The objective of this retrospective study is to develop and validate an artificial intelligence model constrained by the anatomical structure of the brain with the aim of improving the accuracy of prenatal diagnosis of fetal cerebellar hypoplasia using ultrasound imaging. Fetal central nervous system dysplasia is one of the most prevalent congenital malformations, and cerebellar hypoplasia represents a significant manifestation of this anomaly. Accurate clinical diagnosis is of great importance for the purpose of prenatal screening of fetal health. Although ultrasound has been extensively utilized to assess fetal development, the accurate assessment of cerebellar development remains challenging due to the inherent limitations of ultrasound imaging, including low resolution, artifacts, and acoustic shadowing of the skull. This retrospective study included 302 cases diagnosed with cerebellar hypoplasia and 549 normal pregnancies collected from Maternal and Child Health Hospital of Hubei Province between September 2019 and September 2023. For each case, experienced ultrasound physicians selected appropriate brain ultrasound images to delineate the boundaries of the skull, cerebellum, and cerebellomedullary cistern. These cases were divided into one training set and two test sets, based on the examination dates. This study then proposed a dual-branch deep learning classification network, anatomical structure-constrained network (ASC-Net), which took ultrasound images and anatomical structure masks as separate inputs. The performance of the ASC-Net was extensively evaluated and compared with several state-of-the-art deep learning networks. The impact of anatomical structures on the performance of ASC-Net was carefully examined. ASC-Net demonstrated superior performance in the diagnosis of cerebellar hypoplasia, achieving classification accuracies of 0.9778 and 0.9222, as well as areas under the receiver operating characteristic curve of 0.9986 and 0.9265 on the two test sets. These results significantly outperformed several state-of-the-art networks on the same dataset. In comparison to other studies on cerebellar hypoplasia auxiliary diagnosis, ASC-Net also demonstrated comparable or even better performance. A subgroup analysis revealed that ASC-Net was more capable of distinguishing cerebellar hypoplasia in cases with gestational weeks greater than 30 weeks. Furthermore, when constrained by anatomical structures of both the cerebellum and cistern, ASC-Net exhibited the best performance compared to other kinds of structural constraint. The development and validation of ASC-Net have significantly enhanced the accuracy of prenatal diagnosis of cerebellar hypoplasia using ultrasound images. This study highlights the importance of anatomical structures of the fetal cerebellum and cistern on the performance of the diagnostic artificial intelligence model in ultrasound. This might provide new insights for clinical diagnosis of cerebellar hypoplasia, assist clinicians in providing more targeted advice and treatment during pregnancy, and contribute to improved perinatal healthcare. ASC-Net is open-sourced and publicly available in a GitHub repository at https://github.com/Wwwwww111112/ASC-Net .

Recognition of tumors is very important in clinical practice and radiomics; however, the segmentation task currently still needs to be done manually by experts. With the development of deep learning, automatic segmentation of tumors is gradually becoming possible. This paper combines the molecular information from PET and the pathology information from CT for tumor segmentation. A dual-branch encoder is designed based on SE-UNet (Squeeze-and-Excitation Normalization UNet) and Transformer, 3D Convolutional Block Attention Module (CBAM) is added to skip-connection, and BCE loss is used in training for improving segmentation accuracy. The new model is named TASE-UNet. The proposed method was tested on the HECKTOR2022 dataset, which obtains the best segmentation accuracy compared with state-of-the-art methods. Specifically, we obtained results of 76.10 <math xmlns="http://www.w3.org/1998/Math/MathML"><mo>%</mo></math> and 3.27 for the two key evaluation metrics, DSC and HD95. Experiments demonstrate that the designed network is reasonable and effective. The full implementation is available at https://github.com/LiMingrui1/TASE-UNet .

