3D Magnetic Resonance Imaging Research Articles

Fast BET Based on Pre-Processing Evolution Using Global Mean Inter-Vertex Distance of Deformable Surface for MRI Brain Extraction

As a method based on the deformable surface evolution, brain extraction tools (BET) is widely used for brain extraction on cranial 3D magnetic resonance (MR) images. BET iteratively applies an evolution model depending on local parameters to the deformable surface until it reaches the brain border. In this paper, we propose a modified BET based on the fast model introducing a global parameter, the global mean inter-vertex distance of deformable surface. The surface evolution consists of two steps driven by two models: pre-processing step by the fast model and major step by the original model. We demonstrated our method in the experiments with T1-weighted and diffusion weighted MR images of 19 normal subjects. The modified BET converged within 300 iterations less than half of about 1000 iterations in the original BET, while reducing substantially the false negative regions and self-intersections. The proposed method may be efficient for high resolution images and large-scale studies.

Image quality in three-dimensional (3D) contrast-enhanced dynamic magnetic resonance imaging of the abdomen using deep learning denoising technique: intraindividual comparison between T1-weighted sequences with compressed sensing and with a modified Fast 3D mode wheel.

To assess the image quality of a modified Fast three-dimensional (Fast 3D) mode wheel with sequential data filling (mFast 3D wheel) combined with a deep learning denoising technique (Advanced Intelligent Clear-IQ Engine [AiCE]) in contrast-enhanced (CE) 3D dynamic magnetic resonance (MR) imaging of the abdomen during a single breath hold (BH) by intra-individual comparison with compressed sensing (CS) with AiCE. Forty-two patients who underwent multiphasic CE dynamic MRI obtained with both mFast 3D wheel using AiCE and CS using AiCE in the same patient were retrospectively included. The conspicuity, artifacts, image quality, signal intensity ratio (SIR), signal-to-noise ratio (SNR), contrast ratio (CR), and contrast enhancement ratio (CER) of the organs were compared between these 2 sequences. Conspicuity, artifacts, and overall image quality were significantly better in the mFast 3D wheel using AiCE than in the CS with AiCE (all p < 0.001). The SNR of the liver in CS with AiCE was significantly better than that in the mFast 3D wheel using AiCE (p < 0.01). There were no significant differences in the SIR, CR, and CER between the two sequences. A mFast 3D wheel using AiCE as a deep learning denoising technique improved the conspicuity of abdominal organs and intrahepatic structures and the overall image quality with sufficient contrast enhancement effects, making it feasible for BH 3D CE dynamic MR imaging of the abdomen.

Robotic Pedicle Screw Placement with 3D MRI Registration: Moving Towards Radiation Free Robotic Spine Surgery

BACKGROUND CONTEXTPreoperative imaging for lumbar spine surgery often includes magnetic resonance imaging (MRI) for soft tissues and computer tomography (CT) for bony detail. While CT scans expose patients to ionizing radiation, whereas MRI scans do not. Emerging MRI techniques allow CT-like three-dimensional (3D) visualization of bony structures, potentially removing the need for ionizing radiation from CT scans. PURPOSEThis study aims to explore the accuracy of robot-assisted lumbar pedicle screw placement based on preoperative CT-like 3D MRI as the data source for robotic registration. STUDY DESIGNHuman cadaveric study. METHODS: CT-like 3D MRI scans of the lumbar spine were acquired in ten human cadavers. A robotic navigation platform was used to plan and navigate pedicle screw placement based on the CT-like 3D MRI. Postoperative CT scans assessed the accuracy of screw positioning compared to preoperative planning based on the Gertzbein-Robbins scale (GRS) and by direct measurement (mm). RESULTSA total of 100 lumbar pedicle screws were robotically placed in ten cadavers (L1 through L5 bilaterally) based on CT-like 3D MRI. On postoperative CT evaluation, 99.0% of the positioned screws achieved an acceptable grade on the GRS (Grade A: n = 89 or Grade B: n = 10), with 89.0% classified as Grade A and 10.0% as Grade B. Meaning that 89.0% of screws were fully contained within the pedicle (GRS A), and 10% had a minor cortical breach <2mm (GRS B). The median deviation from the planned trajectory was 0.2 mm (axial IQR: 0.1 to 0.5 mm; sagittal: IQR: 0.1 to 0.4 mm), in both axial and sagittal planes. CONCLUSIONThis study showed that image registration of CT-like 3D MRI for robotic-assisted spine surgery is technically feasible and that accurate pedicle screw placement can be achieved without preoperative CT. Each CT-like 3D MRI was successfully registered for robotic navigation. CLINICAL SIGNIFICANCEThe results suggest that CT-like 3D MRI has the potential to be a radiation-free alternative for preoperative planning and navigation in lumbar spine instrumentation procedures.

