Thyroid nodules are commonly evaluated using ultrasound-based risk stratification systems, which rely on subjective descriptors. Artificial intelligence (AI) may improve assessment, but its effectiveness in non-subspecialist settings is unclear. This study evaluated the impact of an AI-based decision support system (AI-DSS) on thyroid nodule ultrasound assessments by general endocrinologists (GE) without subspecialty thyroid imaging training. A prospective cohort study was conducted on 80 patients undergoing thyroid ultrasound in GE outpatient clinics. Thyroid ultrasound was performed based on clinical judgment as part of routine care by GE. Images were retrospectively analyzed using an AI-DSS (Koios DS), independently of clinician assessments. AI-DSS results were compared with initial GE evaluations and, when referred, with expert evaluations at a subspecialized thyroid nodule clinic (TNC). Agreement in ultrasound features, risk classification by the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) and American Thyroid Association guidelines, and referral recommendations was assessed. AI-DSS differed notably from GE, particularly assessing nodule composition (solid: 80%vs.36%,p < 0.01), echogenicity (hypoechoic:52%vs.16%,p < 0.01), and echogenic foci (microcalcifications:10.7%vs.1.3%,p < 0.05). AI-DSS classification led to a higher referral rate compared to GE (37.3%vs.30.7%, not statistically significant). Agreement between AI-DSS and GE in ACR TI-RADS scoring was moderate (r = 0.337;p < 0.001), but improved when comparing GE to AI-DSS and TNC subspecialist (r = 0.465;p < 0.05 and r = 0.607;p < 0.05, respectively). In a non-subspecialist setting, non-adjunct AI-DSS use did not significantly improve risk stratification or reduce hypothetical referrals. The system tended to overestimate risk, potentially leading to unnecessary procedures. Further optimization is required for AI to function effectively in low-prevalence environment.

Patients living with HIV (PLHIV) have a higher cardiovascular risk than others, which is why the early detection of atherosclerosis in this population is important. The present study reports predictive models of subclinical atherosclerosis for this population of patients, made up of variables that are easily collected in the clinic. The study design is a cross-sectional observational study. PLHIV without established cardiovascular disease were recruited for this study. Predictive models of subclinical atherosclerosis (Doppler ultrasound) were developed by testing sociodemographic variables, pathological history, data related to HIV infection, laboratory parameters, and capillaroscopy as potential predictors. Logistic regression with internal validation (bootstrapping) and machine learning techniques were used to develop the models. Data from 96 HIV patients were analysed, 19 (19.8%) of whom had subclinical atherosclerosis. The predictors that went into both machine learning models and the regression model were hypertension, dyslipidaemia, protease inhibitors, triglycerides, fibrinogen, and alkaline phosphatase. Age and C-reactive protein were also part of the machine learning models. The logistic regression model had an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.84-0.99), which became 0.80 after internal validation by bootstrapping. The ma-chine learning techniques produced models with AUCs ranging from 0.73 to 0.86. We report predictive models for subclinical atherosclerosis in PLHIV, demonstrating relevant predictive performance based on easily accessible parameters, making them potentially useful as a screening tool. However, given the study's limitations-primarily the sample size-external validation in larger cohorts is warranted.

