Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data. We ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines.

Accurate fetal brain tissue segmentation and biometric measurement are essential for monitoring neurodevelopment and detecting abnormalities in utero. The Fetal Tissue Annotation (FeTA) Challenges have established robust multi-center benchmarks for evaluating state-of-the-art segmentation methods. This paper presents the results of the 2024 challenge edition, which introduced three key innovations. First, we introduced a topology-aware metric based on the Euler characteristic difference (ED) to overcome the performance plateau observed with traditional metrics like Dice or Hausdorff distance (HD), as the performance of the best models in segmentation surpassed the inter-rater variability. While the best teams reached similar scores in Dice (0.81-0.82) and HD95 (2.1-2.3 mm), ED provided greater discriminative power: the winning method achieved an ED of 20.9, representing roughly a 50% improvement over the second-and third-ranked teams despite comparable Dice scores. Second, we introduced a new 0.55T low-field MRI test set, which, when paired with high-quality super-resolution reconstruction, achieved the highest segmentation performance across all test cohorts (Dice=0.86, HD95=1.69, ED=6.26). This provides the first quantitative evidence that low-cost, low-field MRI can match or surpass high-field systems in automated fetal brain segmentation. Third, the new biometry estimation task exposed a clear performance gap: although the best model reached a mean average percentage error (MAPE) of 7.72%, most submissions failed to outperform a simple gestational-age-based linear regression model (MAPE=9.56%), and all remained above inter-rater variability with a MAPE of 5.38%. Finally, by analyzing the top-performing models from FeTA 2024 alongside those from previous challenge editions, we identify ensembles of 3D nnU-Net trained on both real and synthetic data with both image-and anatomy-level augmentations as the most effective approaches for fetal brain segmentation. Our quantitative analysis reveals that acquisition site, super-resolution strategy, and image quality are the primary sources of domain shift, informing recommendations to enhance the robustness and generalizability of automated fetal brain analysis methods.

Human arousal is essential to survival and mediated by the ascending arousal network (AAN) and its connections. It spans from the brainstem to the diencephalon, basal forebrain, and cerebral cortex. Despite advances in mapping the AAN in adults, it is unexplored in fetal and early infant life, especially with high-resolution magnetic resonance imaging techniques. In this study, we conducted-for the first time-high-resolution ex vivo diffusion MRI-based analysis of the AAN in seven fetal, infant, and adult brains, incorporating probabilistic tractography and quantifying connectivity using graph theory. We observed that AAN structural connectivity becomes increasingly integrated during development, progressively reaching rostrally during the first postconceptional year. We quantitatively identified the dorsal raphe (DR) nucleus and ventral tegmental area (VTA) as AAN connectivity hubs already in the fetus persisting into adulthood. The DR appears to form a local hub of short-range connectivities, while the VTA evolves as a long-range global hub. The identified connectivity maps advance our understanding of AAN architecture changes due to normative human brain development, as well as disorders of arousal, such as coma and sudden infant death syndrome.

BACKGROUND AND OBJECTIVE:Patients with metastatic bone disease are at risk of pathological femoral fractures and may require prophylactic surgical fixation. Current clinical decision support tools often overestimate fracture risk, leading to overtreatment. While novel scores integrating femoral strength assessment via finite element (FE) models show promise, they require 3D imaging, extensive computation, and are difficult to automate. Predicting femoral strength directly from single 2D radiographic projections using convolutional neural networks (CNNs) could address these limitations, but this approach has not yet been explored for femora with metastatic lesions. This study aimed to test whether CNNs can accurately predict strength of femora with metastatic lesions from single 2D radiographic projections. METHODS:CNNs with various architectures were developed and trained using an FE model generated training dataset. This training dataset was based on 36,000 modified computed tomography (CT) scans, created by randomly inserting artificial lytic lesions into the CT scans of 36 intact anatomical femoral specimens. From each modified CT scan, an anterior-posterior 2D projection was generated and femoral strength in one-legged stance was determined using nonlinear FE models. Following training, the CNN performance was evaluated on an independent experimental test dataset consisting of 31 anatomical femoral specimens (16 intact, 15 with artificial lytic lesions). 2D projections of each specimen were created from corresponding CT scans and femoral strength was assessed in mechanical tests. The CNNs' performance was evaluated using linear regression analysis and compared to 2D densitometric predictors (bone mineral density and content) and CT-based 3D FE models. RESULTS:All CNNs accurately predicted the experimentally measured strength in femora with and without metastatic lesions of the test dataset (R²≥0.80, CCC≥0.81). In femora with metastatic lesions, the performance of the CNNs (best: R²=0.84, CCC=0.86) was considerably superior to 2D densitometric predictors (R²≤0.07) and slightly inferior to 3D FE models (R²=0.90, CCC=0.94). CONCLUSIONS:CNNs, trained on a large dataset generated via FE models, predicted experimentally measured strength of femora with artificial metastatic lesions with accuracy comparable to 3D FE models. By eliminating the need for 3D imaging and reducing computational demands, this novel approach demonstrates potential for application in a clinical setting.

