Integration of AI and XR in TAVR is revolutionizing the management of severe aortic stenosis by enhancing diagnostic accuracy, risk stratification, and pre-procedural planning. Advanced algorithms now facilitate precise electrocardiographic, echocardiographic, and CT-based assessments that reduce observer variability and enable patient-specific risk prediction. Immersive XR technologies, including augmented, virtual, and mixed reality, improve spatial visualization of complex cardiac anatomy and support real-time procedural guidance. Despite these advancements, standardized protocols, regulatory frameworks, and ethical safeguards remain necessary for widespread clinical adoption.

Efficient and accurate preoperative assessment of the right-sided heart structural complex (RSHSc) is crucial for planning transcatheter tricuspid valve replacement (TTVR). However, current manual methods remain time-consuming and inconsistent. To address this unmet clinical need, this study aimed to develop and validate TRI-PLAN, the first fully automated, deep learning (DL)-based framework for pre-TTVR assessment. A total of 140 preprocedural computed tomography angiography (CTA) scans (63,962 slices) from patients with severe tricuspid regurgitation (TR) at two high-volume cardiac centers in China were retrospectively included. The patients were divided into a training cohort (n = 100), an internal validation cohort (n = 20), and an external validation cohort (n = 20). TRI-PLAN was developed by a dual-stage right heart assessment network (DRA-Net) to segment the RSHSc and localize the tricuspid annulus (TA), followed by automated measurement of key anatomical parameters and right ventricular ejection fraction (RVEF). Performance was comprehensively evaluated in terms of accuracy, interobserver benchmark comparison, clinical usability, and workflow efficiency. TRI-PLAN achieved expert-level segmentation accuracy (volumetric Dice 0.952/0.955; surface Dice 0.934/0.940), precise localization (standard deviation 1.18/1.14 mm), excellent measurement agreement (ICC 0.984/0.979) and reliable RVEF evaluation (R = 0.97, bias<5 %) across internal and external cohorts. In addition, TRI-PLAN obtained a direct acceptance rate of 80 % and reduced total assessment time from 30 min manually to under 2 min (>95 % time saving). TRI-PLAN provides an accurate, efficient, and clinically applicable solution for pre-TTVR assessment, with strong potential to streamline TTVR planning and enhance procedural outcomes.

Dynamic Positron Emission Tomography (PET) scans offer rich spatiotemporal data for detecting malignancies, but their high-dimensionality and noise pose significant challenges. We introduce a novel framework, the Equivariant Spatiotemporal Transformer with MDL-Guided Feature Selection (EST-MDL), which integrates group-theoretic symmetries, Kolmogorov complexity, and Minimum Description Length (MDL) principles. By enforcing spatial and temporal symmetries (e.g., translations and rotations) and leveraging MDL for robust feature selection, our model achieves improved generalization and interpretability. Evaluated on three realworld PET datasets--LUNG-PET, BRAIN-PET, and BREAST-PET--our approach achieves AUCs of 0.94, 0.92, and 0.95, respectively, outperforming CNNs, Vision Transformers (ViTs), and Graph Neural Networks (GNNs) in AUC, sensitivity, specificity, and computational efficiency. This framework offers a robust, interpretable solution for malignancy detection in clinical settings.

BackgroundLarge Language Models (LLMs) represent an ever-emerging and rapidly evolving generative artificial intelligence (AI) modality with promising developments in the field of medical education. LLMs can provide automated feedback services to medical trainees (i.e. medical students, residents, fellows, etc.) and possibly serve a role in medical imaging education. AimThis systematic review aims to comprehensively explore the current applications and educational outcomes of LLMs in providing automated feedback on medical imaging reports. MethodsThis study employs a comprehensive systematic review strategy, involving an extensive search of the literature (Pubmed, Scopus, Embase, and Cochrane), data extraction, and synthesis of the data. ConclusionThis systematic review will highlight the best practices of LLM use in automated feedback of medical imaging reports and guide further development of these models.

