Risk stratification is a core challenge in fetal growth restriction (FGR) care, in part because FGR does not represent a single diagnosis but instead is a finding that is associated with morbidity. Considerable effort has been invested in the development and study of methods to identify fetuses at risk of morbidity and who warrant intervention across multiple domains: Doppler ultrasound, maternal biomarkers, multivariable modeling, and artificial intelligence. It is likely that the most promising advances will integrate findings from across these domains, but further investigation remains necessary.

To address the limitations of traditional CT-guided pulmonary nodule interventions, such as excessive radiation exposure, prolonged procedure times, and limited precision, we developed an electromagnetic navigation surgical robotic system (ENSRS) to enhance accuracy, efficiency, and safety in percutaneous procedures. The ENSRS integrates artificial intelligence to automate the segmentation of pulmonary nodules and surrounding anatomical structures, generating a detailed surgical environment. A customized path-planning algorithm facilitates minimally invasive access, whereas submillimeter localization using fiducial markers ensures precise coordinate registration. Adaptive multicalibration strategies and robust safety protocols enhance procedural reliability. System performance was evaluated through phantom and animal experiments, with comparisons to traditional CTguided techniques. The ENSRS achieved a groove localization error of 0.51 ± 0.27 mm across 63 patches and a classification accuracy of 100%. In phantom studies, it demonstrated significantly reduced puncture error (0.81 ± 0.98 mm vs. 3.50 ± 2.88 mm, p < 0.0001), required fewer CT scans (1.02 ± 0.25 vs. 1.53 ± 0.92) and shortened puncture times (39.01 ± 29.71 s). In animal experiments, ENSRS achieved improved accuracy (0.33 ± 0.74 mm vs. 1.86 ± 0.99 mm, p = 0.015). The safety outcomes were comparable between the groups, with one pneumothorax reported each. ENSRS improves the precision, efficiency, and safety of pulmonary nodule interventions, outperforming traditional CT-guided methods in phantom and animal models. This system offers a promising approach to pulmonary interventions by combining robotic precision with intelligent planning and tracking, potentially enhancing outcomes in minimally invasive procedures.

Major adverse cardiac events (MACE) pose a high life-threatening risk to patients with arrhythmogenic right ventricular cardiomyopathy (ARVC). Cardiac magnetic resonance (CMR) has been proven to reflect the risk of MACE, but two challenges remain: limited dataset size due to the rarity of ARVC and overlapping image distributions between non-MACE and MACE patients. To address these challenges by fully leveraging the dynamic and spatial information in the limited CMR dataset, a deep learning-based risk prediction model named Three-Tier Spatiotemporal Transformer (TTST) is proposed in this paper, which utilizes three transformer-based tiers to sequentially extract and fuse features from three domains: the 2D spatial domain of each slice, the temporal dimension of slice sequence and the inter-slice depth dimension. In TTST, a pericardial adipose tissue (PAT) embedding unit is proposed to incorporate the dynamic and positional information of PAT, a key biomarker for distinguishing MACE from non-MACE based on its thickening and reduced motion, as prior knowledge to reduce reliance on large-scale datasets. Additionally, a patch voting unit is introduced to pick out local features that highlight more indicative regions in the heart, guided by the PAT embedding information. Experimental results demonstrate that TTST outperforms existing classification methods in MACE prediction (internal: AUC = 0.89, ACC = 84.02%; external: AUC = 0.87, ACC = 86.21%). Clinically, TTST achieves effective risk prediction performance either independently (C-index = 0.744) or in combination with the existing 5-year risk score model (increasing C-index from 0.686 to 0.777). Code and dataset are accessible at https://github.com/DFLAG-NEU.

This study evaluated the accuracy of large language models (LLMs) in assigning Coronary Artery Disease Reporting and Data System (CAD-RADS) 2.0 categories and modifiers based on real-world coronary CT angiography (CCTA) reports and compared their accuracy with human readers. From 2752 eligible CCTA reports generated at an academic hospital between January and September 2024, 180 were randomly selected to fit a balanced distribution of categories and modifiers. The reference standard was established by consensus between two expert cardiac radiologists with 15 and 14 years of experience, respectively. Four LLMs (O1, GPT-4o, GPT-4, GPT-3.5-turbo) and four human readers (a cardiac radiologist, a fellow, two residents) independently assigned CAD-RADS categories and modifiers for each report. For LLMs, the input prompt consisted of the report and a summary of CAD-RADS 2.0. The accuracy of evaluators in full CAD-RADS categorization was compared with O1 using McNemar tests. O1 demonstrated the highest accuracy (90.7%) in full CAD-RADS categorization, outperforming GPT-4o (73.8%), GPT-4 (59.7%), GPT-3.5-turbo (25.8%), the fellow (83.3%), and resident 1 (83.3%; all P-values ≤ 0.01). However, there was no significant difference in accuracy when compared to the cardiac radiologist (86.1%; P = 0.12) and resident 2 (89.4%; P = 0.68). Processing time per report ranged 1.34-16.61 s for LLMs, whereas human readers required 32.10-55.06 s. In the external validation dataset (n = 327) derived from two independent institutions, O1 achieved 95.7% accuracy for full CAD-RADS categorization. In conclusion, compared to human readers, O1 exhibited similar or higher accuracy and shorter processing times to produce a full CAD-RADS 2.0 categorization based on CCTA reports.

