MRS contrast power. At physiological glutamate levels, the CA-SPIONs yielded a pronounced signal change ratio of nearly 60%, while showing a negligible response to other neurotransmitters such as GABA and dopamine. Computational simulations confirmed the mechanism of glutamate-mediated aggregation and its impact on transversal relaxation rates and relaxivities. The sensitivity and selectivity of CA-SPIONs underscore their potential as eco-friendly, iron-based alternatives for future neurological sensing applications targeting glutamatergic dysfunction. Full article

Background: Low-field Magnetic Resonance Imaging (MRI) (fields below 0.5 T) has received increasing attention since the images produced have been shown to be diagnostically equivalent to high-field MR images for specific applications, such as musculoskeletal studies. In recent years, low-field MRI has made great strides in clinical relevance due to advances in high-performance gradients, magnet technology, and the development of organ-specific radiofrequency (RF) coils, as well as advances in acquisition sequence design. For achieving optimized image homogeneity and signal-to-noise Ratio (SNR), the design and simulation of dedicated RF coils is a constraint both in clinical and in many research studies. Methods: This paper describes the application of a numerical full-wave method based on the finite-difference time-domain (FDTD) algorithm for the simulation and the design of birdcage coils for musculoskeletal low-field MRI. In particular, the magnetic field pattern in loaded and unloaded conditions was investigated. Moreover, the magnetic field homogeneity variations and the coil detuning after an RF shield insertion were evaluated. Finally, the coil inductance and the sample-induced resistance were estimated. Results: The accuracy of the results was verified by data acquired from two lowpass birdcage prototypes designed for musculoskeletal experiments on a 0.18 T open MR clinical scanner. Conclusions: This work describes the capability of numerical simulations to design RF coils for various scenarios, including the presence of electromagnetic shields and different load conditions. Full article

Background: Intra-arterial cerebral infusion (IACI) of radiotherapeutics is a promising treatment for glioblastoma (GBM) recurrence. We investigated the in silico feasibility and safety of Yttrium-90-Poly(vinyl alcohol)-Microbubble (⁹⁰Y-PVA-MB) IACI in patients with recurrent GBM and compared the results with those of external beam radiation therapy (EBRT). Methods: Contrast-enhanced T1-weighted magnetic resonance imaging (T1W-MRI) was used to delineate the tumor volumes and CT scans were used to automatically segment the organs at risk in nine patients with recurrent GBM. Volumetric Modulated Arc Therapy (VMAT) treatment plans were generated using a clinical treatment planning system. Assuming the relative intensity of each voxel from the MR-T1W as a valid surrogate for the post-IACI ⁹⁰Y-PVA-MB distribution, a specific ⁹⁰Y dose voxel kernel was obtained through Monte Carlo (MC) simulations and convolved with the MRI, resulting in a ⁹⁰Y-PVA-MB-based dose distribution that was then compared with the VMAT plans. Results: The physical dose distribution obtained from the simulation of 1GBq of ⁹⁰Y-PVA-MBs was rescaled to ensure that 95% of the prescribed dose was delivered to 95% or 99% of the target (i.e., A95% and A99%, respectively). The calculated activities were A95% = 269.2 [63.6–2334.1] MBq and A99% = 370.6 [93.8–3315.2] MBq, while the mean doses to the target were 58.2 [58.0–60.0] Gy for VMAT, and 123.1 [106.9–153.9] Gy and 170.1 [145.9–223.8] Gy for A95% and A99%, respectively. Additionally, non-target brain tissue was spared in the ⁹⁰Y-PVA-MB treatment compared to the VMAT approach, with a median [range] of mean doses of 12.5 [12.0–23.0] Gy for VMAT, and 0.6 [0.2–1.0] Gy and 0.9 [0.3–1.5] Gy for the ⁹⁰Y treatments assuming A95% and A99%, respectively. Conclusions: ⁹⁰Y-PVA-MB IACI using MR-T1W appears to be feasible and safe, as it enables the delivery of higher doses to tumors and lower doses to non-target volumes compared to the VMAT approach. Full article

