Computed Tomography (CT)has gained recognition as the leading imaging method, extensively used in the diagnosis of spinal cord injuries. The reliance on CT imaging for acute care in patients with Spinal Cord Injury (SCI) has expanded rapidly. However, the diagnosis of initial clinical injury is crucial to accurately predict functional prediction, which is a difficult task for both clinicians and radiologists. To conquer this issue, an efficient model based on SCI detection is proposed, named as Shepard Parallel Convolutional Forward Harmonic Net (ShPCFHNet). The first step involves improving the CT image by applying logarithmic transformations in the enhancement phase. Spinal cord segmentation is then performed with the aid of the proposed Dual-branch UNet, whose loss function is adapted using Sensitivity-Specificity Loss (SSL). Following this, disc localization is carried out using an active contour model, and feature extraction is subsequently performed. The final step involves detecting SCI using ShPCFHNet, which combines the Shepard Convolutional Neural Network (ShCNN) and Parallel Convolutional Neural Network (PCNN) with Harmonic analysis. The proposed model achieved performance metrics of 91.397% accuracy, 92.684% True Positive Rate (TPR), and 90.366% True Negative Rate (TNR).

Cervical spine fractures present considerable challenges in both diagnosis and treatment. With the increasing incidence of such injuries and the limitations of conventional diagnostic tools, there is a pressing demand for more precise and effective detection methods. This study proposes a robust Multi-class Classification model for Cervical Spine Fractures (MC-CSF) using Computed Tomography (CT) images to enable the precise identification of fracture types. The process of MC-CSF starts with preprocessing input images using an Enhanced Wiener Filtering (EWF) technique to minimize noise while retaining critical structural features. Following this, a Modified Residual Block-assisted ResUNet (MRB-RUNet) model is utilized for segmentation to precisely isolate the cervical spine area. Once segmented, feature extraction combines both deep learning approaches and texture-based analysis, in which deep features are extracted from established models like VGG16 and Residual Network (ResNet), while Local Gabor Transitional Pattern (LGTrP) captures subtle local texture variations. These features are then processed by an ensemble of sophisticated classifiers, including Enhanced LeNet (E-LNet), ShuffleNet, and a deep convolutional neural network (DCNN), each tasked with distinguishing between different fracture types. To enhance overall classification accuracy, a soft voting approach is applied, where the probabilistic outputs of multiple classifiers are aggregated. This strategy leverages the complementary strengths of individual models, resulting in a more robust and reliable prediction of cervical spine fracture categories. The Ensemble model consistently outperforms the traditional approaches with peak accuracy of 0.954, precision of 0.813 and NPV of 0.974, respectively.

Deep learning models which perform well on images from their training distribution can degrade substantially when applied to new distributions. If a CT scanner introduces a new artifact not present in the training labels, the model may misclassify the images. Although modern CT scanners include design features which mitigate these artifacts, unanticipated or difficult-to-mitigate artifacts can still appear in practice. The direct solution of labeling images from this new distribution can be costly. As a more accessible alternative, this study evaluates domain adaptation as an approach for training models that maintain classification performance despite new artifacts, even without corresponding labels. We simulate ring artifacts from detector gain error in sinogram space and evaluate domain adversarial neural networks (DANN) against baseline and augmentation-based approaches on the OrganAMNIST abdominal CT dataset. Our results demonstrate that baseline models trained only on clean images fail to generalize to images with ring artifacts, and traditional augmentation with other distortion types provides no improvement on unseen artifact domains. In contrast, the DANN approach successfully maintains high classification accuracy on ring artifact images using only unlabeled artifact data during training, demonstrating the viability of domain adaptation for artifact robustness. The domain-adapted model achieved classification performance on ring artifact test data comparable to models explicitly trained with labeled artifact images, while also showing unexpected generalization to uniform noise. These findings provide empirical evidence that domain adaptation can effectively address distribution shift in medical imaging without requiring expensive expert labeling of new artifact distributions, suggesting promise for deployment in clinical settings where novel artifacts may emerge.

This study aimed to evaluate the diagnostic performance of machine learning (ML) algorithms based on radiomic features extracted from cone-beam computed tomography (CBCT) images in differentiating the nasopalatine duct (NPD) from the nasopalatine duct cyst (NPDC), and to compare their performance with that of a dentomaxillofacial radiologist. CBCT scans from 101 histopathologically confirmed NPDC cases and 101 age- and sex-matched controls with normal NPD were retrospectively analyzed. Manual segmentation was performed to extract 1037 radiomic features (original, Laplacian of Gaussian, and wavelet-transformed). After dimensionality reduction, five ML models (support vector machine (SVM), random forest (RF), decision tree (DT), k-nearest neighbors (KNN), and logistic regression (LR)) were trained using 5-fold cross-validation. Performance was evaluated using the area under the ROC curve (AUC), sensitivity, specificity, precision, recall, and F1-score. Among the 11 optimal features identified through feature selection, large area high gray level emphasis and zone variance from the gray level size zone matrix (GLSZM) class were the most prominent. SVM achieved the highest performance in the test set (AUC and all other metrics = 1.00). The radiologist showed comparable but slightly lower overall performance than SVM (AUC = 0.94, with other metrics between 0.93 and 0.95). Machine learning algorithms based on radiomic features extracted from CBCT images can effectively differentiate NPD from NPDC. Unlike standard visual interpretation, this approach analyzes quantitative image features via mathematical models, yielding objective and reproducible results. It may serve as a non-invasive, complementary decision-support tool, particularly in diagnostically challenging cases.