Vision-language models and their adaptations to image segmentation tasks present enormous potential for producing highly accurate and interpretable results. However, implementations based on CLIP and BiomedCLIP are still lagging behind more sophisticated architectures such as CRIS. In this work, instead of focusing on text prompt engineering as is the norm, we attempt to narrow this gap by showing how to ensemble vision-language segmentation models (VLSMs) with a low-complexity CNN. By doing so, we achieve a significant Dice score improvement of 6.3% on the BKAI polyp dataset using the ensembled BiomedCLIPSeg, while other datasets exhibit gains ranging from 1% to 6%. Furthermore, we provide initial results on additional four radiology and non-radiology datasets. We conclude that ensembling works differently across these datasets (from outperforming to underperforming the CRIS model), indicating a topic for future investigation by the community. The code is available at https://github.com/juliadietlmeier/VLSM-Ensemble.

Diagnostic ultrasound has long filled a crucial niche in medical imaging thanks to its portability, affordability, and favorable safety profile. Now, multi-view hardware and deep-learning-based image reconstruction algorithms promise to extend this niche to increasingly sophisticated applications, such as volume rendering and long-term organ monitoring. However, progress on these fronts is impeded by the complexities of ultrasound electronics and by the scarcity of high-fidelity radiofrequency data. Evidently, there is a critical need for tools that enable rapid ultrasound prototyping and generation of synthetic data. We meet this need with MUSiK, the first open-source ultrasound simulation library expressly designed for multi-view acoustic simulations of realistic anatomy. This library covers the full gamut of image acquisition: building anatomical digital phantoms, defining and positioning diverse transducer types, running simulations, and reconstructing images. In this paper, we demonstrate several use cases for MUSiK. We simulate in vitro multi-view experiments and compare the resolution and contrast of the resulting images. We then perform multiple conventional and experimental in vivo imaging tasks, such as 2D scans of the kidney, 2D and 3D echocardiography, 2.5D tomography of large regions, and 3D tomography for lesion detection in soft tissue. Finally, we introduce MUSiK's Bayesian reconstruction framework for multi-view ultrasound and validate an original SNR-enhancing reconstruction algorithm. We anticipate that these unique features will seed new hypotheses and accelerate the overall pace of ultrasound technological development. The MUSiK library is publicly available at github.com/norway99/MUSiK.

Lung lobe segmentation is required to assess lobar function with nuclear imaging before surgical interventions. We evaluated the performance of open-source deep learning-based lung lobe segmentation tools, compared to a similar nnU-Net model trained on a smaller but more representative clinical dataset. We collated and semi-automatically segmented an internal dataset of 164 computed tomography scans and classified them for task difficulty as easy, moderate, or hard. The performance of three open-source models-multi-organ objective segmentation (MOOSE), TotalSegmentator, and LungMask-was assessed using Dice similarity coefficient (DSC), robust Hausdorff distance (rHd95), and normalized surface distance (NSD). Additionally, we trained, validated, and tested an nnU-Net model using our local dataset and compared its performance with that of the other software on the test subset. All models were evaluated for generalizability using an external competition (LOLA11, n = 55). TotalSegmentator outperformed MOOSE in DSC and NSD across all difficulty levels (p < 0.001), but not in rHd95 (p = 1.000). MOOSE and TotalSegmentator surpassed LungMask across metrics and difficulty classes (p < 0.001). Our model exceeded all other models on the internal dataset (n = 33) in all metrics, across all difficulty classes (p < 0.001), and on the external dataset. Missing lobes were correctly identified only by our model and LungMask in 3 and 1 of 7 cases, respectively. Open-source segmentation tools perform well in straightforward cases but struggle in unfamiliar, complex cases. Training on diverse, specialized datasets can improve generalizability, emphasizing representative data over sheer quantity. Training lung lobe segmentation models on a local variety of cases improves accuracy, thus enhancing presurgical planning, ventilation-perfusion analysis, and disease localization, potentially impacting treatment decisions and patient outcomes in respiratory and thoracic care. Deep learning models trained on non-specialized datasets struggle with complex lung anomalies, yet their real-world limitations are insufficiently assessed. Training an identical model on a smaller yet clinically diverse and representative cohort improved performance in challenging cases. Data diversity outweighs the quantity in deep learning-based segmentation models. Accurate lung lobe segmentation may enhance presurgical assessment of lung lobar ventilation and perfusion function, optimizing clinical decision-making and patient outcomes.