In recent years, synthetic Computed Tomography (CT) images generated from Magnetic Resonance (MR) or Cone Beam Computed Tomography (CBCT) acquisitions have been shown to be comparable to real CT images in terms of dose computation for radiotherapy simulation. However, until now, there has been no independent strategy to assess the quality of each synthetic image in the absence of ground truth. In this work, we propose a Deep Learning (DL)-based framework to predict the accuracy of synthetic CT in terms of Mean Absolute Error (MAE) without the need for a ground truth (GT). The proposed algorithm generates a volumetric map as an output, informing clinicians of the predicted MAE slice-by-slice. A cascading multi-model architecture was used to deal with the complexity of the MAE prediction task. The workflow was trained and tested on two cohorts of head and neck cancer patients with different imaging modalities: 27 MR scans and 33 CBCT. The algorithm evaluation revealed an accurate HU prediction (a median absolute prediction deviation equal to 4 HU for CBCT-based synthetic CTs and 6 HU for MR-based synthetic CTs), with discrepancies that do not affect the clinical decisions made on the basis of the proposed estimation. The workflow exhibited no systematic error in MAE prediction. This work represents a proof of concept about the feasibility of synthetic CT evaluation in daily clinical practice, and it paves the way for future patient-specific quality assessment strategies. Full article

Radiomics, which integrates the comprehensive characterization of imaging phenotypes with machine learning algorithms, is increasingly recognized for its potential in the diagnosis and prognosis of oncological conditions. However, the repeatability and reproducibility of radiomic features are critical challenges that hinder their widespread clinical adoption. This review aims to address the paucity of discussion regarding the factors that influence the reproducibility and repeatability of radiomic features and their subsequent impact on the application of radiomic models. We provide a synthesis of the literature on the repeatability and reproducibility of CT/MR-based radiomic features, examining sources of variation, the number of reproducible features, and the availability of individual feature repeatability indices. We differentiate sources of variation into random effects, which are challenging to control but can be quantified through simulation methods such as perturbation, and biases, which arise from scanner variability and inter-reader differences and can significantly affect the generalizability of radiomic model performance in diverse settings. Four suggestions for repeatability and reproducibility studies are suggested: (1) detailed reporting of variation sources, (2) transparent disclosure of calculation parameters, (3) careful selection of suitable reliability indices, and (4) comprehensive reporting of reliability metrics. This review underscores the importance of random effects in feature selection and harmonizing biases between development and clinical application settings to facilitate the successful translation of radiomic models from research to clinical practice. Full article

Quantitative and objective evaluation tools are essential for assessing the performance of machine learning (ML)-based magnetic resonance imaging (MRI) reconstruction methods. However, the commonly used fidelity metrics, such as mean squared error (MSE), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR), often fail to capture fundamental and clinically relevant MR image quality aspects. To address this, we propose evaluation of ML-based MRI reconstruction using digital image quality phantoms and automated evaluation methods. Our phantoms are based upon the American College of Radiology (ACR) large physical phantom but created in k-space to simulate their MR images, and they can vary in object size, signal-to-noise ratio, resolution, and image contrast. Our evaluation pipeline incorporates evaluation metrics of geometric accuracy, intensity uniformity, percentage ghosting, sharpness, signal-to-noise ratio, resolution, and low-contrast detectability. We demonstrate the utility of our proposed pipeline by assessing an example ML-based reconstruction model across various training and testing scenarios. The performance results indicate that training data acquired with a lower undersampling factor and coils of larger anatomical coverage yield a better performing model. The comprehensive and standardized pipeline introduced in this study can help to facilitate a better understanding of the performance and guide future development and advancement of ML-based reconstruction algorithms. Full article

The inevitable noise generated in the acquisition and transmission process of MRIs seriously affects the reliability and accuracy of medical research and diagnosis. The denoising effect for Rician noise, whose distribution is related to MR image signal, is not good enough. Furthermore, the brain has a complex texture structure and a small density difference between different parts, which leads to higher quality requirements for brain MR images. To upgrade the reliability and accuracy of brain MRIs application and analysis, we designed a new and dedicated denoising algorithm (named VST–MCAATE), based on their inherent characteristics. Comparative experiments were performed on the same simulated and real brain MR datasets. The peak signal-to-noise ratio (PSNR), and mean structural similarity index measure (MSSIM) were used as objective image quality evaluation. The one-way ANOVA was used to compare the effects of denoising between different approaches. p < 0.01 was considered statistically significant. The experimental results show that the PSNR and MSSIM values of VST–MCAATE are significantly higher than state-of-the-art methods (p < 0.01), and also that residual images have no anatomical structure. The proposed denoising method has advantages in improving the quality of brain MRIs, while effectively removing the noise with a wide range of unknown noise levels without damaging texture details, and has potential clinical promise. Full article

