To identify predictors of a true scaphoid fracture among patients with radial wrist pain following acute trauma, train 5 machine learning (ML) algorithms in predicting scaphoid fracture probability, and design a decision rule to initiate advanced imaging in high-risk patients. Two prospective cohorts including 422 patients with radial wrist pain following wrist trauma were combined. There were 117 scaphoid fractures (28%) confirmed on computed tomography, magnetic resonance imaging, or radiographs. Eighteen fractures (15%) were occult. Predictors of a scaphoid fracture were identified among demographics, mechanism of injury and examination maneuvers. Five ML-algorithms were trained in calculating scaphoid fracture probability. ML-algorithms were assessed on ability to discriminate between patients with and without a fracture (area under the receiver operating characteristic curve), agreement between observed and predicted probabilities (calibration), and overall performance (Brier score). The best performing ML-algorithm was incorporated into a probability calculator. A decision rule was proposed to initiate advanced imaging among patients with negative radiographs. Pain over the scaphoid on ulnar deviation, sex, age, and mechanism of injury were most strongly associated with a true scaphoid fracture. The best performing ML-algorithm yielded an area under the receiver operating characteristic curve, calibration slope, intercept, and Brier score of 0.77, 0.84, -0.01 and 0.159, respectively. The ML-derived decision rule proposes to initiate advanced imaging in patients with radial-sided wrist pain, negative radiographs, and a fracture probability of ≥10%. When applied to our cohort, this would yield 100% sensitivity, 38% specificity, and would have reduced the number of patients undergoing advanced imaging by 36% without missing a fracture. The ML-algorithm accurately calculated scaphoid fracture probability based on scaphoid pain on ulnar deviation, sex, age, and mechanism of injury. The ML-decision rule may reduce the number of patients undergoing advanced imaging by a third with a small risk of missing a fracture. External validation is required before implementation. Diagnostic II.

The skeletal muscles that athletes should train vary depending on their discipline and position. Therefore, individual skeletal muscle cross-sectional area assessment is important in the development of training strategies. To measure the cross-sectional area of skeletal muscle, manual segmentation of each muscle is performed using magnetic resonance (MR) imaging. This task is time-consuming and requires significant effort. Additionally, interobserver variability can sometimes be problematic. The purpose of this study was to develop an automated computerized method for semantic segmentation of individual thigh skeletal muscles from MR images of athletes. Our database consisted of 697 images from the thighs of 697 elite athletes. The images were randomly divided into a training dataset (70%), a validation dataset (10%), and a test dataset (20%). A label image was generated for each image by manually annotating 15 object classes: 12 different skeletal muscles, fat, bones, and vessels and nerves. Using the validation dataset, DeepLab v3+ was chosen from three different semantic segmentation models as a base model for segmenting individual thigh skeletal muscles. The feature extractor in DeepLab v3+ was also optimized to ResNet50. The mean Jaccard index and Dice index for the proposed method were 0.853 and 0.916, respectively, which were significantly higher than those from conventional DeepLab v3+ (Jaccard index: 0.810, p < .001; Dice index: 0.887, p < .001). The proposed method achieved a mean area error for 15 objective classes of 3.12%, useful in the assessment of skeletal muscle cross-sectional area from MR images.

Multimodal artificial intelligence (AI) has the potential to revolutionise healthcare by enabling the simultaneous processing and integration of various data types, including medical imaging, electronic health records, genomic information and real-time data. This review explores the current applications and future potential of multimodal AI across healthcare, with a particular focus on orthopaedic surgery. In presurgical planning, multimodal AI has demonstrated significant improvements in diagnostic accuracy and risk prediction, with studies reporting an Area under the receiving operator curve presenting good to excellent performance across various orthopaedic conditions. Intraoperative applications leverage advanced imaging and tracking technologies to enhance surgical precision, while postoperative care has been advanced through continuous patient monitoring and early detection of complications. Despite these advances, significant challenges remain in data integration, standardisation, and privacy protection. Technical solutions such as federated learning (allowing decentralisation of models) and edge computing (allowing data analysis to happen on site or closer to site instead of multipurpose datacenters) are being developed to address these concerns while maintaining compliance with regulatory frameworks. As this field continues to evolve, the integration of multimodal AI promises to advance personalised medicine, improve patient outcomes, and transform healthcare delivery through more comprehensive and nuanced analysis of patient data. Level of Evidence: Level V.

