Solving computer vision problems through machine learning, one often encounters lack of sufficient training data. To mitigate this we propose the use of ensembles of weak learners based on spectral total-variation (STV) features (Gilboa 2014). The features are related to nonlinear eigenfunctions of the total-variation subgradient and can characterize well textures at various scales. It was shown (Burger et-al 2016) that, in the one-dimensional case, orthogonal features are generated, whereas in two-dimensions the features are empirically lowly correlated. Ensemble learning theory advocates the use of lowly correlated weak learners. We thus propose here to design ensembles using learners based on STV features. To show the effectiveness of this paradigm we examine a hard real-world medical imaging problem: the predictive value of computed tomography (CT) data for high uptake in positron emission tomography (PET) for patients suspected of skeletal metastases. The database consists of 457 scans with 1524 unique pairs of registered CT and PET slices. Our approach is compared to deep-learning methods and to Radiomics features, showing STV learners perform best (AUC=0.87), compared to neural nets (AUC=0.75) and Radiomics (AUC=0.79). We observe that fine STV scales in CT images are especially indicative for the presence of high uptake in PET.

Predicting distant metastases in soft tissue sarcomas (STS) is vital for guiding clinical decision-making. Recent advancements in radiomics and deep learning (DL) models have shown promise, but their diagnostic accuracy remains unclear. This meta-analysis aims to assess the performance of radiomics and DL-based models in predicting metastases in STS by analyzing pooled sensitivity and specificity. Following PRISMA guidelines, a thorough search was conducted in PubMed, Web of Science, and Embase. A random-effects model was used to estimate the pooled area under the curve (AUC), sensitivity, and specificity. Subgroup analyses were performed based on imaging modality (MRI, PET, PET/CT), feature extraction method (DL radiomics [DLR] vs. handcrafted radiomics [HCR]), incorporation of clinical features, and dataset used. Heterogeneity by I² statistic, leave-one-out sensitivity analyses, and publication bias by Egger's test assessed model robustness and potential biases. Ninetheen studies involving 1712 patients were included. The pooled AUC for predicting metastasis was 0.88 (95% CI: 0.80-0.92). The pooled AUC values were 88% (95% CI: 77-89%) for MRI-based models, 80% (95% CI: 76-92%) for PET-based models, and 91% (95% CI: 78-93%) for PET/CT-based models, with no significant differences (p = 0.75). DL-based models showed significantly higher sensitivity than HCR models (p < 0.01). Including clinical features did not significantly improve model performance (AUC: 0.90 vs. 0.88, p = 0.99). Significant heterogeneity was noted (I² > 25%), and Egger's test suggested potential publication bias (p < 0.001). Radiomics models showed promising potential for predicting metastases in STSs, with DL approaches outperforming traditional HCR. While integrating this approach into routine clinical practice is still evolving, it can aid physicians in identifying high-risk patients and implementing targeted monitoring strategies to reduce the risk of severe complications associated with metastasis. However, challenges such as heterogeneity, limited external validation, and potential publication bias persist. Future research should concentrate on standardizing imaging protocols and conducting multi-center validation studies to improve the clinical applicability of radiomics predictive models.

Magnetic resonance imaging (MRI) enables non-invasive, high-resolution analysis of muscle structures. However, automated segmentation remains limited by high computational costs, reliance on large training datasets, and reduced accuracy in segmenting smaller muscles. Convolutional neural network (CNN)-based methods, while powerful, often suffer from substantial computational overhead, limited generalizability, and poor interpretability across diverse populations. This study proposes a training-free segmentation approach based on keypoint tracking, which integrates keypoint selection with Lucas-Kanade optical flow. The proposed method achieves a mean Dice similarity coefficient (DSC) ranging from 0.6 to 0.7, depending on the keypoint selection strategy, performing comparably to state-of-the-art CNN-based models while substantially reducing computational demands and enhancing interpretability. This scalable framework presents a robust and explainable alternative for muscle segmentation in clinical and research applications.