This study aimed to remove motion artifacts from brain magnetic resonance (MR) images using a U-Net model. In addition, a simulation method was proposed to increase the size of the dataset required to train the U-Net model while avoiding the overfitting problem. The volume data were rotated and translated with random intensity and frequency, in three dimensions, and were iterated as the number of slices in the volume data. Then, for every slice, a portion of the motion-free k-space data was replaced with motion k-space data, respectively. In addition, based on the transposed k-space data, we acquired MR images with motion artifacts and residual maps and constructed datasets. For a quantitative evaluation, the root mean square error (RMSE), peak signal-to-noise ratio (PSNR), coefficient of correlation (CC), and universal image quality index (UQI) were measured. The U-Net models for motion artifact reduction with the residual map-based dataset showed the best performance across all evaluation factors. In particular, the RMSE, PSNR, CC, and UQI improved by approximately 5.35×, 1.51×, 1.12×, and 1.01×, respectively, and the U-Net model with the residual map-based dataset was compared with the direct images. In conclusion, our simulation-based dataset demonstrates that U-Net models can be effectively trained for motion artifact reduction. Full article

Unmanned aerial vehicle technology is the most advanced and helpful in almost every area of interest in human work. These devices become autonomous and can fulfil a variety of tasks, from simple imaging and obtaining data to search and rescue operations. The most challenging environment for search and rescue operations is the mountainous area. This article is devoted to the theoretical description and simulation tests of a prototype method of landing the light and the medium-weight UAVs used as supplementary devices for SAR (search and rescue) and HEMS (helicopter emergency medical service) in hard-to-reach mountainous terrains. The autonomous flight of a UAV in mountainous terrain has many specifics, and it is usually performed according to predetermined map points (pins) uploaded directly into the control software of the UAV. It is necessary to characterise each point flown on the chosen flight route line in advance and therefore to know its exact geographical coordinates (longitude, latitude and height of the point above the terrain), and the control system of UAV must react to the change in the weather and other conditions in real time. Usually, it is difficult to make this forecast with sufficient time in advance, mainly when UAVs are used as supplementary devices for the needs of HEMS or MRS (mountain rescue service). The most challenging phase is the final approach and landing of the UAV, especially if a loss of GNSS (global navigation satellite system) signal occurs, like in the determined area of the Little Cold Valley in the Slovak High Tatras—which is infamous for the widespread loss of GNSS signals or communication/controlling connection between the UAV and the pilot-operator at the operational station. To solve the loss of guidance, a new method for guiding and controlling the UAV in its final approach and landing in a determined area is tested. An alternative landing navigation system for UAVs in a specific mountainous environment—the authors’ designed frequency Doppler landing system (FDLS)—is briefly described but thoroughly tested with the help of artificial intelligence. An estimation of dynamic stability is used based on the time recording of the current position of the UAV, with the help of a frequency-modulated or amplitude-modulated signal based on the author’s prototype of a precision landing system designed for mountainous terrain. This solution could overcome the problems of GNSS signal loss. The presented research primarily evaluates the success of the simulation flights for the supplementary UAV. The success of navigating the UAV to land in the mountainous environment at an exact landing point using the navigation signals from the FDLS was evaluated at more than 95%. Full article

The potential improvement in sonication efficiency achieved by tilting the focused ultrasound (FUS) transducer of the transcranial MR-guided FUS system is presented. A total of 56 cases of patient treatment data were used. The relative position of the clinical FUS transducer to the patient’s head was reconstructed, and region-specific skull density and porosity were calculated based on the patient’s CT volume image. The total transmission coefficient of acoustic waves emitted from each channel was calculated. Then, the total energy penetrating the human skull—which represents the sonication efficiency—was estimated. As a result, improved sonication efficiency was by titling the FUS transducer to a more appropriate angle achieved in all 56 treatment cases. This simulation result suggests the potential improvement in transcranial-focused ultrasound treatment by simply adjusting the transducer angle. Full article