<b>Purpose</b>: Early diagnosis of schizophrenia plays a crucial role in improving patients' prognosis and effectively reducing the social burden. However, traditional diagnosis methods mainly rely on the subjectivity of clinical evaluation and lack objective quantitative basis, which poses significant challenges to the early recognition of schizophrenia. In recent years, although machine learning methods based on neuroimaging have made certain progress, when dealing with high dimensional, small sample MRI data, there are still problems such as low automation of feature extraction and insufficient model generalisation ability. <b>Methods</b>: To address these issues, we propose MRI feature engineering and support vector machines (SVM) framework for schizophrenia recognition. First, the framework reduces the structural differences between individuals through preprocessing operations such as skull stripping and data registration. Second, it extracts macroscopic statistical features and optimises the feature set by screening key region-of-interest features using feature masking technology. Finally, it uses the SVM to analyse the discriminative patterns of features to complete the recognition. <b>Results</b>: On the COBRE dataset, this paper uses five-fold cross-validation to comprehensively evaluate the model performance. The experimental results show that the average classification accuracy of this method reaches 95.00%. Meanwhile, it significantly outperforms six mainstream machine learning algorithms in multiple metrics. <b>Conclusions</b>: This paper provides an objective and innovative approach for the auxiliary diagnosis of schizophrenia and offers strong support for its early intervention practices.

Diffusion-weighted imaging (DWI) enables non-invasive characterization of tissue microstructure, yet acquiring densely sampled q-space data remains time-consuming and impractical in many clinical settings. Existing deep learning methods are typically constrained by fixed q-space sampling, limiting their adaptability to variable sampling scenarios. In this paper, we propose a Q-space Guided Multi-Modal Translation Network (Q-MMTN) for synthesizing multi-shell, high-angular resolution DWI (MS-HARDI) from flexible q-space sampling, leveraging commonly acquired structural data (e.g., T1- and T2-weighted MRI). Q-MMTN integrates the hybrid encoder and multi-modal attention fusion mechanism to effectively extract both local and global complementary information from multiple modalities. This design enhances feature representation and, together with a flexible q-space-aware embedding, enables dynamic modulation of internal features without relying on fixed sampling schemes. Additionally, we introduce a set of task-specific constraints, including adversarial, reconstruction, and anatomical consistency losses, which jointly enforce anatomical fidelity and signal realism. These constraints guide Q-MMTN to accurately capture the intrinsic and nonlinear relationships between directional DWI signals and q-space information. Extensive experiments across four lifespan datasets of children, adolescents, young and older adults demonstrate that Q-MMTN outperforms existing methods, including 1D-qDL, 2D-qDL, MESC-SD, and Q-GAN in estimating parameter maps and fiber tracts with fine-grained anatomical details. Notably, its ability to accommodate flexible q-space sampling highlights its potential as a promising toolkit for clinical and research applications. Our code is available at https://github.com/Idea89560041/Q-MMTN.

Whole-body MRI (WB-MRI) is a non-invasive imaging technique offering comprehensive anatomical coverage and high-resolution contrast, ideal for evaluating multi-system diseases without ionizing radiation. Recent advancements in parallel imaging have enhanced its utility in oncology and non-oncology applications. WB-MRI is routinely used for cancer staging, including in multiple myeloma (MM), prostate, and colorectal cancer, as well as in evaluating cancer predisposition syndromes and inflammatory conditions. In MM, WB-MRI is crucial for assessing bone marrow involvement and monitoring treatment response. However, manual analysis of WB-MRI for bone marrow (BM) diseases is time-consuming and prone to data loss, limiting its clinical utility. Tumor load in MM is spatially heterogeneous, requiring detailed BM feature extraction-such as size, volume, intensity, and texture-across the entire bone marrow space. Current guidelines, including Myeloma Response Assessment and Diagnosis System (MY-RADS), offer limited interpretation analysis, and automated methods for comprehensive BM characterisation remain underexplored. These goals rely on automated BM segmentation as a foundational step. This study introduces U-Swing, a hybrid deep learning model combining Swin Transformer (SM) and U-Net Modules (UM) designed for WB-MRI whole spine bone marrow segmentation. U-Swing incorporates dynamic feature fusion of the SMs and UMs via U-Swing Patch Fusion and hierarchical optimization through Stage-Wise U-Swing Adaptation (SUA). The model demonstrated superior performance in WB-MRI bone marrow segmentation using T1-weighted turbo spin-echo (T1W-TSE) sequences, achieving a Dice Similarity (DS) score of 0.928, a Hausdorff Distance (HD95) of 3.919 mm, and an Average Symmetric Surface Distance (ASSD) of 0.281 mm, outperforming model architectures such as U-Net, Swin-UNETR, and UNETR.

