The objective was to use convolutional neural networks (CNNs) for automatic segmentation of hip cartilage and labrum based on 3D MRI. In this retrospective single-center study, CNNs with a U-Net architecture were used to develop a fully automated segmentation model for hip cartilage and labrum from MRI. Direct hip MR arthrographies (01/2020-10/2021) were selected from 100 symptomatic patients. Institutional routine protocol included a 3D T1 mapping sequence, which was used for manual segmentation of hip cartilage and labrum. 80 hips were used for training and the remaining 20 for testing. Model performance was assessed with six evaluation metrics including Dice similarity coefficient (DSC). In addition, model performance was tested on an external dataset (40 patients) with a 3D T2-weighted sequence from a different institution. Inter-rater agreement of manual segmentation served as benchmark for automatic segmentation performance. 100 patients were included (mean age 30 ± 10 years, 64% female patients). Mean DSC for cartilage was 0.92 ± 0.02 (95% confidence interval [CI] 0.92-0.93) and 0.83 ± 0.04 (0.81-0.85) for labrum and comparable (p = 0.232 and 0.297, respectively) to inter-rater agreement of manual segmentation: DSC cartilage 0.93 ± 0.04 (0.92-0.95); DSC labrum 0.82 ± 0.05 (0.80-0.85). When tested on the external dataset, the DSC was 0.89 ± 0.02 (0.88-0.90) and 0.71 ± 0.04 (0.69-0.73) for cartilage and labrum, respectively.The presented deep learning approach accurately segments hip cartilage and labrum from 3D MRI sequences and can potentially be used in clinical practice to provide rapid and accurate 3D MRI models.

BACKGROUND: T2*-weighted imaging at 7 T offers detailed visualization of brain structures, but image quality and artifacts depend on echo time (TE) adjustments. Optimizing TE is crucial for tissue contrast and artifact minimization.

OBJECTIVE: To evaluate the impact of TE on tissue contrast and image quality in T2*-weighted sequences at 7 T in adolescents and young adults.

MATERIALS AND METHODS: Ten adolescent and young adult patients underwent 7-T MRI with multi-echo T2*-weighted sequences. Six TEs (8.1 ms to 36 ms) were acquired. Signal contrast ratios (CR) for seven brain regions-caudate nuclei, corpus callosum genu, frontal cortex, cortical veins, globi pallidi, medullary veins, and left optic radiation-were analyzed. Two blinded neuroradiologists assessed image quality and artifact severity using a 4-point Likert scale (IQS). Statistical trends were analyzed using the Jonckheere-Terpstra test. A P-value < 0.05 was considered statistically significant.

RESULTS: The study cohort consisted of 4 male and 6 females; the median age of the patients was 16 years (range 15-23 years). CR increased significantly with higher TEs for most regions except the caudate, where CR decreased (P < 0.05). Longer TEs led to greater artifact severity in the brainstem, temporal, occipital, and frontal lobes (P < 0.02), but not in parietal lobes (P > 0.05). Kappa agreement for IQS was 0.76.

CONCLUSION: TE significantly affects contrast and artifacts in 7-T T2*-weighted imaging. TEs between 20 and 30 ms offer the best balance between tissue contrast and artifact severity, optimizing image quality for clinical and research applications.

During the second and third trimesters of human gestation, the brain undergoes rapid neurodevelopment thanks to critical processes such as neuronal migration, radial glial scaffolding, and synaptic sprouting. Unfortunately, gathering high-quality MRI data on the healthy fetal brain is complex, making it challenging to understand this development. To address this issue, we conducted a study using motion-corrected diffusion tensor imaging (DTI) to analyze changes in the cortical gray matter (CP) and sub-cortical white matter (scWM) microstructure in 44 healthy fetuses between 23 and 36 weeks of gestational age. We automatically segmented these two tissues and parcellated them into eight regions based on anatomy, including the frontal, parietal, occipital, and temporal lobes, cingulate, sensory and motor cortices, and the insula. We were able to observe distinct patterns of diffusion MRI signals across these regions. Specifically, we found that in the CP, fractional anisotropy (FA) consistently decreased with age, while mean diffusivity (MD) followed a downward-open parabolic trend. Conversely, in the scWM, FA exhibited an upward-open parabolic trajectory, while MD followed a downward-open parabolic trend. Our study underscores the potential for diffusion as a biomarker for normal and abnormal neurodevelopment before birth, especially since most neurodiagnostic tools are not yet available at this stage.

Diffusion magnetic resonance imaging (dMRI) is essential for studying the microstructure of the developing fetal brain. However, fetal motion during scans and its interaction with magnetic field inhomo-geneities lead to amplified artifacts and data scattering, compromising the consistency of dMRI analysis. This work introduces HAITCH, a novel open-source framework for correcting and reconstructing high-angular resolution dMRI data from challenging fetal scans. Our multi-stage approach incorporates an optimized multi-shell design for increased information capture and motion tolerance, a blip-reversed dual-echo multi-shell acquisition for dynamic distortion correction, advanced motion correction for robust and model-free reconstruction, and outlier detection for improved reconstruction fidelity. Validation experiments on real fetal dMRI scans demonstrate significant improvements and accurate correction across diverse fetal ages and motion levels. HAITCH effectively removes artifacts and reconstructs high-fidelity dMRI data suitable for advanced diffusion modeling and tractography.