The Ganglionic Eminence (GE) plays a pivotal role in neural migration during fetal brain development. Early detection of GE anomalies is crucial for identifying migration deficiencies that may lead to neurological or psychiatric disorders postnatally. Currently, no robust automatic GE segmentation approaches exist to enable its early analysis. Segmentation challenges arise from the transient nature of this structure, resulting in an increase in isolated components and a decrease in their volumes with age. Additional complexity is introduced by the inaccuracy of determining the gestational age, potential artifacts due to fetal movement, and intensity fluctuations in images for the same structure. In this work, we propose an automated GE segmentation method for fetal Magnetic Resonance Imaging (MRI) data by extending 3D UNets and exploiting a registration–driven generative data augmentation technique to increase the number of scans from 138 to more than 2,500 with manually defined labels by an expert neuroradiologist. Our solution spans 19 to 38 weeks of gestation, achieving a mean Dice score of 0.79 ± 0.04 in the 2nd trimester and 0.74 ± 0.05 in the 3rd trimester, matching current state-of-the-art models. Overall, the GE volume decreases throughout pregnancy (R2 = 0.77, ranged 31– 668 mm3), highlighting an inverse relationship to the whole brain volume, which continues to grow (R2 = 0.93). The volumetric dynamics of predicted GE segmentations correlate with known anatomical development patterns, indicating the model’s ability to learn GE dynamics over time.

Irregular and unpredictable fetal movement is the most common cause of artifacts in in utero functional magnetic resonance imaging (fMRI), affecting analysis and limiting our understanding of early functional brain development. The accurate detection of corrupted functional connectivity (FC) resulting from motion artifacts or preprocessing, instead of neural activity, is a prerequisite for reliable and valid analysis of FC and early brain development. Approaches to address this problem in adult data are of limited utility in fetal fMRI. In this study, we evaluate a novel technique for robust computational assessment of motion artifacts, and the quantitative comparison of regression models for artifact removal in fetal FC analysis. It exploits the association between dynamic FC and non-stationarity of fetal movement, to detect residual noise. To validate our motion artifact detection technique in detail, we used a parametric generative model for neural events and fMRI blood oxygenation level-dependent (BOLD) signal. We conducted a systematic evaluation of 11 commonly used regression models in a sample of 70 fetuses with gestational age of 19-39 weeks. Results demonstrate that the proposed method has better accuracy in identifying corrupted FC compared to methods designed for adults. The technique, suggests that censoring, global signal regression and anatomical component-based regression models are the most effective models for compensating motion. The benchmarking technique, and the generative model for realistic fetal fMRI BOLD enables investigators conducting in utero fMRI analysis to effectively quantify the impact of fetal motion and evaluate alternative regression strategies for mitigating this impact. The code is publicly available at: https://github.com/cirmuw/fetalfMRIproc.

Segmentation is a critical step in analyzing the developing human fetal brain. There have been vast improvements in automatic segmentation methods in the past several years, and the Fetal Brain Tissue Annotation (FeTA) Challenge 2021 helped to establish an excellent standard of fetal brain segmentation. However, FeTA 2021 was a single center study, and the generalizability of algorithms across different imaging centers remains unsolved, limiting real-world clinical applicability. The multi-center FeTA Challenge 2022 focuses on advancing the generalizability of fetal brain segmentation algorithms for magnetic resonance imaging (MRI). In FeTA 2022, the training dataset contained images and corresponding manually annotated multi-class labels from two imaging centers, and the testing data contained images from these two imaging centers as well as two additional unseen centers. The data from different centers varied in many aspects, including scanners used, imaging parameters, and fetal brain super-resolution algorithms applied. 16 teams participated in the challenge, and 17 algorithms were evaluated. Here, a detailed overview and analysis of the challenge results are provided, focusing on the generalizability of the submissions. Both in- and out of domain, the white matter and ventricles were segmented with the highest accuracy, while the most challenging structure remains the cerebral cortex due to anatomical complexity. The FeTA Challenge 2022 was able to successfully evaluate and advance generalizability of multi-class fetal brain tissue segmentation algorithms for MRI and it continues to benchmark new algorithms. The resulting new methods contribute to improving the analysis of brain development in utero.