Sandstone wettability in supercritical CO2-brine-rock interactions evaluated with 13C and 1H magnetic resonance

During the first decades of geologic CO2 storage in saline formations and depleted reservoirs, structural trapping is the most important storage mechanism. The effectiveness of CO2 containment hinges on the assumption that the sealing formation remains water wet in the presence of dense CO2. In this work, multiple 13C and 1H magnetic resonance (MR) methodologies were employed for the first time to evaluate the interactions between supercritical CO2, brine, and the pore surface of a Berea sandstone core plug under reservoir conditions. These studies employed a novel variable field superconducting MR and magnetic resonance imaging (MRI) instrument which permitted sequential 1H and 13C measurements of core plugs at high-pressure and high-temperature. To systematically study the wettability of rock core exposed to supercritical CO2, four experiments were designed including bulk CO2 in a high-pressure vessel, bulk CO2-brine, 13CO2 in dried rock core, and a 13CO2-brine-rock experiment.The measured 13C and 1H MR relaxation times in this work indicate that the Berea sandstone remained strongly water-wet when the brine saturated core plug was exposed to supercritical CO2 under reservoir conditions. For both 13C and 1H, T1 relaxation times provide more reliable wettability evaluation as compared to T2 due to the impact of molecular diffusion through internal magnetic field gradients. One-dimensional (1D) MRI was employed to spatially resolve 13CO2 and brine in the core plug. Two-dimensional (2D) MRI was able to image 13CO2 and brine in a PEEK vessel. The quantities of CO2 and brine in the core plug were determined from the MR signal intensities of 13CO2 and brine.

Super-resolution reconstruction of time-resolved four-dimensional computed tomography (TR-4DCT) with multiple breathing cycles based on TR-4DMRI.

Respiratory motion irregularities in lung cancer patients are common and can be severe during multi-fractional (∼20 mins/fraction) radiotherapy. However, the current clinical standard of motion management is to use a single-breath respiratory-correlated four-dimension computed tomography (RC-4DCT or 4DCT) to estimate tumor motion to delineate the internal tumor volume (ITV), covering the trajectory of tumor motion, as a treatment target. To develop a novel multi-breath time-resolved (TR) 4DCT using the super-resolution reconstruction framework with TR 4D magnetic resonance imaging (TR-4DMRI) as guidance for patient-specific breathing irregularity assessment, overcoming the shortcomings of RC-4DCT, including binning artifacts and single-breath limitations. Six lung cancer patients participated in the IRB-approved protocol study to receive multiple T1w MRI scans, besides an RC-4DCT scan on the simulation day, including 80 low-resolution (lowR: 5×5×5mm3) free-breathing (FB) 3D cine MRFB images in 40s (2Hz) and a high-resolution (highR: 2×2×2mm3) 3D breath-hold (BH) MRBH image for each patient. A CT (1×1×3mm3) image was selected from 10-bin RC-4DCT with minimal binning artifacts and a close diaphragm match (<1cm) to the MRBH image. A mutual-information-based Freeform deformable image registration (DIR) was used to register the CT and MRBH via the opposite directions (namely F1: and F2: ) to establish CT-MR voxel correspondences. An intensity-based enhanced Demons DIR was then applied for , in which the original MRBH was used in D1: , while the deformed MRBH was used in D2: . The deformation vector fields (DVFs) obtained from each DIR were composed to apply to the deformed CT (D1) and original CT (D2) to reconstruct TR-4DCT images. A digital 4D-XCAT phantom at the end of inhalation (EOI) and end of exhalation (EOE) with 2.5cm diaphragmatic motion and three spherical targets (ϕ=2, 3, 4cm) were first tested to reconstruct TR-4DCT. For each of the six patients, TR-4DCT images at the EOI, middle (MID), and EOE were reconstructed with both D1 and D2 approaches. TR-4DCT image quality was evaluated with mean distance-to-agreement (MDA) at the diaphragm compared with MRFB, tumor volume ratio (TVR) referenced to MRBH, and tumor shape difference (DICE index) compared with the selected input CT. Additionally, differences in the tumor center of mass (|∆COMD1-D2|), together with TVR and DICE comparison, was assessed in the D1 and D2 reconstructed TR-4DCT images. In the phantom, TR-4DCT quality is assessed by MDA=2.0±0.8mm at the diaphragm, TVR=0.8±0.0 for all tumors, and DICE=0.83±0.01, 0.85±0.02, 0.88±0.01 for ϕ=2, 3, 4cm tumors, respectively. In six patients, the MDA in diaphragm match is -1.6±3.1mm (D1) and 1.0±3.9mm (D2) between the reconstructed TR-4DCT and lowR MRFB among 18 images (3 phases/patient). The tumor similarity is TVR=1.2±0.2 and DICE=0.70±0.07 for D1 and TVR=1.4±0.3 (D2) and DICE=0.73±0.07 for D2. The tumor position difference is |∆COMD1-D2|=1.2±0.8mm between D1 and D2 reconstructions. The feasibility of super-resolution reconstruction of multi-breathing-cycle TR-4DCT is demonstrated and image quality at the diaphragm and tumor is assessed in both the 4D-XCAT phantom and six lung cancer patients. The similarity of D1 and D2 reconstruction suggests consistent and reliable DIR results. Clinically, TR-4DCT has the potential for breathing irregularity assessment and dosimetry evaluation in radiotherapy.

