State-of-the-art computer- and robot-assisted surgery systems rely on intraoperative imaging technologies such as computed tomography and fluoroscopy to provide detailed 3D visualizations of patient anatomy. However, these methods expose both patients and clinicians to ionizing radiation. This study introduces a radiation-free approach for 3D spine reconstruction using RGB-D data. Inspired by the "mental map" surgeons form during procedures, we present SurgPointTransformer, a shape completion method that reconstructs unexposed spinal regions from sparse surface observations. The method begins with a vertebra segmentation step that extracts vertebra-level point clouds for subsequent shape completion. SurgPointTransformer then uses an attention mechanism to learn the relationship between visible surface features and the complete spine structure. The approach is evaluated on an <i>ex vivo</i> dataset comprising nine samples, with CT-derived data used as ground truth. SurgPointTransformer significantly outperforms state-of-the-art baselines, achieving a Chamfer distance of 5.39 mm, an F-score of 0.85, an Earth mover's distance of 11.00 and a signal-to-noise ratio of 22.90 dB. These results demonstrate the potential of our method to reconstruct 3D vertebral shapes without exposing patients to ionizing radiation. This work contributes to the advancement of computer-aided and robot-assisted surgery by enhancing system perception and intelligence.

Ultrasound imaging is critical for clinical diagnostics, providing insights into various diseases and organs. However, artificial intelligence (AI) in this field faces challenges, such as the need for large labeled datasets and limited task-specific model applicability, particularly due to ultrasound's low signal-to-noise ratio (SNR). To overcome these, we introduce the Ultrasound Representation Foundation Model (URFM), designed to learn robust, generalizable representations from unlabeled ultrasound images, enabling label-efficient adaptation to diverse diagnostic tasks. URFM is pre-trained on over 1M images from 15 major anatomical organs using representation-based masked image modeling (MIM), an advanced self-supervised learning. Unlike traditional pixel-based MIM, URFM integrates high-level representations from BiomedCLIP, a specialized medical vision-language model, to address the low SNR issue. Extensive evaluation shows that URFM outperforms state-of-the-art methods, offering enhanced generalization, label efficiency, and training-time efficiency. URFM's scalability and flexibility signal a significant advancement in diagnostic accuracy and clinical workflow optimization in ultrasound imaging.

Passive acoustic mapping (PAM) is a promising tool for monitoring acoustic cavitation activities in the applications of ultrasound therapy. Data-adaptive beamformers for PAM have better image quality compared with time exposure acoustics (TEA) algorithms. However, the computational cost of data-adaptive beamformers is considerably expensive. In this work, we develop a deep beamformer based on a generative adversarial network that can switch between different transducer arrays and reconstruct high-quality PAM images directly from radiofrequency ultrasound signals with low computational cost. The deep beamformer was trained on a dataset consisting of simulated and experimental cavitation signals of single and multiple microbubble clouds measured by different (linear and phased) arrays covering 1-15 MHz. We compared the performance of the deep beamformer to TEA and three different data-adaptive beamformers using simulated and experimental test dataset. Compared with TEA, the deep beamformer reduced the energy spread area by 27.3%-77.8% and improved the image signal-to-noise ratio by 13.9-25.1 dB on average for the different arrays in our data. Compared with the data-adaptive beamformers, the deep beamformer reduced the computational cost by three orders of magnitude achieving 10.5 ms image reconstruction speed in our data, while the image quality was as good as that of the data-adaptive beamformers. These results demonstrate the potential of the deep beamformer for high-resolution monitoring of microbubble cavitation activities for ultrasound therapy.

Retrospective cross-sectional study. To develop a multi-view fusion framework that effectively identifies suspect keratoconus cases and facilitates the possibility of early clinical intervention. A total of 573 corneal topography maps representing eyes classified as normal, suspect, or keratoconus. We designed the Corneal Multi-View Fusion Transformer (CMVFT), which integrates features from seven standard corneal topography maps. A pretrained ResNet-50 extracts single-view representations that are further refined by a custom-designed Multi-Scale Attention Module (MSAM). This integrated design specifically compensates for the representation gap commonly encountered when applying Transformers to small-sample corneal topography datasets by dynamically bridging local convolution-based feature extraction with global self-attention mechanisms. A subsequent fusion Transformer then models long-range dependencies across views for comprehensive multi-view feature integration. The primary measure was the framework's ability to differentiate suspect cases from normal and keratoconus cases, thereby creating a pathway for early clinical intervention. Experimental evaluation demonstrated that CMVFT effectively distinguishes suspect cases within a feature space characterized by overlapping attributes. Ablation studies confirmed that both the MSAM and the fusion Transformer are essential for robust multi-view feature integration, successfully compensating for potential representation shortcomings in small datasets. This study is the first to apply a Transformer-driven multi-view fusion approach in corneal topography analysis. By compensating for the representation gap inherent in small-sample settings, CMVFT shows promise in enabling the identification of suspect keratoconus cases and supporting early intervention strategies, with prospective implications for early clinical intervention.