To develop an artificial intelligence (AI)-driven model for automatic Lenke classification of adolescent idiopathic scoliosis (AIS) and assess its performance. This retrospective study utilized 860 spinal radiographs from 215 AIS patients with four views, including 161 training sets and 54 testing sets. Additionally, 1220 spinal radiographs from 610 patients with only anterior-posterior (AP) and lateral (LAT) views were collected for training. The model was designed to perform keypoint detection, pedicle segmentation, and AIS classification based on a custom classification strategy. Its performance was evaluated against the gold standard using metrics such as mean absolute difference (MAD), intraclass correlation coefficient (ICC), Bland-Altman plots, Cohen's Kappa, and the confusion matrix. In comparison to the gold standard, the MAD for all predicted angles was 2.29°, with an excellent ICC. Bland-Altman analysis revealed minimal differences between the methods. For Lenke classification, the model exhibited exceptional consistency in curve type, lumbar modifier, and thoracic sagittal profile, with average Kappa values of 0.866, 0.845, and 0.827, respectively, and corresponding accuracy rates of 87.07%, 92.59%, and 92.59%. Subgroup analysis further confirmed the model's high consistency, with Kappa values ranging from 0.635 to 0.930, 0.672 to 0.926, and 0.815 to 0.847, and accuracy rates between 90.7 and 98.1%, 92.6-98.3%, and 92.6-98.1%, respectively. This novel AI system facilitates the rapid and accurate automatic Lenke classification, offering potential assistance to spinal surgeons.

In pediatric orthodontics, accurate estimation of growth potential is essential for developing effective treatment strategies. Our research aims to predict this potential by identifying the growth peak and analyzing cervical vertebra morphology solely through lateral cephalometric radiographs. We accomplish this by comprehensively analyzing cervical vertebral maturation (CVM) features from these radiographs. This methodology provides clinicians with a reliable and efficient tool to determine the optimal timings for orthodontic interventions, ultimately enhancing patient outcomes. A crucial aspect of this approach is the meticulous annotation of keypoints on the cervical vertebrae, a task often challenged by its labor-intensive nature. To mitigate this, we introduce Attend-and-Refine Network (ARNet), a user-interactive, deep learning-based model designed to streamline the annotation process. ARNet features Interaction-guided recalibration network, which adaptively recalibrates image features in response to user feedback, coupled with a morphology-aware loss function that preserves the structural consistency of keypoints. This novel approach substantially reduces manual effort in keypoint identification, thereby enhancing the efficiency and accuracy of the process. Extensively validated across various datasets, ARNet demonstrates remarkable performance and exhibits wide-ranging applicability in medical imaging. In conclusion, our research offers an effective AI-assisted diagnostic tool for assessing growth potential in pediatric orthodontics, marking a significant advancement in the field.

To assess the value of a chest CT-based machine learning model in predicting osteoporotic vertebral fractures (OVFs) of the thoracolumbar vertebral bodies. We monitored 8910 patients aged ≥50 who underwent chest CT (2021-2024), identifying 54 incident OVFs cases. Using propensity score matching, 108 controls were selected. The 162 patients were randomly assigned to training (n=113) and testing (n=49) cohorts. Clinical models were developed through logistic regression. Radiomics features were extracted from the thoracolumbar vertebral bodies (T11-L2), with top 10 features selected via minimum-redundancy maximum-relevancy and the least absolute shrinkage and selection operator to construct a Radscore model. Nomogram model was established combining clinical and radiomics features, evaluated using receiver operating characteristic curves, decision curve analysis (DCA) and calibration plots. Volumetric bone mineral density (vBMD) (OR=0.95, 95%CI=0.93-0.97) and hemoglobin (HGB) (OR=0.96, 95%CI=0.94-0.98) were selected as independent risk factors for clinical model. From 2288 radiomics features, 10 were selected for Radscore calculation. The Nomogram model (Radscore + vBMD + HGB) achieved area under the curve (AUC) of 0.938/0.906 in training/testing cohorts, outperforming both Radscore (AUC=0.902/0.871) and clinical (AUC=0.802/0.820) models. DCA and calibration plots confirmed the Nomogram model's superior prediction capability. Nomogram model combined with radiomics and clinical features has high predictive performance, and its predictive results for thoracolumbar OVFs can provide reference for clinical decision making.

Brucella spondylitis (BS) and tuberculous spondylitis (TS) are prevalent spinal infections with distinct treatment protocols. Rapid and accurate differentiation between these two conditions is crucial for effective clinical management; however, current imaging and pathogen-based diagnostic methods fall short of fully meeting clinical requirements. This study explores the feasibility of employing deep learning (DL) models based on conventional magnetic resonance imaging (MRI) to differentiate BS and TS. A total of 310 subjects were enrolled in our hospital, comprising 209 with BS, 101 with TS. The participants were randomly divided into a training set (n = 217) and a test set (n = 93). And 74 with other hospital was external validation set. Integrating Convolutional Block Attention Module (CBAM) into the ResNeXt-50 architecture and training the model using sagittal T2-weighted images (T2WI). Classification performance was evaluated using the area under the receiver operating characteristic (AUC) curve, and diagnostic accuracy was compared against general models such as ResNet50, GoogleNet, EfficientNetV2, and VGG16. The CBAM-ResNeXt model revealed superior performance, with accuracy, precision, recall, F1-score, and AUC from 0.942, 0.940, 0.928, 0.934, 0.953, respectively. These metrics outperformed those of the general models. The proposed model offers promising potential for the diagnosis of BS and TS using conventional MRI. It could serve as an invaluable tool in clinical practice, providing a reliable reference for distinguishing between these two diseases.

