Two-dimensional Ultrasound Imaging Research Articles

Shear wave elastography to evaluate the effect of serum uric acid levels on carotid artery elasticity in patients with high-normal blood pressure

Background: Populations with normal high blood pressure often already have elevated blood uric acid levels and a higher chance of developing atherosclerosis, which accelerates the process of cardiovascular disease. The risk of atherosclerosis increases with thickening of the carotid artery intima-media, and changes in carotid artery elasticity precede intima-media changes, so early monitoring of carotid artery elasticity is of great significance in the prevention of cardiovascular disease. Using shear wave elastography (SWE) to evaluate the effect of serum uric acid (SUA) levels on carotid artery elasticity in patients with high-normal blood pressure (BP). Methods: One hundred and fifteen patients with high-normal BP were selected, and then divided into tertiles according to the SUA levels. The left carotid intima-media thickness (IMT), peak systolic velocity (PSV) and diameter of common carotid artery were measured by two-dimensional ultrasound and Doppler flow imaging. Longitudinal elasticity of the left anterior carotid wall was measured by SWE, including the mean values of the minimum elastic modulus (MEmin), maximum elastic modulus (MEmax) and mean elastic modulus (MEmean). Results: IMT, MEmean, MEmin and MEmax were obviously higher in the 3rd tertile (all P < 0.05), while there were no obviously different between the 1st tertile and 2nd tertile. Pearson correlation analysis showed positive correlations between SUA and SWE-related parameters, while there was no correlation with IMT. Multiple linear regression analysis found that age, systolic BP, and SUA levels were independently associated with SWE-related parameters. Conclusion: SWE will be more helpful than IMT in monitoring the effect of blood uric acid levels on carotid artery elasticity in patients with high-normal BP.

Ultrasound-based Radiomics Analysis for Assessing Risk Factors Associated With Early Recurrence Following Surgical Resection of Hepatocellular Carcinoma

ObjectiveThe aim of this study was to explore the value of ultrasound-based radiomics analysis for early recurrence (ER) after surgical resection of hepatocellular carcinoma (HCC). MethodsThis retrospective study included 127 patients who underwent primary surgical resection for HCC between October 2019 and November 2021. The patients were subsequently divided into training and validation sets (7:3 ratio). All patients received preoperative routine ultrasound and contrast-enhanced ultrasound (CEUS), with postoperative pathological confirmation of HCC. Radiomics features were extracted from maximum section of two-dimensional ultrasound image. The least absolute shrinkage and selection operation (LASSO) logistic regression algorithm with 10-fold cross-validation was employed to establish ultrasonic radiomics features. Logistic regression modeling was employed to build models based on clinical and ultrasonic features (model 1, clinical-ultrasonic model), radiomics signature (model 2, ultrasonic radiomics model), and the combination (model 3, clinical-ultrasonic-radiomics model). Then a nomogram model was established to predict the risk of ER, and the application value of nomogram through internal verification was evaluated. ResultsModel 3 showed optimal diagnostic performance in both training set (AUC=0.907) and validation set (AUC=0.925), followed by the model 1 in training set (AUC=0.846) and validation set (AUC=0.855), both above two models performed better than model 2 in training set (AUC=0.751) and validation set (AUC=0.702) (p<0.05). In training set and validation set of model 3, the sensitivity were 83.3%, 77.8%, the specificity ware 95.8%, 100.0% and the C-index were 0.791, 0.778. ConclusionThe preoperative clinical-ultrasonic-radiomics model is anticipated to be a reliable tool for predicting the ER of surgical resection of HCC.

Machine Learning-Enabled Fuhrman Grade in Clear-cell Renal Carcinoma Prediction Using Two-dimensional Ultrasound Images

ObjectiveAccurate assessment of Fuhrman grade is crucial for optimal clinical management and personalized treatment strategies in patients with clear cell renal cell carcinoma (CCRCC). In this study, we developed a predictive model using ultrasound (US) images to accurately predict the Fuhrman grade. MethodsBetween March 2013 and July 2023, a retrospective analysis was conducted on the US imaging and clinical data of 235 patients with pathologically confirmed CCRCC, including 67 with Fuhrman grades Ⅲ and Ⅳ. This study included 201 patients from Hospital A who were divided into training set (n = 161) and an internal validation set (n = 40) in an 8:2 ratio. Additionally, 34 patients from Hospital B were included for external validation. US images were delineated using ITK software, and radiomics features were extracted using PyRadiomics software. Subsequently, separate models for clinical factors, radiomics features, and their combinations were constructed. The model's performance was assessed by calculating the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA). ResultsIn total, 235 patients diagnosed with CCRCC, comprising 168 low-grade and 67 high-grade tumors, were included in this study. A comparison of the predictive performances of different models revealed that the logistic regression model exhibited relatively good stability and robustness. The AUC of the combined model for the training, internal validation and external validation sets were 0.871, 0.785 and 0.826, respectively, which were higher than those of the clinical and imaging histology models. Furthermore, the calibration curve demonstrated excellent concordance between the predicted Fuhrman grade probability of CCRCC using the combined model and the observed values in both the training and validation sets. Additionally, within the threshold range of 0–0.93, the combined model demonstrated substantial clinical utility, as evidenced by DCA. ConclusionThe application of US radiomics techniques enabled objective prediction of Fuhrman grading in patients with CCRCC. Nevertheless, certain clinical indicators remain indispensable, underscoring the pressing need for their integrated use in clinical practice. Advances in knowledgePrevious studies have predominantly focused on using computed tomography or magnetic resonance imaging modalities to predict the Fuhrman grade of CCRCC. Our findings demonstrate that a prediction model based on US images is more cost-effective, easily accessible and exhibits commendable performance. Consequently, this study offers a promising approach to maximizing the use of US examinations in future research.