ReMiND: Recovery of missing neuroimaging using diffusion models with application to Alzheimer’s disease

Abstract Missing data is a significant challenge in medical research. In longitudinal studies of Alzheimer’s disease (AD) where structural magnetic resonance imaging (MRI) is collected from individuals at multiple time points, participants may miss a study visit or drop out. Additionally, technical issues such as participant motion in the scanner may result in unusable imaging data at designated visits. Such missing data may hinder the development of high-quality imaging-based biomarkers. To address the problem of missing MRI data in studies of AD, we introduced a novel 3D diffusion model specifically designed for imputing missing structural MRI (Recovery of Missing Neuroimaging using Diffusion models (ReMiND)). The model generates a whole-brain image conditional on a single structural MRI observed at a past visit or conditional on one past and one future observed structural MRI relative to the missing observation. The performance of models was compared with two alternative imputation approaches: forward filling and image generation using variational autoencoders. Experimental results show that our method can generate 3D structural MRI with high similarity to ground-truth images at designated visits. Furthermore, images generated using ReMiND show relatively lower differences in volume estimation between the imputed and observed images compared to images generated by forward filling or autoencoders. Additionally, ReMiND provides more accurate estimated rates of atrophy over time in important anatomical brain regions than the two comparator methods. Our 3D diffusion model can impute missing structural MRI data at a single designated visit and outperforms alternative methods for imputing whole-brain images that are missing from longitudinal trajectories.

Electric potential energy optimized 3D radial sampling trajectories for MRI

A novel method for creating “golden” 3D center-out radial MRI sampling trajectories was developed and analyzed. This method, called ELECTRO (ELECTRic potential energy Optimized), uses repulsive forces to minimize electric potential energy. An objective function \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:G\\left(S\\right)$$\\end{document}, the electric potential energies of all subsets of consecutive readouts in a 3D radial trajectory, and its reduced form were minimized using a multi-stage optimization strategy. A metric called normalized mean nearest neighbor angular distance (NMNA) was proposed for describing distributions of points on a sphere. ELECTRO and other relevant golden trajectories were compared in silico using NMNA and point spread function analysis. Consecutive readouts from an ELECTRO trajectory were well spread out, with consistent NMNA values across sphere sizes (σNMNA = 0.005) and between regions on the sphere (NMNA ≈ 1.49). Conversely, the supergolden trajectory had poor consistency in NMNA values (σNMNA = 0.090) and clustering (NMNA = 1.28 at the pole with 40,000 readouts) that lead to artifact in the point spread function. Multi-stage optimization was faster than single-stage and obtained lower values of \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:G\\left(S\\right)$$\\end{document} (e.g., 0.87 vs. 0.91, for a sphere size of 40). In conclusion, ELECTRO trajectories are more golden than other 3D center-out radial trajectories, making them a suitable candidate for dynamic 3D MR imaging.

Simulation of Dendrite Growth with a Diffusion-Limited Aggregation Model Validated by MRI of a Lithium Symmetric Cell during Charging

Lithium metal batteries offer high energy density but are challenged by dendrite growth, which can lead to short circuits and battery failure. Multiple models with varying degrees of accuracy and computational cost have been developed to understand and predict dendrite growth. This study presents a simple model to simulate macroscale dendrite growth on lithium metal electrodes. The model uses a 3D single-particle Diffusion-Limited Aggregation (DLA) algorithm with an electric field bias to simulate dendrite growth. The electric field bias was introduced into the model with an important parameter, namely the biasing factor c, which determines the balance between diffusion and electric field effects. Before performing the simulation with the proposed model, the dendrite growth in a lithium symmetric cell during charging was measured by sequential 3D magnetic resonance imaging (MRI). These data were then used to validate the simulation, as the dendrite structure in each measured MRI time frame was used a starting point for a new simulation, the results of which were then validated with the measured dendrite structure of the next time frame. The best agreement between the simulated and measured dendrite structures using the overlap and displacement of deposition sites metrics was obtained at the biasing factor c = 0.7. This agreement was also good in terms with the fractal dimension of the dendrite structures. The proposed method offers a simple, accurate, and scalable framework for predicting dendrite growth over long deposition periods, making it a valuable tool for studying dendrite suppression under real-world battery charging conditions.

