The inherent spectral properties of photon-counting computed tomography (PCCT) allow detailed material identification through decomposition techniques, but these methods often amplify image noise and artifacts. Current denoising approaches mainly focus on improving already degraded images, ignoring the fundamental noise caused by random variations in photon detection. To tackle these issues, we combine a physics-based noise analysis with deep learning to control noise during the material decomposition process. Our work has three key parts: (1) A noise analysis model that explains how random photon-count variations in the detector affect the noise levels in different materials after decomposition. This model connects the Poisson-distributed detector noise to material-specific noise patterns. (2) A self-supervised training method that combines the noise model with neural networks using probability-based optimization, allowing the system to learn from limited training data without needing high-quality data. (3) A flexible image improvement system that adapts to different body structures and noise conditions, ensuring reliable results across various scanning scenarios. Tests using real patient scan data show our method better preserves material accuracy and produces cleaner virtual monochromatic images compared to traditional approaches. Importantly, our solution works effectively with small training datasets and can be practically used in hospital settings without slowing down workflows. This research bridges the gap between theoretical noise analysis and clinical medical imaging needs, offering a balanced approach to improving PCCT technology.

Abdominal aortic calcification (AAC), a marker of subclinical cardiovascular disease, has previously shown to be associated with low bone mineral density (BMD) and fracture. However, it remains unclear whether AAC is associated with trabecular bone score (TBS), a gray-level textural measure, or whether it predicts fracture risk independent of this measure. Here, we examined the cross-sectional association of AAC scored using a validated machine learning algorithm (ML-AAC24) with TBS, and their simultaneous associations with incident fractures in 7,691 individuals (93.4% women) through the Manitoba BMD Registry (mean age 75.3 years). The association between ML-AAC24 and TBS was tested using generalised linear regression. Cox proportional hazards models tested the simultaneous relationships of ML-AAC24 and TBS with incident fractures. At baseline, 41.3% of the study cohort had low (<2), 32.4% had moderate (2 to <6) and 26.3% had high (≥6) ML-AAC24. Compared to low ML-AAC24, high ML-AAC24 was associated with a 0.81% lower TBS in the multivariable-adjusted model. Independent of each other and multiple established fracture risk factors, ML-AAC24 and TBS were each associated with an increased risk of incident fractures. Specifically, high ML-AAC24 (HR 1.41 95%CI 1.15-1.73, compared to low ML-AAC24) and lower TBS (HR 1.13 95%CI 1.05-1.22, per SD decrease) were associated with increased relative hazards for any incident fracture. High ML-AAC24 and lower TBS were also associated with incident major osteoporotic fracture (HR 1.48 95%CI 1.18-1.87 and HR 1.15 95%CI 1.06-1.25, respectively) and hip fracture (HR 1.56 95%CI 1.05-2.31 and HR 1.25 95%CI 1.08-1.44, respectively). In conclusion, high ML-AAC24 is associated with lower TBS in older adults attending routine osteoporosis screening. Both measures were associated with incident fractures. The findings of this study highlight high ML-AAC24, seen in more than 1 in 4 of the study cohort, and lower TBS provide complementary prognostic information for fracture risk.

The aim of this retrospective study was the evaluation of the patient-reported and radiological outcome of intravenous Iloprost therapy in the treatment of spontaneous osteonecrosis of the knee (SONK). 36 patients (age 57.3 ± 8.7 years, 38.9% women, 61.1% men) who received Iloprost between 2018 and 2021 due to SONK (ARCO I and II) were included in this retrospective cohort study. Outcome was evaluated by pre- and postinterventional pain (Numeric Rating Scale - NRS), patient reported outcome (subjective knee value (SKV), Oxford Knee Score (OKS)) at latest follow-up (2.9 months ± 1) as well as quantitative artificial intelligence assisted analysis of bone marrow edema (BME) in Magnetic Resonance Imaging (MRI) before and after 3 months. Radiologically, there was a 71% reduction in edema (pre-intervention: 37.0 cm³±37.7, post-intervention: 10.8 cm³ ± 14.9, p < 0.01). Overall satisfaction was 2.0 ± 1.3, SKV was 83.3%±16.6 and NRS at follow-up was 1.3 ± 1.8. OKS reached 33.6 ± 12.0. No major complications were observed. Rare side effects were dizziness which required premature termination of Ilomedin therapy on day 3. Iloprost treatment seems a safe and promising therapeutic option also in SONK with excellent subjective outcome and reduction of BME of 70% within 3 months after Iloprost infusion.