Magnetic resonance imaging of fetal and neonatal brains reveals rapid neurodevelopment marked by substantial anatomical changes unfolding within days. Studying this critical stage of the developing human brain, therefore, requires accurate brain models-referred to as atlases-of high spatial and temporal resolution. To meet these demands, established traditional atlases and recently proposed deep learning-based methods rely on large and comprehensive datasets. This poses a major challenge for studying brains in the presence of pathologies for which data remains scarce. We address this limitation with CINeMA (Conditional Implicit Neural Multi-Modal Atlas), a novel framework for creating high-resolution, spatio-temporal, multimodal brain atlases, suitable for low-data settings. Unlike established methods, CINeMA operates in latent space, avoiding compute-intensive image registration and reducing atlas construction times from days to minutes. Furthermore, it enables flexible conditioning on anatomical features including gestational age, birth age, and pathologies like agenesis of the corpus callosum and ventriculomegaly of varying degree. CINeMA supports downstream tasks such as tissue segmentation and age prediction whereas its generative properties enable synthetic data creation and anatomically informed data augmentation. Surpassing state-of-the-art methods in accuracy, efficiency, and versatility, CINeMA represents a powerful tool for advancing brain research. We release the code and atlases at https://github.com/m-dannecker/CINeMA.

Low-field portable magnetic resonance imaging (pMRI) devices address a crucial requirement in the realm of healthcare by offering the capability for on-demand and timely access to MRI, especially in the context of routine stroke emergency. Nevertheless, images acquired by these devices often exhibit poor clarity and low resolution, resulting in their reduced potential to support precise diagnostic evaluations and lesion quantification. In this paper, we propose a 3D deep learning based model, named Stroke-Aware CycleGAN (SA-CycleGAN), to enhance the quality of low-field images for further improving diagnosis of routine stroke. Firstly, based on traditional CycleGAN, SA-CycleGAN incorporates a prior of stroke lesions by applying a novel spatial feature transform mechanism. Secondly, gradient difference losses are combined to deal with the problem that the synthesized images tend to be overly smooth. We present a dataset comprising 101 paired high-field and low-field diffusion-weighted imaging (DWI), which were acquired through dual scans of the same patient in close temporal proximity. Our experiments demonstrate that SA-CycleGAN is capable of generating images with higher quality and greater clarity compared to the original low-field DWI. Additionally, in terms of quantifying stroke lesions, SA-CycleGAN outperforms existing methods. The lesion volume exhibits a strong correlation between the generated images and the high-field images, with R=0.852. In contrast, the lesion volume correlation between the low-field images and the high-field images is notably lower, with R=0.462. Furthermore, the mean absolute difference in lesion volumes between the generated images and high-field images (1.73±2.03 mL) was significantly smaller than the difference between the low-field images and high-field images (2.53±4.24 mL). It shows that the synthesized images not only exhibit superior visual clarity compared to the low-field acquired images, but also possess a high degree of consistency with high-field images. In routine clinical practice, the proposed SA-CycleGAN offers an accessible and cost-effective means of rapidly obtaining higher-quality images, holding the potential to enhance the efficiency and accuracy of stroke diagnosis in routine clinical settings. The code and trained models will be released on GitHub: SA-CycleGAN.