Ranking attention multiple instance learning for lymph node metastasis prediction on multicenter cervical cancer MRI.

In the current clinical diagnostic process, the gold standard for lymph node metastasis (LNM) diagnosis is histopathological examination following surgical lymphadenectomy. Developing a non-invasive and preoperative method for predicting LNM is necessary and holds significant clinical importance. We develop a ranking attention multiple instance learning (RA-MIL) model that integrates convolutional neural networks (CNNs) and ranking attention pooling to diagnose LNM from T2 MRI. Our RA-MIL model applies the CNNs to derive imaging features from 2D MRI slices and employs ranking attention pooling to create patient-level feature representation for diagnostic classification. Based on the MIL and attention theory, informative regions of top-ranking MRI slices from LNM-positive patients are visualized to enhance the interpretability of automatic LNM prediction. This retrospective study collected 300 female patients with cervical cancer who underwent T2-weighted magnetic resonance imaging (MRI) scanning and histopathological diagnosis from one hospital (289 patients) and one open-source dataset (11 patients). Our RA-MIL model delivers promising LNM prediction performance, achieving the area under the receiver operating characteristic curve (AUC) of 0.809 on the internal test set and 0.833 on the public dataset. Experiments show significant improvements in LNM status prediction using the proposed RA-MIL model compared with other state-of-the-art (SOTA) comparative deep learning models. The developed RA-MIL model has the potential to serve as a non-invasive auxiliary tool for preoperative LNM prediction, offering visual interpretability regarding informative MRI slices and regions in LNM-positive patients.

7594 Diagnostic utility of 11C-Methionine PET-CT imaging in persistent or recurrent Cushing’s disease after transsphenoidal surgery

Abstract Disclosure: R. Furnica: None. F. Devuyst: None. C. Mathey: None. S. Constantinescu: None. C. De Herdt: None. L. Renaud: None. D.M. Maiter: None. Introduction: Equivocal or negative pituitary magnetic resonance imaging (MRI) findings pose a significant challenge in the management of persistent or recurrent Cushing’s disease (CD), compromising the chances of success of a further transsphenoidal surgery (TSS). The aim of our study was to determine the diagnostic utility of [1][1]C-methionine (MET) positron emission tomography coupled with computerized tomography (PET-CT) in localizing the residual corticotroph adenoma. Methods: We retrospectively analyzed the results of all MET-PET-CT performed between May 2002 and November 2023 in patients with a CD persisting or relapsing after TSS, and equivocal (n=14) or negative pituitary MRI findings (n=8). In 15 cases, images obtained from MET-PET were also co-registered with a high-resolution 3D pituitary MRI. All patients had a pathologically confirmed corticotroph tumor, and/or biochemical evidence of early postoperative remission after the first TSS, and/or proven ACTH-dependent Cushing’s syndrome with positive bilateral inferior petrosal sinus sampling. Results: Twenty-two patients were included (18 females and 4 males), with a mean age of 35.5 years at diagnosis. Initial tumors were mostly microadenomas with a mean tumor volume of 15 mm3. Thirteen out of the 22 patients had a suspect anomaly on conventional MRI that could however not be clearly distinguished from postsurgical changes, while the remaining 9 had a negative MRI. A significant MET standardized uptake value (SUV) in the suspected area of the tumor residue was defined as a ratio ≥ 1.80 relative to cerebellum SUV and was found in 12/22 patients (55%; 4 patients with negative pituitary MRI and 8 with equivocal findings). On the basis of positive imaging, repeat TSS was performed in 10 patients and was successful in 6, while Gamma Knife radiosurgery (GKRS) was performed in 2 patients allowing remission in both (total remission rate: 8/12). Among the 4 patients not cured by TSS, the presence of corticotroph adenoma in the resected tissue was found in 3 cases. Exploratory TSS was performed in 4 of the 10 PET negative patients, with no remission. Two patients were treated with GKRS, with remission in 1 case. Among the 4 other patients, bilateral adrenalectomy was performed in one case and adrenal steroidogenesis inhibitors were used in the remaining patients. Conclusions: [1][1]C-Methionine PET-CT imaging can provide valuable diagnostic information to detect a residual active corticotroph adenoma in about half of patients with a persistent or recurrent CD and equivocal or negative MRI results, thereby allowing targeted TSS or radiosurgery with a global success rate of 67% in this selected subpopulation. Presentation: 6/1/2024