We investigate the use of quantum computing algorithms on real quantum hardware to tackle the computationally intensive task of feature selection for light-weight medical image datasets. Feature selection is often formulated as a k of n selection problem, where the complexity grows binomially with increasing k and n. Quantum computers, particularly quantum annealers, are well-suited for such problems, which may offer advantages under certain problem formulations. We present a method to solve larger feature selection instances than previously demonstrated on commercial quantum annealers. Our approach combines a linear Ising penalty mechanism with subsampling and thresholding techniques to enhance scalability. The method is tested in a toy problem where feature selection identifies pixel masks used to reconstruct small-scale medical images. We compare our approach against a range of feature selection strategies, including randomized baselines, classical supervised and unsupervised methods, combinatorial optimization via classical and quantum solvers, and learning-based feature representations. The results indicate that quantum annealing-based feature selection is effective for this simplified use case, demonstrating its potential in high-dimensional optimization tasks. However, its applicability to broader, real-world problems remains uncertain, given the current limitations of quantum computing hardware. While learned feature representations such as autoencoders achieve superior reconstruction performance, they do not offer the same level of interpretability or direct control over input feature selection as our approach.

The circulation of cerebrospinal and interstitial fluid plays a vital role in clearing metabolic waste from the brain, and its disruption has been linked to neurological disorders. However, directly measuring brain-wide fluid transport-especially in the deep brain-has remained elusive. Here, we introduce magnetic resonance artificial intelligence velocimetry (MR-AIV), a framework featuring a specialized physics-informed architecture and optimization method that reconstructs three-dimensional fluid velocity fields from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MR-AIV unveils brain-wide velocity maps while providing estimates of tissue permeability and pressure fields-quantities inaccessible to other methods. Applied to the brain, MR-AIV reveals a functional landscape of interstitial and perivascular flow, quantitatively distinguishing slow diffusion-driven transport (∼ 0.1 µm/s) from rapid advective flow (∼ 3 µm/s). This approach enables new investigations into brain clearance mechanisms and fluid dynamics in health and disease, with broad potential applications to other porous media systems, from geophysics to tissue mechanics.

Deep learning for body composition analysis (BCA) is gaining traction in clinical research, offering rapid and automated ways to measure body features like muscle or fat volume. However, most current methods prioritize computed tomography (CT) over magnetic resonance imaging (MRI). This study presents a deep learning approach for automatic BCA using MR T2-weighted sequences. Initial BCA segmentations (10 body regions and 4 body parts) were generated by mapping CT segmentations from body and organ analysis (BOA) model to synthetic MR images created using an in-house trained CycleGAN. In total, 30 synthetic data pairs were used to train an initial nnU-Net V2 in 3D, and this preliminary model was then applied to segment 120 real T2-weighted MRI sequences from 120 patients (46% female) with a median age of 56 (interquartile range, 17.75), generating early segmentation proposals. These proposals were refined by human annotators, and nnU-Net V2 2D and 3D models were trained using 5-fold cross-validation on this optimized dataset of real MR images. Performance was evaluated using Sørensen-Dice, Surface Dice, and Hausdorff Distance metrics including 95% confidence intervals for cross-validation and ensemble models. The 3D ensemble segmentation model achieved the highest Dice scores for the body region classes: bone 0.926 (95% confidence interval [CI], 0.914-0.937), muscle 0.968 (95% CI, 0.961-0.975), subcutaneous fat 0.98 (95% CI, 0.971-0.986), nervous system 0.973 (95% CI, 0.965-0.98), thoracic cavity 0.978 (95% CI, 0.969-0.984), abdominal cavity 0.989 (95% CI, 0.986-0.991), mediastinum 0.92 (95% CI, 0.901-0.936), pericardium 0.945 (95% CI, 0.924-0.96), brain 0.966 (95% CI, 0.927-0.989), and glands 0.905 (95% CI, 0.886-0.921). Furthermore, body part 2D ensemble model reached the highest Dice scores for all labels: arms 0.952 (95% CI, 0.937-0.965), head + neck 0.965 (95% CI, 0.953-0.976), legs 0.978 (95% CI, 0.968-0.988), and torso 0.99 (95% CI, 0.988-0.991). The overall average Dice across body parts (2D = 0.971, 3D = 0.969, P = ns) and body regions (2D = 0.935, 3D = 0.955, P < 0.001) ensemble models indicates stable performance across all classes. The presented approach facilitates efficient and automated extraction of BCA parameters from T2-weighted MRI sequences, providing precise and detailed body composition information across various regions and body parts.