This study aims to explore whether intratumoral and peritumoral ultrasound radiomics of ultrasound images can predict the low expression status of human epidermal growth factor receptor 2 (HER2) in HER2-negative breast cancer patients. HER2-negative breast cancer patients were recruited retrospectively and randomly divided into a training cohort (n = 303) and a test cohort (n = 130) at a ratio of 7:3. The region of interest within the breast ultrasound image was designated as the intratumoral region, and expansions of 3 mm, 5 mm, and 8 mm from this region were considered as the peritumoral regions for the extraction of ultrasound radiomic features. Feature extraction and selection were performed, and radiomics scores (Rad-score) were obtained in four ultrasound radiomics scenarios: intratumoral only, intratumoral + peritumoral 3 mm, intratumoral + peritumoral 5 mm, and intratumoral + peritumoral 8 mm. An optimal combined nomogram radiomic model incorporating clinical features was established and validated. Subsequently, the diagnostic performance of the radiomic models was evaluated. The results indicated that the intratumoral + peritumoral (5 mm) ultrasound radiomics exhibited the excellent diagnostic performance in evaluated the HER2 low expression. The nomogram combining intratumoral + peritumoral (5 mm) and clinical features showed superior diagnostic performance, achieving an area under the curve (AUC) of 0.911 and 0.869 in the training and test cohorts, respectively. The combination of intratumoral + peritumoral (5 mm) ultrasound radiomics and clinical features possesses the capability to accurately predict the low-expression status of HER2 in HER2-negative breast cancer patients.

Segmentation of medical images is a fundamental task with numerous applications. While MRI, CT, and PET modalities have significantly benefited from deep learning segmentation techniques, more recent modalities, like functional ultrasound (fUS), have seen limited progress. fUS is a non invasive imaging method that measures changes in cerebral blood volume (CBV) with high spatio-temporal resolution. However, distinguishing arterioles from venules in fUS is challenging due to opposing blood flow directions within the same pixel. Ultrasound localization microscopy (ULM) can enhance resolution by tracking microbubble contrast agents but is invasive, and lacks dynamic CBV quantification. In this paper, we introduce the first deep learning-based application for fUS image segmentation, capable of differentiating signals based on vertical flow direction (upward vs. downward), using ULM-based automatic annotation, and enabling dynamic CBV quantification. In the cortical vasculature, this distinction in flow direction provides a proxy for differentiating arteries from veins. We evaluate various UNet architectures on fUS images of rat brains, achieving competitive segmentation performance, with 90% accuracy, a 71% F1 score, and an IoU of 0.59, using only 100 temporal frames from a fUS stack. These results are comparable to those from tubular structure segmentation in other imaging modalities. Additionally, models trained on resting-state data generalize well to images captured during visual stimulation, highlighting robustness. Although it does not reach the full granularity of ULM, the proposed method provides a practical, non-invasive and cost-effective solution for inferring flow direction-particularly valuable in scenarios where ULM is not available or feasible. Our pipeline shows high linear correlation coefficients between signals from predicted and actual compartments, showcasing its ability to accurately capture blood flow dynamics.

Prenatal healthcare development requires accurate automated techniques for fetal ultrasound image segmentation. This approach allows standardized evaluation of fetal development by minimizing time-exhaustive processes that perform poorly due to human intervention. This research develops a segmentation framework through U-Net++ with ResNet backbone features which incorporates attention components for enhancing extraction of features in low contrast, noisy ultrasound data. The model leverages the nested skip connections of U-Net++ and the residual learning of ResNet-34 to achieve state-of-the-art segmentation accuracy. Evaluations of the developed model against the vast fetal ultrasound image collection yielded superior results by reaching 97.52% Dice coefficient as well as 95.15% Intersection over Union (IoU), and 3.91 mm Hausdorff distance. The pipeline integrated Grad-CAM++ allows explanations of the model decisions for clinical utility and trust enhancement. The explainability component enables medical professionals to study how the model functions, which creates clear and proven segmentation outputs for better overall reliability. The framework fills in the gap between AI automation and clinical interpretability by showing important areas which affect predictions. The research shows that deep learning combined with Explainable AI (XAI) operates to generate medical imaging solutions that achieve high accuracy. The proposed system demonstrates readiness for clinical workflows due to its ability to deliver a sophisticated prenatal diagnostic instrument that enhances healthcare results.