9272 Diagnostic utility of 11C-Methionine PET-CT imaging in persistent or recurrent Cushing’s disease after transsphenoidal surgery

Abstract Disclosure: R. Furnica: None. F. Devuyst: None. C. Mathey: None. S. Constantinescu: None. C. De Herdt: None. L. Renaud: None. D.M. Maiter: None. Introduction: Equivocal or negative pituitary magnetic resonance imaging (MRI) findings pose a significant challenge in the management of persistent or recurrent Cushing’s disease (CD), compromising the chances of success of a further transsphenoidal surgery (TSS). The aim of our study was to determine the diagnostic utility of [1][1]C-methionine (MET) positron emission tomography coupled with computerized tomography (PET-CT) in localizing the residual corticotroph adenoma. Methods: We retrospectively analyzed the results of all MET-PET-CT performed between May 2002 and November 2023 in patients with a CD persisting or relapsing after TSS, and equivocal (n=14) or negative pituitary MRI findings (n=8). In 15 cases, images obtained from MET-PET were also co-registered with a high-resolution 3D pituitary MRI. All patients had a pathologically confirmed corticotroph tumor, and/or biochemical evidence of early postoperative remission after the first TSS, and/or proven ACTH-dependent Cushing’s syndrome with positive bilateral inferior petrosal sinus sampling. Results: Twenty-two patients were included (18 females and 4 males), with a mean age of 35.5 years at diagnosis. Initial tumors were mostly microadenomas with a mean tumor volume of 15 mm3. Thirteen out of the 22 patients had a suspect anomaly on conventional MRI that could however not be clearly distinguished from postsurgical changes, while the remaining 9 had a negative MRI. A significant MET standardized uptake value (SUV) in the suspected area of the tumor residue was defined as a ratio ≥ 1.80 relative to cerebellum SUV and was found in 12/22 patients (55%; 4 patients with negative pituitary MRI and 8 with equivocal findings). On the basis of positive imaging, repeat TSS was performed in 10 patients and was successful in 6, while Gamma Knife radiosurgery (GKRS) was performed in 2 patients allowing remission in both (total remission rate: 8/12). Among the 4 patients not cured by TSS, the presence of corticotroph adenoma in the resected tissue was found in 3 cases. Exploratory TSS was performed in 4 of the 10 PET negative patients, with no remission. Two patients were treated with GKRS, with remission in 1 case. Among the 4 other patients, bilateral adrenalectomy was performed in one case and adrenal steroidogenesis inhibitors were used in the remaining patients. Conclusions: [1][1]C-Methionine PET-CT imaging can provide valuable diagnostic information to detect a residual active corticotroph adenoma in about half of patients with a persistent or recurrent CD and equivocal or negative MRI results, thereby allowing targeted TSS or radiosurgery with a global success rate of 67% in this selected subpopulation. Presentation: 6/1/2024

4D-Flow MRI and Vector Ultrasound in the In-Vitro Evaluation of Surgical Aortic Heart Valves - a Pilot Study.

The aim of this study was the initial investigation of 4D-Flow MRI and Vector Ultrasound as novel imaging techniques in the in-vitro analysis of hemodynamics in anatomical models. Specifically, by looking at the hemodynamic performance of state-of-the-art surgical heart valves in a 3D-printed aortic arch. The mock circulatory loop simulated physiological, pulsatile flow. Two mechanical and three biological aortic valves prostheses were compared in a 3D-printed aortic arch. 4D magnetic resonance imaging and vector flow Doppler ultrasound served as imaging methods. Hemodynamic parameters such as wall shear stress, flow velocities and pressure gradients were analyzed. The flow analysis revealed characteristic flow-patterns in the 3D-printed aortic arch. The blood-flow in the arch presented complex patterns, including the formation of helixes and vortices. Higher proximal peak velocities and lower flow volumes were found for biological valves. The mock circulatory loop in combination with modern radiological imaging provides a sufficient basis for the hemodynamic comparison of aortic valves.

Comparing the Diagnostic Efficacy of 3D Ultrasound and MRI in the Classification of Müllerian Anomalies.