Functional magnetic resonance imaging (fMRI) is a powerful tool for probing brain function, yet reliable clinical diagnosis is hampered by low signal-to-noise ratios, inter-subject variability, and the limited frequency awareness of prevailing CNN- and Transformer-based models. Moreover, most fMRI datasets lack textual annotations that could contextualize regional activation and connectivity patterns. We introduce RTGMFF, a framework that unifies automatic ROI-level text generation with multimodal feature fusion for brain-disorder diagnosis. RTGMFF consists of three components: (i) ROI-driven fMRI text generation deterministically condenses each subject's activation, connectivity, age, and sex into reproducible text tokens; (ii) Hybrid frequency-spatial encoder fuses a hierarchical wavelet-mamba branch with a cross-scale Transformer encoder to capture frequency-domain structure alongside long-range spatial dependencies; and (iii) Adaptive semantic alignment module embeds the ROI token sequence and visual features in a shared space, using a regularized cosine-similarity loss to narrow the modality gap. Extensive experiments on the ADHD-200 and ABIDE benchmarks show that RTGMFF surpasses current methods in diagnostic accuracy, achieving notable gains in sensitivity, specificity, and area under the ROC curve. Code is available at https://github.com/BeistMedAI/RTGMFF.

Generating realistic MRIs to accurately predict future changes in the structure of brain is an invaluable tool for clinicians in assessing clinical outcomes and analysing the disease progression at the patient level. However, current existing methods present some limitations: (i) some approaches fail to explicitly capture the relationship between structural changes and time intervals, especially when trained on age-imbalanced datasets; (ii) others rely only on scan interpolation, which lack clinical utility, as they generate intermediate images between timepoints rather than future pathological progression; and (iii) most approaches rely on 2D slice-based architectures, thereby disregarding full 3D anatomical context, which is essential for accurate longitudinal predictions. We propose a 3D Temporally-Aware Diffusion Model (TADM-3D), which accurately predicts brain progression on MRI volumes. To better model the relationship between time interval and brain changes, TADM-3D uses a pre-trained Brain-Age Estimator (BAE) that guides the diffusion model in the generation of MRIs that accurately reflect the expected age difference between baseline and generated follow-up scans. Additionally, to further improve the temporal awareness of TADM-3D, we propose the Back-In-Time Regularisation (BITR), by training TADM-3D to predict bidirectionally from the baseline to follow-up (forward), as well as from the follow-up to baseline (backward). Although predicting past scans has limited clinical applications, this regularisation helps the model generate temporally more accurate scans. We train and evaluate TADM-3D on the OASIS-3 dataset, and we validate the generalisation performance on an external test set from the NACC dataset. The code will be available upon acceptance.

Harmonizing multisite functional magnetic resonance imaging (fMRI) data is crucial for eliminating site-specific variability that hinders the generalizability of machine learning models. Traditional harmonization techniques, such as ComBat, depend on additive and multiplicative factors, and may struggle to capture the non-linear interactions between scanner hardware, acquisition protocols, and signal variations between different imaging sites. In addition, these statistical techniques require data from all the sites during their model training which may have the unintended consequence of data leakage for ML models trained using this harmonized data. The ML models trained using this harmonized data may result in low reliability and reproducibility when tested on unseen data sets, limiting their applicability for general clinical usage. In this study, we propose Autoencoders (AEs) as an alternative for harmonizing multisite fMRI data. Our designed and developed framework leverages the non-linear representation learning capabilities of AEs to reduce site-specific effects while preserving biologically meaningful features. Our evaluation using Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, containing 1,035 subjects collected from 17 centers demonstrates statistically significant improvements in leave-one-site-out (LOSO) cross-validation evaluations. All AE variants (AE, SAE, TAE, and DAE) significantly outperformed the baseline mode (p < 0.01), with mean accuracy improvements ranging from 3.41% to 5.04%. Our findings demonstrate the potential of AEs to harmonize multisite neuroimaging data effectively enabling robust downstream analyses across various neuroscience applications while reducing data-leakage, and preservation of neurobiological features. Our open-source code is made available at https://github.com/pcdslab/Autoencoder-fMRI-Harmonization .