Ultrasound-based bone surface segmentation is crucial in computer-assisted orthopedic surgery. However, ultrasound images have limitations, including a low signal-to-noise ratio, acoustic shadowing, and speckle noise, which make interpretation difficult. Existing deep learning models for bone segmentation rely primarily on costly manual labeling by experts, limiting dataset size and model generalizability. Additionally, the complexity of ultrasound physics and acoustic shadow makes the images difficult for humans to interpret, leading to incomplete labels in low-intensity and anechoic regions and limiting model performance. To advance the state-of-the-art in ultrasound bone segmentation and establish effective model benchmarks, larger and higher-quality datasets are needed. We propose a methodology for collecting ex-vivo ultrasound datasets with automatically generated bone labels, including anechoic regions. The proposed labels are derived by accurately superimposing tracked bone Computed Tomography (CT) models onto the tracked ultrasound images. These initial labels are refined to account for ultrasound physics. To clinically evaluate the proposed method, an expert physician from our university hospital specialized in orthopedic sonography assessed the quality of the generated bone labels. A neural network for bone segmentation is trained on the collected dataset and its predictions are compared to expert manual labels, evaluating accuracy, completeness, and F1-score. We collected UltraBones100k, the largest known dataset comprising 100k ex-vivo ultrasound images of human lower limbs with bone annotations, specifically targeting the fibula, tibia, and foot bones. A Wilcoxon signed-rank test with Bonferroni correction confirmed that the bone alignment after our optimization pipeline significantly improved the quality of bone labeling (p<0.001). The model trained on UltraBones100k consistently outperforms manual labeling in all metrics, particularly in low-intensity regions (at a distance threshold of 0.5 mm: 320% improvement in completeness, 27.4% improvement in accuracy, and 197% improvement in F1 score) CONCLUSION:: This work is promising to facilitate research and clinical translation of ultrasound imaging in computer-assisted interventions, particularly for applications such as 2D bone segmentation, 3D bone surface reconstruction, and multi-modality bone registration.

Accurate preoperative discrimination of salivary gland pleomorphic adenoma (SPA) stromal subtypes is essential for therapeutic plannings. We aimed to establish and test machine learning (ML) models for classification of stromal subtypes in SPA based on ultrasound histogram analysis. A total of 256 SPA patients were enrolled in the study and categorized into two groups: stroma-low and stroma-high. The dataset was split into a training cohort with 177 patients and a validation cohort with 79 patients. The least absolute shrinkage and selection operator (LASSO) regression identified optimal features, which were then utilized to build predictive models using logistic regression (LR) and eight ML algorithms. The effectiveness of the models was evaluated using a range of performance metrics, with a particular focus on the area under the receiver operating characteristic curve (AUC). After LASSO regression, six key features (lesion size, shape, cystic areas, vascularity, mean, and skewness) were selected to develop predictive models. The AUCs ranged from 0.575 to 0.827 for the nine models. The support vector machine (SVM) algorithm achieved the highest performance with an AUC of 0.827, accompanied by an accuracy of 0.798, precision of 0.792, recall of 0.862, and an F1 score of 0.826. The LR algorithm also exhibited robust performance, achieving an AUC of 0.818, slightly trailing behind the SVM algorithm. Decision curve analysis indicated that the SVM-based model provided superior clinical utility compared to other models. The ML model based on ultrasound histogram analysis offers a precise and non-invasive approach for preoperative categorization of stromal subtypes in SPA.

Superficial lymph node (LN) enlargement is a common ultrasonographic finding and can be associated with a broad spectrum of conditions, from benign reactive hyperplasia to malignant lymphoproliferative disorders (LPDs). LPDs, which include various hematologic malignancies affecting lymphoid tissue, present with diverse immune-morphological and clinical features, making differentiation from other malignant causes of lymphadenopathy challenging. Radiologic assessment is crucial in characterizing lymphadenopathy, with ultrasonography serving as a noninvasive and widely available imaging modality. High-resolution ultrasound allows the evaluation of key features such as LN size, shape, border definition, echogenicity, and the presence of abnormal cortical thickening, loss of the fatty hilum, or altered vascular patterns, which aid in distinguishing benign from malignant processes. This review aims to describe the ultrasonographic characteristics of lymphadenopathy, offering essential diagnostic insights to differentiate malignant disorders, particularly LPDs. We will discuss standard ultrasound techniques, including grayscale imaging and Doppler ultrasound, and explore more advanced methods such as contrast-enhanced ultrasound (CEUS), elastography, and artificial intelligence-assisted imaging, which are gaining prominence in LN evaluation. By highlighting these imaging modalities, we aim to enhance the diagnostic accuracy of ultrasonography in lymphadenopathy assessment and improve early detection of LPDs and other malignant conditions.