Müllerian anomalies significantly impact female reproductive health. This study aims to compare the diagnostic efficacy of three-dimensional ultrasound (3D-US) and magnetic resonance imaging (MRI) in detecting and classifying these anomalies. A retrospective analysis of 150 patients with Müllerian anomalies was conducted at Saveetha Medical College and Hospital from March 2018 to March 2024. MRI and 3D-US examinations were performed and analyzed independently by two radiologists. Anomalies were classified according to European Society of Human Reproduction and Embryology (ESHRE)/European Society for Gynaecological Endoscopy (ESGE) and American Society for Reproductive Medicine (ASRM) guidelines. The septate uterus was the most prevalent anomaly, observed in 53 patients (35.3%). MRI demonstrated superior diagnostic accuracy (AUC 0.92) compared to 3D-US (AUC 0.88). Significant associations were found between presenting symptoms and specific anomaly types (p < 0.05). Inter-rater reliability between the two radiologists, with respect to classification of anomalies, was high (Cohen's kappa 0.85). MRI's superior soft-tissue contrast and multiplanar capabilities make it the gold standard for evaluating complex uterine malformations. 3D-US offers valuable real-time imaging and is particularly effective in assessing septum characteristics. The combined use of MRI and 3D-US enhances diagnostic precision and facilitates tailored management strategies. Integrating MRI and 3D-US in clinical practice improves diagnostic accuracy and treatment planning for Müllerian anomalies, ultimately enhancing patient outcomes.

Green exercise versus indoor urban exercise: Related frontal brain thickness and cognitive performance

Background and aimsThis study compared, for the first time, cognitive function, and the cortical thickness of frontal areas in healthy adults who exercise regularly in outdoor green spaces ("green exercise group," GEG; n=22, mean age=39.91 years, females=11) with those who exercise in indoor urban settings ("urban exercise group," UEG; n=25, mean age=40 years, females=11). We further explored the associations between frontal brain thickness and cognitive measures in each group separately. MethodForty-seven healthy adults participated. All underwent a neuropsychological evaluation for short-term memory, working memory, and attention. High-resolution T1-weighted 3D magnetic resonance imaging (MRI) scans were acquired for each participant. The thickness of frontal brain regions was extracted and exported to JASP software for statistical analyses. ResultsThe GEG performed better on working memory and short-term memory tasks compared to the UEG. Additionally, the GEG exhibited increased thickness in the right anterior cingulate cortex (rACC) and the right superior frontal sulcus (rSFS). These areas were associated with short-term memory within the GEG. Fisher's test and Zou's intervals revealed that only the correlation between the rSFS and short-term memory was significantly different between the UEG and GEG. ConclusionThese findings suggest that exercising in outdoor natural areas might be related to better cognitive function and greater brain thickness in frontal areas. This study will contribute to the growing body of evidence linking brain, cognition and exercising in natural areas. Further research is needed to confirm these findings and explore the underlying mechanisms.

Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation.

In medical image segmentation, a domain gap often exists between training and testing datasets due to different scanners or imaging protocols, which leads to performance degradation in deep learning-based segmentation models. Given the high cost of manual labeling and the need for privacy protection, it is often challenging to annotate the testing (target) domain data for model fine-tuning or to collect data from different domains to train domain generalization models. Therefore, using only unlabeled target domain data for test-time adaptation (TTA) presents a more practical but challenging solution. To improve the segmentation accuracy of deep learning-based models on unseen datasets, and especially to enhance the efficiency and stability of TTA for individual samples from heterogeneous domains. In this study, we proposed to dynamically adapt a wavelet-VNet (WaVNet) to unseen target domains with a hybrid objective function, based on each unlabeled test sample during the test time. We embedded multiscale wavelet coefficients into a V-Net encoder and adaptively adjusted the spatial and spectral features according to the input, and the model parameters were optimized by three loss functions. We integrated a shape-aware loss to focus on the foreground segmentations, a Refine loss to correct the incomplete and noisy segmentations caused by domain shifts, and an entropy loss to promote the global consistency of the segmentations. We evaluated the proposed method on multidomain liver and prostate segmentation datasets to assess its advantages over other TTA methods. For the source domain model training of the liver dataset, we used 15 3D MR image samples for training and 5 for validation. Correspondingly, for the prostate dataset, we used 22 3D MR image samples for training and 7 for validation. In the target domain, we used a single 3D MR image sample for adaptation and testing. The total number of testing samples is 60 in the liver dataset (for 3 different domains) and 116 in the prostate dataset (for 6 different domains). The proposed method showed the highest segmentation accuracy among all methods, achieving a mean(±SD) Dice coefficient (DSC) of 78.10±5.23% and a mean 95th Hausdorff distance (HD95) of 15.52±5.84mm on the liver dataset; and a mean DSC of 80.02±3.89% and a mean HD95 of 9.18±3.47mm on the prostate dataset. The DSC is 11.67% (in absolute terms) and 15.27% higher than that of the baseline (no adaptation) method, for the liver and the prostate datasets, respectively. The proposed adaptive WaVNet enhanced the image segmentation accuracy from unseen domains during the test time via unsupervised learning and multi-objective optimization. It can benefit clinical applications where data are scarce or with changing data distributions, including online adaptive radiotherapy. The code will be released at: https://github.com/sanny1226/WaVNet.