Comprehending the biomechanical characteristics of the human lumbar spine is crucial for managing and preventing spinal disorders. Precise material properties derived from patient-specific CT scans are essential for simulations to accurately mimic real-life scenarios, which is invaluable in creating effective surgical plans. The integration of Finite Element Analysis (FEA) with Physics-Informed Neural Networks (PINNs) offers significant clinical benefits by automating lumbar spine segmentation and meshing. We developed a FEA model of the lumbar spine incorporating detailed anatomical and material properties derived from high-quality CT and MRI scans. The model includes vertebrae and intervertebral discs, segmented and meshed using advanced imaging and computational techniques. PINNs were implemented to integrate physical laws directly into the neural network training process, ensuring that the predictions of material properties adhered to the governing equations of mechanics. The model achieved an accuracy of 94.30% in predicting material properties such as Young's modulus (14.88 GPa for cortical bone and 1.23 MPa for intervertebral discs), Poisson's ratio (0.25 and 0.47, respectively), bulk modulus (9.87 GPa and 6.56 MPa, respectively), and shear modulus (5.96 GPa and 0.42 MPa, respectively). We developed a lumbar spine FEA model using anatomical and material properties from CT and MRI scans. Vertebrae and discs were segmented and meshed with advanced imaging techniques, while PINNs ensured material predictions followed mechanical laws. The integration of FEA and PINNs allows for accurate, automated prediction of material properties and mechanical behaviors of the lumbar spine, significantly reducing manual input and enhancing reliability. This approach ensures dependable biomechanical simulations and supports the development of personalized treatment plans and surgical strategies, ultimately improving clinical outcomes for spinal disorders. This method improves surgical planning and outcomes, contributing to better patient care and recovery in spinal disorders.

Scoliosis, a 3-D spinal deformity, requires early detection and intervention. Ultrasound curve angle (UCA) measurement using ultrasound images has emerged as a promising diagnostic tool. However, calculating the UCA directly from ultrasound images remains challenging due to low contrast, high noise, and irregular target shapes. Accurate segmentation results are therefore crucial to enhance image clarity and precision prior to UCA calculation. We propose the SSAT-Swin model, a transformer-based multi-class segmentation framework designed for ultrasound image analysis in scoliosis diagnosis. The model integrates a boundary-enhancement module in the decoder and a channel attention module in the skip connections. Additionally, self-supervised proxy tasks are used during pre-training on 1,170 images, followed by fine-tuning on 109 image-label pairs. The SSAT-Swin achieved Dice scores of 85.6% and Jaccard scores of 74.5%, with a 92.8% scoliosis bone feature detection rate, outperforming state-of-the-art models. Self-supervised learning enhances the model's ability to capture global context information, making it well-suited for addressing the unique challenges of ultrasound images, ultimately advancing scoliosis assessment through more accurate segmentation.

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. 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. 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). 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.

To evaluate the usefulness of radiomics features extracted from ultrasonographic images in diagnosing and predicting the severity of knee osteoarthritis (OA). In this single-center, prospective, observational study, radiomics features were extracted from standing radiographs and ultrasonographic images of knees of patients aged 40-85 years with primary medial OA and without OA. Analysis was conducted using LIFEx software (version 7.2.n), ANOVA, and LASSO regression. The diagnostic accuracy of three different models, including a statistical model incorporating background factors and machine learning models, was evaluated. Among 491 limbs analyzed, 318 were OA and 173 were non-OA cases. The mean age was 72.7 (±8.7) and 62.6 (±11.3) years in the OA and non-OA groups, respectively. The OA group included 81 (25.5 %) men and 237 (74.5 %) women, whereas the non-OA group included 73 men (42.2 %) and 100 (57.8 %) women. A statistical model using the cutoff value of MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) achieved a specificity of 0.98 and sensitivity of 0.47. Machine learning diagnostic models (Model 2) demonstrated areas under the curve (AUCs) of 0.88 (discriminant analysis) and 0.87 (logistic regression), with sensitivities of 0.80 and 0.81 and specificities of 0.82 and 0.80, respectively. For severity prediction, the statistical model using MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) showed sensitivity and specificity values of 0.78 and 0.86, respectively, whereas machine learning models achieved an AUC of 0.92, sensitivity of 0.81, and specificity of 0.85 for severity prediction. The use of radiomics features in diagnosing knee OA shows potential as a supportive tool for enhancing clinicians' decision-making.