This study aimed to develop and evaluate automated deep learning models for multi-class classification of dental conditions in panoramic X-ray images, comparing the effectiveness of custom CNN architectures with attention mechanisms, pre-trained models, and hybrid approaches. A dataset of 1,512 panoramic dental X-rays was preprocessed through segmentation, creating 4,764 class-balanced images across four categories: Fillings, Cavity, Implant, and Impacted Tooth. Data augmentation and preprocessing techniques including brightness adjustment, CLAHE enhancement, and normalization were applied. Multiple architectures were evaluated: custom CNN with attention mechanism, pre-trained models (VGG16, ResNet50, Xception) with attention integration, and hybrid CNN-machine learning approaches (CNN + SVM, CNN + Random Forest, CNN + Decision Tree). Performance was assessed using 5-fold cross-validation with accuracy, precision, recall, F1-score, and ROC-AUC metrics. The hybrid CNN + Random Forest model with preprocessing achieved the highest performance: 90.6% accuracy, 0.987 ROC-AUC, and 0.906 F1-score. Preprocessing consistently improved performance across all architectures, with accuracy gains ranging from 6.3% (VGG16) to 19.4% (ResNet50). The custom CNN with attention mechanism reached 86.0% accuracy, outperforming conventional CNN approaches (76.0%). Among pre-trained models, Xception with preprocessing achieved 79.8% accuracy. Hybrid CNN-machine learning approaches demonstrated superior performance for dental condition classification compared to end-to-end deep learning models. However, clinical implementation requires addressing the dataset limitation of lacking normal/healthy cases and conducting prospective validation studies across diverse clinical populations to establish real-world effectiveness and safety.

Cardiac remodeling occurs in the mature heart and is a cascade of adaptations in response to stress, which are primed in early life. A key question remains as to the processes that regulate the geometry and motion of the heart and how it adapts to stress. We performed spatially resolved phenotyping using machine learning-based analysis of cardiac magnetic resonance imaging in 47 549 UK Biobank participants. We analyzed 16 left ventricular spatial phenotypes, including regional myocardial wall thickness and systolic strain in both circumferential and radial directions. In up to 40 058 participants, genetic associations across the allele frequency spectrum were assessed using genome-wide association studies with imputed genotype participants, and exome-wide association studies and gene-based burden tests using whole-exome sequencing data. We integrated transcriptomic data from the GTEx project and used pathway enrichment analyses to further interpret the biological relevance of identified loci. To investigate causal relationships, we conducted Mendelian randomization analyses to evaluate the effects of blood pressure on regional cardiac traits and the effects of these traits on cardiomyopathy risk. We found 42 loci associated with cardiac structure and contractility, many of which reveal patterns of spatial organization in the heart. Whole-exome sequencing revealed 3 additional variants not captured by the genome-wide association study, including a missense variant in <i>CSRP3</i> (minor allele frequency 0.5%). The majority of newly discovered loci are found in cardiomyopathy-associated genes, suggesting that they regulate spatially distinct patterns of remodeling in the left ventricle in an adult population. Our causal analysis also found regional modulation of blood pressure on cardiac wall thickness and strain. These findings provide a comprehensive description of the pathways that orchestrate heart development and cardiac remodeling. These data highlight the role that cardiomyopathy-associated genes have on the regulation of spatial adaptations in those without known disease.

After total hip arthroplasty (THA), dual-energy x-ray absorptiometry (DXA) is used as necessary to assess the bone mineral density (BMD) in the Gruen zones around the femoral stem implants. Although periprosthetic BMD may serve as a potential indicator for evaluating stress adaptive remodelling and stem fixation, several factors can introduce measurement errors. Therefore, an automated method was applied using quantitative CT, verified for the total hip with correlation coefficient > 0.9, for BMD assessment in the Gruen zones. This was a retrospective analysis of 71 hips from 58 participants (9 male and 49 female) who underwent THA using the same taper-wedge type stem. Preoperative and postoperative CT scans were acquired alongside DXA measurements of the Gruen zones. A deep-learning method was used to measure BMD in the Gruen zones from preoperative CT images by embedding the stem position information acquired from postoperative CT images through iterative closest point registration. CT images were rotated to the neutral position and were projected anteroposteriorly to generate a digitally reconstructed radiograph to measure the BMD at each zone (CT-aBMD). Correlations between CT-aBMD and DXA measurements were assessed for each zone. The correlations between CT-aBMD and DXA measurements for zones 1 to 7 were 0.924, 0.783, 0.817, 0.921, 0.731, 0.847, and 0.677, respectively (p < 0.001 for all). Our results based on CT analysis suggest that DXA is generally reliable for assessing BMD in the Gruen zones. However, caution may be advised for zones 5 and 7 because of limited correlations. As zone 7 plays a crucial role in stem fixation, during longitudinal evaluation of post-THA stress adaptive remodelling, we recommend ensuring cautious interpretation and consistent BMD measurements using the image attached to the DXA report. It is imperative to calculate the least significant change for accurate BMD evaluation.