Transducer module apodization to reduce bone heating during focused ultrasound uterine fibroid ablation with phased arrays: A numerical study.

During magnetic resonance-guided focused ultrasound (MRgFUS) surgery for uterine fibroids, ablation of fibrous tissues in proximity to the hips and spine is challenging due to heating within the bone that can cause patients to experience pain and potentially damage nerves. This far-field bone heating limits the volume of fibroid tissue that is treatable viaMRgFUS. To investigate transducer module apodization for improving the ratio of focal-to-bone heating ( ) when targeting fibroid tissue close to the hips and spine, to enable MRgFUS treatments closer to thebone. Acoustic and thermal simulations were performed using 3D magnetic resonance imaging (MRI)-derived anatomies of ten patients who underwent MRgFUS ablation for uterine fibroids using a low-frequency ( ) 6144-element flat fully-populated modular phased array system (Arrayus Technologies Inc., Burlington, Canada) at our institution as part of a larger clinical trial (NCT03323905). Transducer modules ( per module) whose beams intersected with no-pass zones delineated within the field were identified, their output power levels were reduced by varying blocking percentage levels, and the resulting temperature field distributions were evaluated across multiple sonications near the hip and spine bones in each patient. Acoustic and thermal simulations took approximately ( ) and ( ) to run for a single near-spine (near-hip) target,respectively. For all simulated sonications, transducer module blocking improved compared to the no blocking case. In just over half of sonications, full module blocking maximized (increase of 82% 38% in 50% of hip targets and 49% 30% in 62% of spine targets vs. no blocking; mean±SD), at the cost of more diffuse focusing (focal heating volumes increased by 13%±13% for hip targets and 39%±27% for spine targets) and thus requiring elevated total (hip: 6%±17%, spine: 37%±17%) and peak module-wise (hip: 65%±36%, spine: 101%±56%) acoustic power levels to achieve equivalent focal heating as the no blocking control case. In the remaining sonications, partial module blocking provided further improvements in both (increased by 29%±25% in the hip and 15%±12% in the spine) and focal heating volume (decrease of 20%±10% in the hip and 34%±17% in the spine) relative to the full blocking case. The optimal blocking percentage value was dependent on the specific patient geometry and target location of interest. Although not all individual target locations saw the benefit, element-wise phase aberration corrections improved the average compared to the no correction case (increase of 52%±47% in the hip, 35%±24% in the spine) and impacted the optimal blocking percentage value. Transducer module blocking enabled ablative treatments to be carried out closer to both hip and spine without overheating or damaging the bone (no blocking: / , full blocking: / , optimal partial blocking: / for hip/spine). The proposed transducer apodization scheme shows promise for improving MRgFUS treatments of uterine fibroids, and may ultimately increase the effective treatment envelope of MRgFUS surgery in the body by enabling tissue ablation closer to bonystructures.

DELR-Net: a network for 3D multimodal medical image registration in more lightweight application scenarios.

3D multimodal medical image deformable registration plays a significant role in medical image analysis and diagnosis. However, due to the substantial differences between images of different modalities, registration is challenging and requires high computational costs. Deep learning-based registration methods face these challenges. The primary aim of this paper is to design a 3D multimodal registration network that ensures high-quality registration results while reducing the number of parameters. This study designed a Dual-Encoder More Lightweight Registration Network (DELR-Net). DELR-Net is a low-complexity network that integrates Mamba and ConvNet. The State Space Sequence Module and the Dynamic Large Kernel block are used as the main components of the dual encoders, while the Dynamic Feature Fusion block is used as the main component of the decoder. This study conducted experiments on 3D brain MR images and abdominal MR and CT images. Compared to existing registration methods, DELR-Net achieved better registration results while maintaining a lower number of parameters. Additionally, generalization experiments on other modalities showed that DELR-Net has superior generalization capabilities. DELR-Net significantly improves the limitations of 3D multimodal medical image deformable registration, achieving better registration performance with fewer parameters.