Artificial Intelligence (AI) has been shown to enhance fracture-detection-accuracy, but the most effective AI-implementation in clinical practice is less well understood. In the current study, four approaches to AI-implementation are evaluated for their impact on AI-effectiveness. Retrospective single-center study based on all consecutive, around-the-clock radiographic examinations for suspected fractures, and accompanying clinical-practice radiologist-diagnoses, between January and March 2023. These image-sets were independently analysed by a dedicated bone-fracture-detection-AI. Findings were combined with radiologist clinical-practice diagnoses to simulate the four AI-implementation methods deemed most relevant to clinical workflows: AI-standalone (radiologist-findings not consulted); AI-problem-solving (AI-findings consulted when radiologist in doubt); AI-triage (radiologist-findings consulted when AI in doubt); and AI-safety net (AI-findings consulted when radiologist diagnosis negative). Reference-standard diagnoses were established by two senior musculoskeletal-radiologists (by consensus in cases of disagreement). Radiologist- and radiologist + AI diagnoses were compared for false negatives (FN), false positives (FP) and their clinical consequences. Experience-level-subgroups radiologists-in-training-, non-musculoskeletal-radiologists, and dedicated musculoskeletal-radiologists were analysed separately. 1508 image-sets were included (1227 unique patients; 40 radiologist-readers). Radiologist results were: 2.7 % FN (40/1508), 28 with clinical consequences; 1.2 % FP (18/1508), 2 received full-fracture treatments (11.1 %). All AI-implementation methods changed overall FN and FP with statistical significance (p < 0.001): AI-standalone 1.5 % FN (23/1508; 11 consequences), 6.8 % FP (103/1508); AI-problem-solving 3.2 % FN (48/1508; 31 consequences), 0.6 % FP (9/1508); AI-triage 2.1 % FN (32/1508; 18 consequences), 1.7 % FP (26/1508); AI-safety net 0.07 % FN (1/1508; 1 consequence), 7.6 % FP (115/1508). Subgroups show similar trends, except AI-triage increased FN for all subgroups except radiologists-in-training. Implementation methods have a large impact on AI-effectiveness. These results suggest AI should not be considered for problem-solving or triage at this time; AI standalone performs better than either and may be a source of assistance where radiologists are unavailable. Best results were obtained implementing AI as safety net, which eliminates missed fractures with serious clinical consequences; even though false positives are increased, unnecessary treatments are limited.

Considering the radiation hazard of X-ray, safer, more convenient and cost-effective ultrasound methods are gradually becoming new diagnostic approaches for scoliosis. For ultrasound images of spine regions, it is challenging to accurately identify spine regions in images due to relatively small target areas and the presence of a lot of interfering information. Therefore, we developed a novel neural network that incorporates prior knowledge to precisely segment spine regions in ultrasound images. We constructed a dataset of ultrasound images of spine regions for semantic segmentation. The dataset contains 3136 images of 30 patients with scoliosis. And we propose a network model (ICPPNet), which fully utilizes inter-class positional prior knowledge by combining an inter-class positional probability heatmap, to achieve accurate segmentation of target areas. ICPPNet achieved an average Dice similarity coefficient of 70.83% and an average 95% Hausdorff distance of 11.28 mm on the dataset, demonstrating its excellent performance. The average error between the Cobb angle measured by our method and the Cobb angle measured by X-ray images is 1.41 degrees, and the coefficient of determination is 0.9879 with a strong correlation. ICPPNet provides a new solution for the medical image segmentation task with positional prior knowledge between target classes. And ICPPNet strongly supports the subsequent reconstruction of spine models using ultrasound images.

Magnetic resonance fingerprinting (MRF), as an emerging versatile and noninvasive imaging technique, provides simultaneous quantification of multiple quantitative MRI parameters, which have been used to detect changes in cartilage composition and structure in osteoarthritis. Deep learning (DL)-based methods for quantification mapping in MRF overcome the memory constraints and offer faster processing compared to the conventional dictionary matching (DM) method. However, limited attention has been given to the fine-tuning of neural networks (NNs) in DL and fair comparison with DM. In this study, we investigate the impact of training parameter choices on NN performance and compare the fine-tuned NN with DM for multiparametric mapping in MRF. Our approach includes optimizing NN hyperparameters, analyzing the singular value decomposition (SVD) components of MRF data, and optimization of the DM method. We conducted experiments on synthetic data, the NIST/ISMRM MRI system phantom with ground truth, and in vivo knee data from 14 healthy volunteers. The results demonstrate the critical importance of selecting appropriate training parameters, as these significantly affect NN performance. The findings also show that NNs improve the accuracy and robustness of T₁, T₂, and T_1ρ mappings compared to DM in synthetic datasets. For in vivo knee data, the NN achieved comparable results for T₁, with slightly lower T₂ and slightly higher T_1ρ measurements compared to DM. In conclusion, the fine-tuned NN can be used to increase accuracy and robustness for multiparametric quantitative mapping from MRF of the knee joint.