Magnetic Resonance Imaging (MRI) of the fetal brain has become a key tool for studying brain development in vivo. Yet, its assessment remains challenging due to variability in brain maturation, imaging protocols, and uncertain estimates of Gestational Age (GA). To overcome these, brain atlases provide a standardized reference framework that facilitates objective evaluation and comparison across subjects by aligning the atlas and subjects in a common coordinate system. In this work, we introduce a novel deep-learning framework for generating continuous, age-specific fetal brain atlases for real-time fetal brain tissue segmentation. The framework combines a direct registration model with a conditional discriminator. Trained on a curated dataset of 219 neurotypical fetal MRIs spanning from 21 to 37 weeks of gestation. The method achieves high registration accuracy, captures dynamic anatomical changes with sharp structural detail, and robust segmentation performance with an average Dice Similarity Coefficient (DSC) of 86.3 % across six brain tissues. Furthermore, volumetric analysis of the generated atlases reveals detailed neurotypical growth trajectories, providing valuable insights into the maturation of the fetal brain. This approach enables individualized developmental assessment with minimal pre-processing and real-time performance, supporting both research and clinical applications. The model code is available at https://github.com/cirmuw/fetal-brain-atlas.

Multiplexed tissue imaging measures dozens of protein markers per cell, yet most deep learning models still apply early channel fusion, assuming shared structure across markers. We investigate whether preserving marker independence, combined with deliberately shallow architectures, provides a more suitable inductive bias for self-supervised representation learning in multiplex data than increasing model scale. Using a Hodgkin lymphoma CODEX dataset with 145,000 cells and 49 markers, we compare standard early-fusion CNNs with channel-separated architectures, including a marker-aware baseline and our novel shallow Channel-Independent Model (CIM-S) with 5.5K parameters. After contrastive pretraining and linear evaluation, early-fusion models show limited ability to retain marker-specific information and struggle particularly with rare-cell discrimination. Channel-independent architectures, and CIM-S in particular, achieve substantially stronger representations despite their compact size. These findings are consistent across multiple self-supervised frameworks, remain stable across augmentation settings, and are reproducible across both the 49-marker and reduced 18-marker settings. These results show that lightweight, channel-independent architectures can match or surpass deep early-fusion CNNs and foundation models for multiplex representation learning. Code is available at https://github.com/SimonBon/CIM-S.

As scientists interested in fetal, infant, and toddler (FIT) neurodevelopment, our research questions often focus on how individual children differ in their neurodevelopment and the predictive value of those individual differences for long-term neural and behavioral outcomes. Measuring and interpreting individual differences in neurodevelopment can present challenges: Is there a "standard" way for the human brain to develop? How do the semantic, practical, or theoretical constraints that we place on studying "development" influence how we measure and interpret individual differences? While it is important to consider these questions across the lifespan, they are particularly relevant for conducting and interpreting research on individual differences in fetal, infant, and toddler neurodevelopment due to the rapid, profound, and heterogeneous changes happening during this period, which may be predictive of long-term outcomes. This article, therefore, has three goals: 1) to provide an overview about how individual differences in neurodevelopment are studied in the field of developmental cognitive neuroscience, 2) to identify challenges and considerations when studying individual differences in neurodevelopment, and 3) to discuss potential implications and solutions moving forward.

Fetal brain tissue segmentation from magnetic resonance imaging (MRI) is crucial for studying neurodevelopment, but remains challenging due to data heterogeneity and limited annotations. Domain randomization (DR) has recently emerged as a promising strategy for single-source domain generalization by synthesizing training images with randomized artifacts, contrast, and resolution. In this work, we investigate how to maximize the out-of-domain (OOD) generalization of DR-based methods. We evaluate several synthetic data generation strategies for DR, with a particular focus on our recently proposed framework, FetalSynthSeg. We show that simple Gaussian mixture-based intensity modeling outperforms more complex physics-based simulations, and that intensity clustering (subdividing tissue classes based on intensity) improves OOD robustness. Evaluated on 348 fetal subjects from four sites spanning 0.55-3T and both T1w and T2w contrasts, FetalSynthSeg reaches state-of-the-art performance on several FeTA 2024 testing datasets (80-85 Dice score) and, for the first time, offers robust segmentation on modalities other than T2w for fetal brain segmentation (80 Dice on dHCP-T1w dataset). Compared with state-of-the-art methods such as BOUNTI, nnU-Net ensemble, and the FeTA 2024 winner, FetalSynthSeg delivers comparable or superior accuracy while maintaining strong robustness across domain shifts. Our code, model weights, and Docker image ready for easy inference are available at https://hub.docker.com/r/vzalevskyi/fetalsynthseg.