Aortic aneurysm disease ranks consistently in the top 20 causes of death in the U.S. population. Thoracic aortic aneurysm is manifested as an abnormal bulging of thoracic aortic wall and it is a leading cause of death in adults. From the perspective of biomechanics, rupture occurs when the stress acting on the aortic wall exceeds the wall strength. Wall stress distribution can be obtained by computational biomechanical analyses, especially structural Finite Element Analysis. For risk assessment, probabilistic rupture risk of TAA can be calculated by comparing stress with material strength using a material failure model. Although these engineering tools are currently available for TAA rupture risk assessment on patient specific level, clinical adoption has been limited due to two major barriers: labor intensive 3D reconstruction current patient specific anatomical modeling still relies on manual segmentation, making it time consuming and difficult to scale to a large patient population, and computational burden traditional FEA simulations are resource intensive and incompatible with time sensitive clinical workflows. The second barrier was successfully overcome by our team through the development of the PyTorch FEA library and the FEA DNN integration framework. By incorporating the FEA functionalities within PyTorch FEA and applying the principle of static determinacy, we reduced the FEA based stress computation time to approximately three minutes per case. Moreover, by integrating DNN and FEA through the PyTorch FEA library, our approach further decreases the computation time to only a few seconds per case. This work focuses on overcoming the first barrier through the development of an end to end deep neural network capable of generating patient specific finite element meshes of the aorta directly from 3D CT images.

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.

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.

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.

To evaluate the role of chest CT radiomics in classifying mediastinal lymphadenopathy caused by hematologic malignancies and abdominopelvic solid cancers. A total of 231 patients with mediastinal lymphadenopathy were selected from the Mediastinal-Lymph-Node-SEG collection in The Cancer Imaging Archive, including 145 patients with hematologic malignancies (74 with chronic lymphocytic leukemia and 71 with lymphoma) and 86 with abdominopelvic solid cancers. Patients were randomly stratified into train and test sets in a 7:3 ratio. Radiomics features were extracted from enhanced CT images of mediastinal lymph nodes, followed by feature selection using univariate analysis and least absolute shrinkage and selection operator regression. A support vector machine algorithm was used to develop classification models, with performance evaluated using the area under the receiver operating characteristic curve (AUC-ROC), accuracy, and 95% CI. For differentiating mediastinal lymphadenopathy between hematologic malignancies and abdominopelvic solid cancers, the model incorporated 23 features and achieved an AUC-ROC of 0.931 (95% CI: 0.891-0.971) and an accuracy of 0.866 in the train set, and an AUC-ROC of 0.830 (95% CI: 0.730-0.929) and an accuracy of 0.759 in the test set. For distinguishing chronic lymphocytic leukemia from lymphoma, the model utilized 4 features, achieving an AUC-ROC of 0.880 (95% CI: 0.813-0.947) and an accuracy of 0.752 in the train set, and an AUC-ROC of 0.872 (95% CI: 0.763-0.982) and an accuracy of 0.836 in the test set. Chest CT radiomics shows promise for classifying mediastinal lymphadenopathy in patients with hematologic malignancies and abdominopelvic solid cancers.

Gout is the world's foremost chronic inflammatory arthritis. Dual-energy computed tomography (DECT) images tophi-monosodium urate (MSU) crystal deposits that indicate gout-as an easily recognizable green color, facilitating high sensitivity. However, tophi-like regions ("artifacts") may be found in healthy controls, degrading specificity. To mitigate false positives, we propose the first automated system to localize MSU-presenting crystal deposits from DECT and classify them as gouty tophi or artifacts. Our solution, developed using 47 gout and 27 control patient scans, is three-stage. First, a computer vision algorithm crops green regions of interest (RoIs) from a patient's DECT scan frames and filters obvious false positives. Next, extracted RoIs are classified as tophi or artifact via one of three fine-tuned deep learning models; one model is trained to predict "small" RoIs, another "medium," and the third predicts "large" RoIs. Size thresholds are based on pixel area quartile statistics. Patient-level gout versus control classification is made via a machine learning system trained using a suite of features calculated from the outcomes of the RoI classifiers. Using 6-fold cross-validation, the proposed pipeline achieved a patient-level diagnostic accuracy, sensitivity, and specificity of 91.89%, 87.23%, and 100.00%. Using confidence values derived from the majority vote of RoI predictions, the best area under the receiver operator characteristics curve (ROC AUC) is 97.16%. The best RoI-level classifiers achieved mean tophus versus artifact accuracy, sensitivity, specificity, and ROC AUC of 89.61%, 85.42%, 93.70%, and 92.72%. Results demonstrate that machine/deep learning facilitates high-specificity gout diagnoses while maintaining respectable sensitivity.