Retinal detachment (RD) is a vision-threatening condition that requires timely intervention to preserve vision. Macular involvement -- whether the macula is still intact (macula-intact) or detached (macula-detached) -- is the key determinant of visual outcomes and treatment urgency. Point-of-care ultrasound (POCUS) offers a fast, non-invasive, cost-effective, and accessible imaging modality widely used in diverse clinical settings to detect RD. However, ultrasound image interpretation is limited by a lack of expertise among healthcare providers, especially in resource-limited settings. Deep learning offers the potential to automate ultrasound-based assessment of RD. However, there are no ML ultrasound algorithms currently available for clinical use to detect RD and no prior research has been done on assessing macular status using ultrasound in RD cases -- an essential distinction for surgical prioritization. Moreover, no public dataset currently supports macular-based RD classification using ultrasound video clips. We introduce Eye Retinal DEtachment ultraSound, ERDES, the first open-access dataset of ocular ultrasound clips labeled for (i) presence of retinal detachment and (ii) macula-intact versus macula-detached status. The dataset is intended to facilitate the development and evaluation of machine learning models for detecting retinal detachment. We also provide baseline benchmarks using multiple spatiotemporal convolutional neural network (CNN) architectures. All clips, labels, and training code are publicly available at https://osupcvlab.github.io/ERDES/.

Bone health is a critical determinant of spine surgery outcomes, yet many patients undergo procedures without adequate preoperative assessment due to limitations in current bone quality assessment methods. This study aimed to develop and validate an artificial intelligence-based algorithm that predicts Vertebral Bone Quality (VBQ) scores from routine MRI scans, enabling improved preoperative identification of patients at risk for poor surgical outcomes. This study utilized 257 lumbar spine T1-weighted MRI scans from the SPIDER challenge dataset. VBQ scores were calculated through a three-step process: selecting the mid-sagittal slice, measuring vertebral body signal intensity from L1-L4, and normalizing by cerebrospinal fluid signal intensity. A YOLOv8 model was developed to automate region of interest placement and VBQ score calculation. The system was validated against manual annotations from 47 lumbar spine surgery patients, with performance evaluated using precision, recall, mean average precision, intraclass correlation coefficient, Pearson correlation, RMSE, and mean error. The YOLOv8 model demonstrated high accuracy in vertebral body detection (precision: 0.9429, recall: 0.9076, [email protected]: 0.9403, mAP@[0.5:0.95]: 0.8288). Strong interrater reliability was observed with ICC values of 0.95 (human-human), 0.88 and 0.93 (human-AI). Pearson correlations for VBQ scores between human and AI measurements were 0.86 and 0.9, with RMSE values of 0.58 and 0.42 respectively. The AI-based algorithm accurately predicts VBQ scores from routine lumbar MRIs. This approach has potential to enhance early identification and intervention for patients with poor bone health, leading to improved surgical outcomes. Further external validation is recommended to ensure generalizability and clinical applicability.

BackgroundNailfold capillaroscopy enables visualisation of structural abnormalities in the microvasculature of patients with systemic sclerosis (SSc). The objective of this feasibility study was to determine whether multispectral imaging could provide functional assessment (differences in haemoglobin concentration or oxygenation) of capillaries to aid discrimination between healthy controls and patients with SSc. MSI of nailfold capillaries visualizes the smallest blood vessels and the impact of SSc on angiogenesis and their deformation, making it suitable for evaluating oxygenation-sensitive imaging techniques. Imaging of the nailfold capillaries offers tissue-specific oxygenation information, unlike pulse oximetry, which measures arterial blood oxygenation as a single-point measurement. MethodsThe CAPoxy study was a single-centre, cross-sectional, feasibility study of nailfold capillary multispectral imaging, comparing a cohort of patients with SSc to controls. A nine-band multispectral camera was used to image 22 individuals (10 patients with SSc and 12 controls). Linear mixed-effects models and summary statistics were used to compare the different regions of the nailfold (capillaries, surrounding edges, and outside area) between SSc and controls. A machine learning model was used to compare the two groups. ResultsPatients with SSc exhibited higher indicators of haemoglobin concentration in the capillary and adjacent regions compared to controls, which were significant in the regions surrounding the capillaries (p<0.001). There were also spectral differences between the SSc and controls groups that could indicate differences in oxygenation of the capillaries and surrounding tissue. Additionally, a machine learning model distinguished SSc patients from healthy controls with an accuracy of 84%, suggesting potential for multispectral imaging to classify SSc based on structural and functional microvascular changes. ConclusionsData indicates that multispectral imaging differentiates between patients with SSc from controls based on differences in vascular function. Further work to develop a targeted spectral camera would further improve the contrast between patients with SSc and controls, enabling better imaging. Key messagesMultispectral imaging holds promise for providing functional oxygenation measurement in nailfold capillaroscopy. Significant oxygenation differences between individuals with systemic sclerosis and healthy controls can be detected with multispectral imaging in the tissue surrounding capillaries.