Although 7 Tesla (7T) field strength MR imaging offers higher signal-to-noise ratio and spatial resolution and improves certain types of tissue contrast, the incorporation of these systems into clinical pediatric neuroradiology has been relatively limited. Following a discussion of available hardware, current regulations, and pediatric specific safety considerations, this article briefly reviews the underlying principles behind the improved image quality attainable with certain techniques at 7T. Subsequently, specific high-performance sequences and techniques are highlighted including MP2RAGE, T2-weighted, and T2*-weighted sequences as well as MR angiography, all with sample images and comparison with standard field strengths. Finally, current clinical neuroradiological applications of 7T are explored with particular focus on focal epilepsy, multiple sclerosis, vascular diseases, and cerebral microbleeds. Ongoing and future innovations in hardware design and sequence development promise continued advancement in 7T neuroimaging and further applications to pediatric neuroradiology.

PURPOSE: To improve the quality of abdominal diffusion-weighted MR images (DW-MRI) when acquired using single-repetition (NEX = 1) protocols, and thereby increase apparent diffusion coefficient (ADC) map accuracy and lesion conspicuity at high b-values. We aim to reduce the effect of blurring due to motion that obscures small lesions when averaging multiple repetition images at each b-value, which is the current clinical standard.

METHODS: We propose a self-supervised denoising diffusion probabilistic model (ssDDPM) to improve DW-MRI quality given noisy single-repetition acquisitions in pediatric abdominal scans. The ssDDPM is designed for multi-b-value DW-MRI and incorporates diffusion signal decay model (i.e., ADC model) constraints into its loss term. The model is trained to denoise single-repetition images from multiple b-values while ensuring that the output adheres to the signal decay model. Training was performed on a dataset of 120 pediatric subjects with liver tumors. The performance of ssDDPM was compared with non-local means (NLM) filtering and deep image prior (DIP) denoising techniques. These techniques have the capability to denoise single repetition images unlike the other techniques in literature that requires multiple direction or repetition images. Evaluation included qualitative radiologist's image quality assessment, receiver operating characteristic (ROC) analysis for lesion detection, and ADC fitting accuracy compared with motion-free, breath-hold reference data.

RESULTS: The ssDDPM demonstrated superior performance over comparison methods in terms of image quality, lesion conspicuity, and ADC map accuracy in NEX = 1 images. It received higher scores in radiologist assessments and showed better lesion discrimination in ROC analysis. Additionally, ssDDPM provided more precise and accurate ADC estimates when compared with the motion-free, breath-hold reference data.

CONCLUSION: The ssDDPM effectively reduces motion related deblurring and enhances the quality of DW-MRI images by directly denoising single-repetition (NEX = 1) images while respecting signal decay model constraints. This method improves the assessment of pediatric liver lesions, offering a more accurate and efficient diagnostic tool with reduced scan times, when compared with current clinical practice and other denoising techniques.

PURPOSE: To address the unmet need for a cross-platform, multiparametric relaxometry technique to facilitate data harmonization across different sites.

METHODS: A simultaneous T1 and T2 mapping technique, 3D quantification using an interleaved Look-Locker acquisition sequence with a T2 preparation pulse (3D-QALAS), was implemented using the open-source vendor-agnostic Pulseq platform. The technique was tested on four 3 T scanners from two vendors across two sites, evaluating cross-scanner, cross-software version, cross-site, and cross-vendor variability. The cross-vendor reproducibility was assessed using both the vendor-native and Pulseq-based implementations. A National Institute of Standards and Technology/International Society for Magnetic Resonance in Medicine system phantom and three human subjects were evaluated. The acquired T1 and T2 maps from the different 3D-QALAS runs were compared using linear regression, Bland-Altman plots, coefficient of variation (CV), and intraclass correlation coefficient (ICC).

RESULTS: Pulseq-QALAS demonstrated high linearity (R2 = 0.994 for T1, R2 = 0.999 for T2) and correlation (ICC = 0.99 [0.98-0.99]) against temperature-corrected NMR reference values in the system phantom. Compared to vendor-native sequences, the Pulseq implementation showed significantly higher reproducibility in phantom T2 values (CV, 2.3% vs. 17%; p < 0.001), and improved T1 reproducibility (CV, 3.4% vs. 4.9%; p = 0.71, not significant). The Pulseq implementation reduced cross-vendor variability to a level comparable to cross-scanner (within-vendor) variability. In vivo, Pulseq-QALAS exhibited reduced cross-vendor variability, particularly for T2 values in gray matter with a twofold reduction in variability (CV, 2.3 vs. 5.9%; p < 0.001).

CONCLUSION: An identical implementation across different scanners and vendors, combined with consistent reconstruction and fitting pipelines, can improve relaxometry measurement reproducibility across platforms.

Accurate characterization of in-utero brain development is essential for understanding typical and atypical neurodevelopment. Building upon previous efforts to construct spatiotemporal fetal brain MRI atlases, we present the CRL-2025 fetal brain atlas, which is a spatiotemporal (4D) atlas of the developing fetal brain between 21 and 37 gestational weeks. This atlas is constructed from carefully processed MRI scans of 160 fetuses with typically-developing brains using a diffeomorphic deformable registration framework integrated with kernel regression on age. CRL-2025 uniquely includes detailed tissue segmentations, transient white matter compartments, and parcellation into 126 anatomical regions. This atlas offers significantly enhanced anatomical details over the CRL-2017 atlas, and is released along with the CRL diffusion MRI atlas with its newly created tissue segmentation and labels as well as deep learning-based multiclass segmentation models for fine-grained fetal brain MRI segmentation. The CRL-2025 atlas and its associated tools provide a robust and scalable platform for fetal brain MRI segmentation, groupwise analysis, and early neurodevelopmental research, and these materials are publicly released to support the broader research community.