To develop and validate a CT-based radiomic-clinical-dosimetric model to assess the treatment response of lung metastasis following stereotactic body radiation therapy (SBRT). 80 lung metastases treated with SBRT curative intent in a single institution were analyzed. The treatment responses of lung lesions were categorized as a complete responding (CR) group vs. a non-complete responding (NCR) group according to RECIST criteria. For each lesion, 107 features were extracted from the CT planning images. The least absolute shrinkage and selection operator (LASSO) was used for features selection. An eXtreme Gradient Boosting (XGBoost) model was trained and validated. SHAP analysis was used to provide insights into the impact of each variable on the model's predictions. Eight radiomic features, one dosimetric variable and no clinical variables were identified by LASSO and used to build the XGBoost model. The model yielded AUCs of 0.897 (95%CI 0.860-0.935) and 0.864 (95%CI 0.803-0.924) in the training cohort and validation cohort, respectively. Skewness, surface-volume ratio, sphericity and BED10 were the most significant variables in predicting CR. The SHAP plots illustrated the feature's global and local impact to the model, explaining the model output in a clinician-friendly way. The integration of the XGBoost model with the SHAP strategy was able to assess lung lesions CR following SBRT, with the potential to assist clinicians in directing personalized SBRT strategies in an understandable manner. The explanaible radiomics model we propose can better predict the treatment response of lung metastasis after SBRT and provide further guidance for clinical practice.

This study aimed to develop machine learning-based algorithms to assist physicians in ultrasound-guided localization of the cricoid cartilage (CC), thyroid cartilage (TC), and cricothyroid membrane (CTM) for cricothyroidotomy. Adult female participants presenting to the emergency department with dyspnea or to the obstetrics and gynecology department for a scheduled cesarean section between August 2022 and July 2024 were prospectively recruited. Ultrasonographic images were collected using a wireless handheld ultrasound device connected to an edge computing tablet. Three You Only Look Once (YOLO) model variants-v5n6, v8n, and v10n-were selected for development and evaluation. A total of 608 participants (median age: 58.0 years, interquartile range [IQR]: 40.0-73.0; median body mass index: 23.2 kg/m², IQR: 20.2-26.5) contributed 117,094 ultrasonographic frames. All three YOLO-based models demonstrated high accuracy in detecting CC, TC, and CTM, with area under the receiver operating characteristic curve values exceeding 0.88. In correctly identified frames, the models effectively localized CC (IOU values: YOLOv5n6, 0.713 [95% confidence interval (CI): 0.698-0.726]; YOLOv8n, 0.718 [95% CI: 0.702-0.733]; YOLOv10n, 0.718 [95% CI: 0.701-0.734]; p value: 0.03) and TC (YOLOv5n6, 0.700 [95% CI: 0.683-0.717]; YOLOv8n, 0.706 [95% CI: 0.687-0.725]; YOLOv10n, 0.703 [95% CI: 0.783-0.721] ; p value: 0.037), though localization accuracy was lower for CTM (YOLOv5n6, 0.364 [95% CI: 0.333-0.394]; YOLOv8n, 0.363 [95% CI: 0.331-0.394]; YOLOv10n, 0.354 [95% CI: 0.325-0.381] ; p value: 0.053). The mean frames per second for YOLOv5n6, YOLOv8n, and YOLOv10n were 3.67, 13.83, and 14.13, respectively, when deployed on the handheld ultrasound platform. YOLO-based models demonstrated high accuracy in detecting and localizing CC, TC, and CTM. YOLOv8n and YOLOv10n achieved clinically acceptable real-time imaging performance when deployed on a wireless handheld ultrasound device with an edge computing tablet. Further studies are needed to assess whether this favorable performance translates into actual clinical benefits.

This study aimed to clarify whether quantitative high-resolution computed tomography (HRCT) analysis can assess the condition of interstitial lung disease (ILD) associated with anti-melanoma differentiation-associated gene 5 positive (anti MDA5+) dermatomyositis (DM) and investigate the efficacy of tofacitinib in the treatment of anti-MDA5+ DM. Seventy patients were included in this retrospective study: 39 in the tofacitinib group and 31 in the group without tofacitinib. Patients' HRCT were uploaded to a deep learning system to assess ILD regression. Based on patients' quantitative HRCT results, survival and glucocorticoids (GCs) usage, the efficacy of tofacitinib in the treatment of anti-MDA5+ DM were assessed. The safety was assessed by recording the incidence of adverse reactions. Data were analyzed using SPSS26.0 and R4.4.1. No significant differences for baseline characteristics were observed between the two groups of patients, except for cutaneous involvement. Tofacitinib group showed higher 3-year survival and it was an independent protective factor against mortality. Elevated serum ferritin (>1000μg/L) increased the risk of death. Quantitative HRCT analysis showed a significant reduction in the percentage of whole-lung involvement in the tofacitinib group between the baseline and follow-up. The total lesion volume reduction in the whole lung after treatment was substantially higher in the tofacitinib group. The tofacitinib group had a shorter duration of GCs tapering and a higher risk of EBV infection. Quantitative HRCT analysis can be used to assess the response of ILD to tofacitinib treatment. Tofacitinib is effective in patients with anti-MDA5+ DM-ILD but increases the risk of infection.