Stroke is one of the leading causes of death and disability worldwide, with a significantly elevated incidence among individuals with hypertension. Conventional risk assessment methods primarily rely on a limited set of clinical parameters and often exclude imaging-derived structural features, resulting in suboptimal predictive accuracy. This study aimed to develop a deep learning-based multimodal stroke risk prediction model by integrating carotid ultrasound imaging with multidimensional clinical data to enable precise identification of high-risk individuals among hypertensive patients. A total of 2,176 carotid artery ultrasound images from 1,088 hypertensive patients were collected. ResNet50 was employed to automatically segment the carotid intima-media and extract key structural features. These imaging features, along with clinical variables such as age, blood pressure, and smoking history, were fused using a Vision Transformer (ViT) and fed into a Radial Basis Probabilistic Neural Network (RBPNN) for risk stratification. The model's performance was systematically evaluated using metrics including AUC, Dice coefficient, IoU, and Precision-Recall curves. The proposed multimodal fusion model achieved outstanding performance on the test set, with an AUC of 0.97, a Dice coefficient of 0.90, and an IoU of 0.80. Ablation studies demonstrated that the inclusion of ViT and RBPNN modules significantly enhanced predictive accuracy. Subgroup analysis further confirmed the model's robust performance in high-risk populations, such as those with diabetes or smoking history. The deep learning-based multimodal fusion model effectively integrates carotid ultrasound imaging and clinical features, significantly improving the accuracy of stroke risk prediction in hypertensive patients. The model demonstrates strong generalizability and clinical application potential, offering a valuable tool for early screening and personalized intervention planning for stroke prevention. Not applicable.

Deep learning-based medical image segmentation techniques have shown promising results when evaluated based on conventional metrics such as the Dice score or Intersection-over-Union. However, these fully automatic methods often fail to meet clinically acceptable accuracy, especially when topological constraints should be observed, e.g., continuous boundaries or closed surfaces. In medical image segmentation, the correctness of a segmentation in terms of the required topological genus sometimes is even more important than the pixel-wise accuracy. Existing topology-aware approaches commonly estimate and constrain the topological structure via the concept of persistent homology (PH). However, these methods are difficult to implement for high dimensional data due to their polynomial computational complexity. To overcome this problem, we propose a novel and fast approach for topology-aware segmentation based on the Euler Characteristic (χ). First, we propose a fast formulation for χ computation in both 2D and 3D. The scalar χ error between the prediction and ground-truth serves as the topological evaluation metric. Then we estimate the spatial topology correctness of any segmentation network via a so-called topological violation map, i.e., a detailed map that highlights regions with χ errors. Finally, the segmentation results from the arbitrary network are refined based on the topological violation maps by a topology-aware correction network. Our experiments are conducted on both 2D and 3D datasets and show that our method can significantly improve topological correctness while preserving pixel-wise segmentation accuracy.

This study presents a fully automated digital workflow using artificial intelligence (AI) to create patient-specific cutting guides for mandible-angle osteotomies in facial feminization surgery (FFS). The goal is to achieve predictable, accurate, and safe results with minimal user input, addressing the time and effort required for conventional guide creation. Three-dimensional CT images of 30 male patients were used to develop and validate a workflow that automates two key processes: (1) segmentation of the mandible using a convolutional neural network (3D U-Net architecture) and (2) virtual design of osteotomy-specific cutting guides. Segmentation accuracy was assessed through comparison with expert manual segmentations using the dice similarity coefficient (DSC) and mean surface distance (MSD). The precision of the cutting guides was evaluated based on osteotomy line accuracy and fit. Workflow efficiency was measured by comparing the time required for automated versus manual planning by expert and novice users. The AI-based workflow achieved a median DSC of 0.966 and a median MSD of 0.212 mm, demonstrating high accuracy. The median planning time was reduced to 1 min and 38 s with the automated system, compared to 19 min and 37 s for an expert and 26 min and 39 s for a novice, representing 10- and 16-fold time reductions, respectively. The AI-based workflow is accurate, efficient, and cost-effective, significantly reducing planning time while maintaining clinical precision. This workflow improves surgical outcomes with precise and reliable cutting guides, enhancing efficiency and accessibility for clinicians, including those with limited experience in designing cutting guides.