Accurate detection of anatomical landmarks in brain Magnetic Resonance Imaging (MRI) scans is essential for reliable spatial normalization, image alignment, and quantitative neuroimaging analyses. In this study, we introduce BrainSignsNET, a deep learning framework designed for robust three-dimensional (3D) landmark detection. Our approach leverages a multi-task 3D convolutional neural network that integrates an attention decoder branch with a multi-class decoder branch to generate precise 3D heatmaps, from which landmark coordinates are extracted. The model was trained and internally validated on T1-weighted Magnetization-Prepared Rapid Gradient-Echo (MPRAGE) scans from the Alzheimers Disease Neuroimaging Initiative (ADNI), the Baltimore Longitudinal Study of Aging (BLSA), and the Biomarkers of Cognitive Decline in Adults at Risk for AD (BIOCARD) datasets and externally validated on a clinical dataset from the Johns Hopkins Hydrocephalus Clinic. The study encompassed 14,472 scans from 6,299 participants, representing a diverse demographic profile with a significant proportion of older adult participants, particularly those over 70 years of age. Extensive preprocessing and data augmentation strategies, including traditional MRI corrections and tailored 3D transformations, ensured data consistency and improved model generalizability. Performance metrics demonstrated that on internal validation BrainSignsNET achieved an overall mean Euclidean distance of 2.32 {+/-} 0.41 mm and 94.8% of landmarks localized within their anatomically defined 3D volumes in the external validation dataset. This improvement in accurate anatomical landmark detection on brain MRI scans should benefit many imaging tasks, including registration, alignment, and quantitative analyses.

This study employed machine learning models to quantitatively analyze liver fat content from MRI images for the evaluation of liver fibrosis and disease severity in patients with metabolic dysfunction-associated fatty liver disease (MAFLD). A total of 26 confirmed MAFLD cases, along with MRI image sequences obtained from public repositories, were included to perform a comprehensive assessment. Radiomics features-such as contrast, correlation, homogeneity, energy, and entropy-were extracted and used to construct a random forest classification model with optimized hyperparameters. The model achieved outstanding performance, with an accuracy of 96.8%, sensitivity of 95.7%, specificity of 97.8%, and an F1-score of 96.8%, demonstrating its strong capability in accurately evaluating the degree of liver fibrosis and overall disease severity in MAFLD patients. The integration of machine learning with MRI-based analysis offers a promising approach to enhancing clinical decision-making and guiding treatment strategies, underscoring the potential of advanced technologies to improve diagnostic precision and disease management in MAFLD.

Accurate localization of the epileptogenic zone (EZ) is essential for surgical success in temporal lobe epilepsy. While stereoelectroencephalography (SEEG) and structural magnetic resonance imaging (MRI) provide complementary insights, existing unimodal methods fail to fully capture epileptogenic brain activity, and multimodal fusion remains challenging due to data complexity and surgeon-dependent interpretations. To address these issues, we proposed a novel multimodal framework to improve EZ localization with SEEG-drived electrophysiology with structural connectivity in temporal lobe epilepsy. By retrospectively analyzing SEEG, post-implant Computed Tomography (CT) and MRI (T1 & Diffusion Tensor Imaging (DTI)) data from 15 patients, we reconstructed SEEG electrode positions and obtained the SEEG and structural connectivity fusion features. We then proposed a spatiotemporal co-attention deep neural network (ST-CANet) to identify the fusion features, categorizing electrodes into seizure onset zone (SOZ), propagation zone (PZ), and non-involved zone (NIZ). Anatomical EZ boundaries were delineated by fusing the electrode position and classification information on brain atlas. The proposed method was evaluated based on the identification and localization performance of three epilepsy-related zones. The experiment results demonstrate that our method achieves 98.08% average accuracy and outperforms other identification methods, and improves the localization with Dice similarity coefficients (DSC) of 95.65% (SOZ), 92.13% (PZ), and 99.61% (NIZ), aligning with clinically validated surgical resection areas. This multimodal fusion strategy based on electrophysiological and structural connectivity information promises to assist neurosurgeons in accurately localizing EZ and may find broader applications in preoperative planning for epilepsy surgeries.