Motivation: Immediate changes in functionality during brain surgery in tumor and epilepsy patients are worth investigating in order to improve prediction of surgical outcomes. Goal(s): We want to implement a preprocessing-pipeline for pre- and post-resection data that allows comparison between both scans and the application of further analysis methods. Approach: We propose a two-step approach, where we first pre-register the anatomical data to MNI-space with consideration of the resection area and then use this data in a second step for preprocessing of fMRI data. Results: The preprocessing gives satisfactory results that enable further analysis of intraoperative fMRI data, such as PICA. Impact: We showed that the difficult case of pre- and post-resection data preprocessing is feasible and allows analysis of intraoperative fMRI data. This enables further investigation of changes in brain functionality during surgery which might lead to improvements in neurosurgery.

Multiplex Imaging (MI) enables the simultaneous visualization of multiple biological markers in separate imaging channels at subcellular resolution, providing valuable insights into cell-type heterogeneity and spatial organization. However, current computational pipelines rely on cell segmentation algorithms, which require laborious fine-tuning and can introduce downstream errors due to inaccurate single-cell representations. We propose a segmentation-free deep learning approach that leverages grouped convolutions to learn interpretable embedded features from each imaging channel, enabling robust cell-type identification without manual feature selection. Validated on an Imaging Mass Cytometry dataset of 1.8 million cells from neuroblastoma patients, our method enables the accurate identification of known cell types, showcasing its scalability and suitability for high-dimensional MI data.

Detecting genetic aberrations is crucial in cancer diagnosis, typically through fluorescence in situ hybridization (FISH). However, existing FISH image classification methods face challenges due to signal variability, the need for costly manual annotations and fail to adequately address the intrinsic uncertainty. We introduce a novel approach that leverages synthetic images to eliminate the requirement for manual annotations and utilizes a joint contrastive and classification objective for training to account for inter-class variation effectively. We demonstrate the superior generalization capabilities and uncertainty calibration of our method, which is trained on synthetic data, by testing it on a manually annotated dataset of real-world FISH images. Our model offers superior calibration in terms of classification accuracy and uncertainty quantification with a classification accuracy of 96.7 https://github.com/SimonBon/FISHing .

Abstract Introduction With the application of high-resolution 3D 7 Tesla Magnetic Resonance Spectroscopy Imaging (MRSI) in high-grade gliomas, we previously identified intratumoral metabolic heterogeneities. In this study, we evaluated the potential of 3D 7 T-MRSI for the preoperative noninvasive classification of glioma grade and isocitrate dehydrogenase (IDH) status. We demonstrated that IDH mutation and glioma grade are detectable by ultra-high field (UHF) MRI. This technique might potentially optimize the perioperative management of glioma patients. Methods We prospectively included 36 patients with WHO 2021 grade 2–4 gliomas (20 IDH mutated, 16 IDH wildtype). Our 7 T 3D MRSI sequence provided high-resolution metabolic maps (e.g., choline, creatine, glutamine, and glycine) of these patients’ brains. We employed multivariate random forest and support vector machine models to voxels within a tumor segmentation, for classification of glioma grade and IDH mutation status. Results Random forest analysis yielded an area under the curve (AUC) of 0.86 for multivariate IDH classification based on metabolic ratios. We distinguished high- and low-grade tumors by total choline (tCho) / total N-acetyl-aspartate (tNAA) ratio difference, yielding an AUC of 0.99. Tumor categorization based on other measured metabolic ratios provided comparable accuracy. Conclusions We successfully classified IDH mutation status and high- versus low-grade gliomas preoperatively based on 7 T MRSI and clinical tumor segmentation. With this approach, we demonstrated imaging based tumor marker predictions at least as accurate as comparable studies, highlighting the potential application of MRSI for pre-operative tumor classifications.

Measuring and understanding functional fetal brain development in utero is critical for the study of the developmental foundations of our cognitive abilities, possible early detection of disorders, and their prevention. Thalamocortical connections are an intricate component of shaping the cortical layout, but so far, only ex-vivo studies provide evidence of how axons enter the sub-plate and cortex during this highly dynamic phase. Evidence for normal in-utero development of the functional thalamocortical connectome in humans is missing. Here, we modeled fetal functional thalamocortical connectome development using in-utero functional magnetic resonance imaging in fetuses observed from 19th to 40th weeks of gestation (GW). We observed a peak increase of thalamocortical functional connectivity strength between 29th and 31st GW, right before axons establish synapses in the cortex. The cortico-cortical connectivity increases in a similar time window, and exhibits significant functional laterality in temporal-superior, -medial, and -inferior areas. Homologous regions exhibit overall similar mirrored connectivity profiles, but this similarity decreases during gestation giving way to a more diverse cortical interconnectedness. Our results complement the understanding of structural development of the human connectome and may serve as the basis for the investigation of disease and deviations from a normal developmental trajectory of connectivity development.