3-1-3 Weight averaging technique-based performance evaluation of deep neural networks for Alzheimer’s disease detection using structural MRI

Alzheimer’s disease (AD) is a progressive neurological disorder. It is identified by the gradual shrinkage of the brain and the loss of brain cells. This leads to cognitive decline and impaired social functioning, making it a major contributor to dementia. While there are no treatments to reverse AD’s progression, spotting the disease’s onset can have a significant impact in the medical field. Deep learning (DL) has revolutionized medical image classification by automating feature engineering, removing the requirement for human experts in feature extraction. DL-based solutions are highly accurate but demand a lot of training data, which poses a common challenge. Transfer learning (TL) has gained attention for its knack for handling limited data and expediting model training. This study uses TL to classify AD using T1-weighted 3D Magnetic Resonance Imaging (MRI) from the Alzheimer’s Disease Neuroimaging (ADNI) database. Four modified pre-trained deep neural networks (DNN), VGG16, MobileNet, DenseNet121, and NASNetMobile, are trained and evaluated on the ADNI dataset. The 3-1-3 weight averaging technique and fine-tuning improve the performance of the classification models. The evaluated accuracies for AD classification are VGG16: 98.75%; MobileNet: 97.5%; DenseNet: 97.5%; and NASNetMobile: 96.25%. The receiver operating characteristic (ROC), precision–recall (PR), and Kolmogorov-Smirnov (KS) statistic plots validate the effectiveness of the modified pre-trained model. Modified VGG16 excels with area under the curve (AUC) values of 0.99 for ROC and 0.998 for PR curves. The proposed approach shows effective AD classification by achieving high accuracy using the 3-1-3 weight averaging technique and fine-tuning.

Global and local feature extraction based on convolutional neural network residual learning for MR image denoising.

Given the different noise distribution information of global and local magnetic resonance (MR) images, this study aims to extend the current work on convolutional neural networks that preserve global structure and local details in MR image denoising tasks. This study proposed a parallel and serial network for denoising 3D MR images, called 3D-PSNet. We use the residual depthwise separable convolution block to learn the local information of the feature map, reduce the network parameters, and thus improve the training speed and parameter efficiency. In addition, we consider the feature extraction of the global image and utilize residual dilated convolution to process the feature map to expand the receptive field of the network and avoid the loss of global information. Finally, we combine both of them to form a parallel network. What's more, we integrate reinforced residual convolution blocks with dense connections to form serial network branches, which can remove redundant information and refine features to further obtain accurate noise information. The peak signal-to-noise ratio, structural similarity index measure, and root mean square error metrics of 3D-PSNet are as high as 47.79%, 99.81%, and 0.40%, respectively, achieving competitive denoising effect on three public datasets. The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets. The proposed 3D-PSNet takes advantage of multi-scale receptive fields, local feature extraction and residual dense connections to more effectively restore the global structure and local fine features in MR images, and is expected to help doctors quickly and accurately diagnose patients' conditions.

Automated Three-Dimensional Imaging and Pfirrmann Classification of Intervertebral Disc Using a Graphical Neural Network in Sagittal Magnetic Resonance Imaging of the Lumbar Spine.

This study aimed to develop a graph neural network (GNN) for automated three-dimensional (3D) magnetic resonance imaging (MRI) visualization and Pfirrmann grading of intervertebral discs (IVDs), and benchmark it against manual classifications. Lumbar IVD MRI data from 300 patients were retrospectively analyzed. Two clinicians assessed the manual segmentation and grading for inter-rater reliability using Cohen's kappa. The IVDs were then processed and classified using an automated convolutional neural network (CNN)-GNN pipeline, and their performance was evaluated using F1 scores. Manual Pfirrmann grading exhibited moderate agreement (κ = 0.455-0.565) among the clinicians, with higher exact match frequencies at lower lumbar levels. Single-grade discrepancies were prevalent except at L5/S1. Automated segmentation of IVDs using a pretrained U-Net model achieved an F1 score of 0.85, with a precision and recall of 0.83 and 0.88, respectively. Following 3D reconstruction of the automatically segmented IVD into a 3D point-cloud representation of the target intervertebral disc, the GNN model demonstrated moderate performance in Pfirrmann classification. The highest precision (0.81) and F1 score (0.71) were observed at L2/3, whereas the overall metrics indicated moderate performance (precision: 0.46, recall: 0.47, and F1 score: 0.46), with variability across spinal levels. The integration of CNN and GNN offers a new perspective for automating IVD analysis in MRI. Although the current performance highlights the need for further refinement, the moderate accuracy of the model, combined with its 3D visualization capabilities, establishes a promising foundation for more advanced grading systems.