<b><i>Purpose:</i></b> Artificial intelligence (AI) models have shown promise in predicting malignant thyroid nodules in adults; however, research on deep learning (DL) for pediatric cases is limited. We evaluated the applicability of a DL-based model for assessing thyroid nodules in children. <b><i>Methods:</i></b> We retrospectively identified two pediatric cohorts (<i>n</i> = 128; mean age 15.5 ± 2.4 years; 103 girls) who had thyroid nodule ultrasonography (US) with histological confirmation at two institutions. The AI-Thyroid DL model, originally trained on adult data, was tested on pediatric nodules in three scenarios axial US images, longitudinal US images, and both. We conducted a subgroup analysis based on the two pediatric cohorts and age groups (≥14 years vs. < 14 years) and compared the model's performance with radiologist interpretations using the Thyroid Imaging Reporting and Data System (TIRADS). <b><i>Results:</i></b> Out of 156 nodules analyzed, 47 (30.1%) were malignant. AI-Thyroid demonstrated respective area under the receiver operating characteristic (AUROC), sensitivity, and specificity values of 0.913-0.929, 78.7-89.4%, and 79.8-91.7%, respectively. The AUROC values did not significantly differ across the image planes (all <i>p</i> > 0.05) and between the two pediatric cohorts (<i>p</i> = 0.804). No significant differences were observed between age groups in terms of sensitivity and specificity (all <i>p</i> > 0.05) while the AUROC values were higher for patients aged <14 years compared to those aged ≥14 years (all <i>p</i> < 0.01). AI-Thyroid yielded the highest AUROC values, followed by ACR-TIRADS and K-TIRADS (<i>p</i> = 0.016 and <i>p</i> < 0.001, respectively). <b><i>Conclusion:</i></b> AI-Thyroid demonstrated high performance in diagnosing pediatric thyroid cancer. Future research should focus on optimizing AI-Thyroid for pediatric use and exploring its role alongside tissue sampling in clinical practice.

BackgroundDelays in the diagnosis of transthyretin amyloid cardiomyopathy (ATTR-CM) contribute to the significant morbidity of the condition, especially in the era of disease-modifying therapies. Screening for ATTR-CM with AI and other algorithms may improve timely diagnosis, but these algorithms have not been directly compared. ObjectivesThe aim of this study was to compare the performance of four algorithms for ATTR-CM detection in a heart failure population and assess the risk for harms due to model bias. MethodsWe identified patients in an integrated health system from 2010-2022 with ATTR-CM and age- and sex-matched them to controls with heart failure to target 5% prevalence. We compared the performance of a claims-based random forest model (Huda et al. model), a regression-based score (Mayo ATTR-CM), and two deep learning echo models (EchoNet-LVH and EchoGo(R) Amyloidosis). We evaluated for bias using standard fairness metrics. ResultsThe analytical cohort included 176 confirmed cases of ATTR-CM and 3192 control patients with 79.2% self-identified as White and 9.0% as Black. The Huda et al. model performed poorly (AUC 0.49). Both deep learning echo models had a higher AUC when compared to the Mayo ATTR-CM Score (EchoNet-LVH 0.88; EchoGo Amyloidosis 0.92; Mayo ATTR-CM Score 0.79; DeLong P<0.001 for both). Bias auditing met fairness criteria for equal opportunity among patients who identified as Black. ConclusionsDeep learning, echo-based models to detect ATTR-CM demonstrated best overall discrimination when compared to two other models in external validation with low risk of harms due to racial bias.