Segmentation of breast lesions in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is critical for effective diagnosis. This study investigates the impact of breast region segmentation (BRS) on the performance of deep learning-based breast lesion segmentation (BLS) in breast DCE-MRI. The study utilized the Stavanger Dataset, comprising 59 DCE-MRI scans, and employed the UNet++ architecture as the segmentation model. Four experimental approaches were designed to assess the influence of BRS on BLS: (1) Whole Volume (WV) without BRS, (2) WV with BRS, (3) BRS applied only to Selected Lesion-containing Slices (SLS), and (4) BRS applied to an Optimal Volume (OV). Data augmentation and oversampling techniques were implemented to address dataset limitations and enhance model generalizability. A systematic method was employed to determine OV sizes for patient's DCE-MRI images ensuring full lesion inclusion. Model training and validation were conducted using a hybrid loss function-comprising Dice loss, focal loss, and cross-entropy loss-and a five-fold cross-validation strategy. Final evaluations were performed on a randomly split test dataset for each of the four approaches. The findings indicate that applying BRS significantly enhances model performance. The most notable improvement was observed in the fourth approach, BRS with OV, which achieved approximately a 50% increase in segmentation accuracy compared to the non-BRS baseline. Furthermore, the BRS with OV approach resulted in a substantial reduction in computational energy consumption-up to 450%, highlighting its potential as an environmentally sustainable solution for large-scale applications.

Accurate diagnosis of anterior disc displacement (ADD) is essential for managing temporomandibular joint disorders (TMJ). This study employed machine learning (ML) to automatically detect anteriorly displaced TMJ discs in magnetic resonance images (MRI). This retrospective study included patients with TMJ disorders who visited the Hospital between January 2023 and June 2024. Five machine learning models-decision tree (DT), K-nearest neighbors (KNN), support vector machine (SVM), random forest (RF), and logistic regression (LR)-were utilized to train and validate radiomics data derived from TMJ imaging. Model performance was assessed using an 8:2 train-test split, evaluating accuracy with metrics such as area under the curve (AUC), sensitivity, specificity, precision, and F1 score. After manual delineation of TMJ ROIs by an experienced radiologist (serving as reference standard), radiomic feature extraction included first-order statistics, size- and shape-based features, and texture features.The open-phase, close-phase, and open and close fusion radiomics image features were evaluated separately. The study analyzed 382 TMJs from 191 patients, comprising 214 normal joints and 168 abnormal joints. The fusion radiomics model using five classifiers surpassed both open-phase and close-phase models, demonstrating superior performance in both training and validation cohorts. The fusion radiomics model consistently outperformed single-phase analyses across both diagnostic tasks. For normal vs. abnormal TMJ discrimination, the Random Forest (RF) classifier demonstrated robust performance with AUCs of 0.889 (95% CI: 0.854-0.924) in training and 0.874 (95% CI: 0.799-0.948) in validation.Complete performance metrics for all five classifiers are detailed in the main text. The fusion radiomics model effectively distinguished normal from abnormal joints and differentiated between ADDwR and ADDwoR, supporting personalized treatment planning. not applicable.

Developing generalist foundation model has recently attracted tremendous attention in the field of AI for Medicine, which requires open-source medical image datasets that incorporate diverse supervision signals across various imaging modalities. In this paper, we introduce RadGenome-Chest CT, a comprehensive, large-scale, region-guided 3D chest CT interpretation dataset based on CT-RATE. Specifically, we leverage the latest powerful universal segmentation model and large language models, to extend the original datasets from the following aspects: organ-level segmentation masks covering 197 categories, which provide intermediate reasoning visual clues for interpretation; 665K multigranularity grounded reports, where each sentence of the report is linked to the corresponding anatomical region of CT volume with a segmentation mask; 1.2M grounded VQA pairs, where questions and answers are all linked with reference segmentation masks, enabling models to associate visual evidence with textual explanations. We believe that RadGenome-Chest CT can significantly advance the development of multimodal medical foundation models, by training to generate texts based on given segmentation regions, which is unattainable with previous relevant datasets.

Training deep neural networks with multi-domain data generally gives more robustness and accuracy than training with single domain data, leading to the development of many deep learning-based algorithms using multi-domain data. However, if part of the input data is unavailable due to missing or corrupted data, a significant bias can occur, a problem that may be relatively more critical in medical applications where patients may be negatively affected. In this study, we propose the Laplacian filter attention with style transfer generative adversarial network (LASTGAN) to solve the problem of missing sequences in brain tumor magnetic resonance imaging (MRI). Our method combines image imputation and image-to-image translation to accurately synthesize specific sequences of missing MR images. LASTGAN can accurately synthesize both overall anatomical structures and tumor regions of the brain in MR images by employing a novel attention module that utilizes a Laplacian filter. Additionally, among the other sub-networks, the generator injects a style vector of the missing domain that is subsequently inferred by the style encoder, while the style mapper assists the generator in synthesizing domain-specific images. We show that the proposed model, LASTGAN, synthesizes high quality MR images with respect to other existing GAN-based methods. Furthermore, we validate the use of LASTGAN for data imputation or augmentation through segmentation experiments.