The early detection and treatment of osteoporosis and prevention of fragility fractures are urgent societal issues. We developed an artificial intelligence-assisted diagnostic system that estimated not only lumbar bone mineral density but also femoral bone mineral density from anteroposterior lumbar X-ray images. We evaluated the performance of lumbar and femoral bone mineral density estimations and the osteoporosis classification accuracy of an artificial intelligence-assisted diagnostic system using lumbar X-ray images from a population-based cohort. The artificial neural network consisted of a deep neural network for estimating lumbar and femoral bone mineral density values and classifying lumbar X-ray images into osteoporosis categories. The deep neural network was built by training dual-energy X-ray absorptiometry-derived lumbar and femoral bone mineral density values as the ground truth of the training data and preprocessed X-ray images. Five-fold cross-validation was performed to evaluate the accuracy of the estimated BMD. A total of 1454 X-ray images from 1454 participants were analyzed using the artificial neural network. For the bone mineral density estimation performance, the mean absolute errors were 0.076 g/cm² for the lumbar and 0.071 g/cm² for the femur between dual-energy X-ray absorptiometry-derived and artificial intelligence-estimated bone mineral density values. The classification performances for the lumbar and femur of patients with osteopenia, in terms of sensitivity, were 86.4% and 80.4%, respectively, and the respective specificities were 84.1% and 76.3%. CLINICAL SIGNIFICANCE: The system was able to estimate the bone mineral density and classify the osteoporosis category of not only patients in clinics or hospitals but also of general inhabitants.

To train and test an AI-based algorithm for automated detection of focal bone marrow lesions (FL) from MRI. This retrospective feasibility study included 444 patients with monoclonal plasma cell disorders. For this feasibility study, only FLs in the left pelvis were included. Using the nnDetection framework, the algorithm was trained based on 334 patients with 494 FLs from center 1, and was tested on an internal test set (36 patients, 89 FLs, center 1) and a multicentric external test set (74 patients, 262 FLs, centers 2-11). Mean average precision (mAP), F1-score, sensitivity, positive predictive value (PPV), and Spearman correlation coefficient between automatically determined and actual number of FLs were calculated. On the internal/external test set, the algorithm achieved a mAP of 0.44/0.34, F1-Score of 0.54/0.44, sensitivity of 0.49/0.34, and a PPV of 0.61/0.61, respectively. In two subsets of the external multicentric test set with high imaging quality, the performance nearly matched that of the internal test set, with mAP of 0.45/0.41, F1-Score of 0.50/0.53, sensitivity of 0.44/0.43, and a PPV of 0.60/0.71, respectively. There was a significant correlation between the automatically determined and actual number of FLs on both the internal (r=0.51, p=0.001) and external multicentric test set (r=0.59, p<0.001). This study demonstrates that the automated detection of FLs from MRI, and thereby the automated assessment of the number of FLs, is feasible.

Magnetic resonance imaging of the lumbar spine is a key technique for clarifying the cause of disease. The greatest challenges today are the repetitive and time-consuming process of interpreting these complex MR images and the problem of unequal diagnostic results from physicians with different levels of experience. To address these issues, in this study, an improved YOLOv8 model (GE-YOLOv8) that combines a gradient search module and efficient channel attention was developed. To address the difficulty of intervertebral disc feature extraction, the GS module was introduced into the backbone network, which enhances the feature learning ability for the key structures through the gradient splitting strategy, and the number of parameters was reduced by 2.1%. The ECA module optimizes the weights of the feature channels and enhances the sensitivity of detection for small-target lesions, and the mAP50 was improved by 4.4% compared with that of YOLOv8. GE-YOLOv8 demonstrated the significance of this innovation on the basis of a P value <.001, with YOLOv8 as the baseline. The experimental results on a dataset from the Pingtan Branch of Union Hospital of Fujian Medical University and an external test dataset show that the model has excellent accuracy.