The diagnostic value of two-dimensional ultrasound score, contrast-enhanced ultrasound score and ultrasound elastography score in prostate cancer.

Prostate cancer (PCa) is a prevalent malignancy in men, with early diagnosis being crucial for treatment and prognosis. This study evaluates the diagnostic efficacy of two-dimensional ultrasound imaging score (2DUS), contrast-enhanced ultrasound score (CEUS), and ultrasound elastography score (UES) in PCa. The PCa group consisted of patients diagnosed with primary PCa who underwent radical prostatectomy at the second hospital of Shanxi Medical University between January 2022 and December 2023. The benign lesion group consisted of patients diagnosed with benign prostatic hyperplasia (BPH)through prostate biopsy during the same period. We compared ultrasound scores at PCa and BPH patients using receiver operating characteristic (ROC) curve analysis. The study collected comprehensive patient data and analyzed variations in 2DUS, CEUS, and UES to identify relationships between preoperative ultrasound findings and the pathological states of PCa patients. PCa patients exhibited significantly higher ultrasound scores (P<0.001). Optimal cut-offs were 2.110 for 2DUS, 3.235 for CEUS, and 2.790 for UES, yielding area under curves (AUC) of 0.789, 0.817, and 0.898. The combined score provided an AUC of 0.933, with 83.33% sensitivity and 90.70% specificity. In the form of that patients with tumor stage III-IV, pathological grade III, poor differentiation, and pelvic lymph node metastasis exhibited significantly higher scores in 2DUS, CEUS, and UES compared to those with tumor stages I-II, pathological grades I-II, moderate and high differentiation without pelvic lymph node metastasis, respectively (P<0.05). The combined use of 2DUS, CEUS, and UES scores is highly effective for early PCa detection, surpassing individual scores in accuracy, and is beneficial for staging and differentiation.

Revolutionizing Bladder Health: Artificial-Intelligence-Powered Automatic Measurement of Bladder Volume Using Two-Dimensional Ultrasound.

Measuring elevated post-void residual volume is important for diagnosing urinary outflow tract obstruction and cauda equina syndrome. Catheter placement is exact but painful, invasive, and may cause infection, whereas an ultrasound is accurate, painless, and safe. The purpose of this single-center study is to evaluate the accuracy of a module for artificial-intelligence (AI)-based fully automated bladder volume (BV) prospective measurement using two-dimensional ultrasound images, as compared with manual measurement by expert sonographers. Pairs of transverse and longitudinal bladder images were obtained from patients evaluated in an urgent care clinic. The scans were prospectively analyzed by the automated module using the prolate ellipsoid method. The same examinations were manually measured by a blinded expert sonographer. The two methods were compared using the Pearson correlation, kappa coefficients, and the Bland-Altman method. A total of 111 pairs of transverse and longitudinal views were included. A very strong correlation was found between the manual BV measurements and the AI-based module with r = 0.97 [95% CI: 0.96-0.98]. The specificity and sensitivity for the diagnosis of an elevated post-void residual volume using a threshold ≥200 mL were 1.00 and 0.82, respectively. An almost-perfect agreement between manual and automated methods was obtained (kappa = 0.85). Perfect reproducibility was found for both inter- and intra-observer agreements. This AI-based module provides an accurate automated measurement of the BV based on ultrasound images. This novel method demonstrates a very strong correlation with the gold standard, making it a potentially valuable decision-support tool for non-experts in acute settings.

A novel artificial intelligence model for measuring fetal intracranial markers during the first trimester based on two-dimensional ultrasound image.

To establish reference ranges of fetal intracranial markers during the first trimester and develop the first novel artificial intelligence (AI) model to measure key markers automatically. This retrospective study used two-dimensional (2D) ultrasound images from 4233 singleton normal fetuses scanned at 11+0-13+6 weeks of gestation at the Affiliated Suzhou Hospital of Nanjing Medical University from January 2018 to July 2022. We analyzed 10 key markers in three important planes of the fetal head. Based on these, reference ranges of 10 fetal intracranial markers were established and an AI model was developed for automated marker measurement. AI and manual measurements were compared to evaluate differences, correlations, consistency, and time consumption based on mean error, Pearson correlation analysis, intraclass correlation coefficients (ICCs), and average measurement time. The results of AI and manual methods had strong consistency and correlation (all ICC values >0.75, all r values >0.75, and all P values <0.001). The average absolute error of both only ranged from 0.124 to 0.178 mm. AI achieved a 100% detection rate for abnormal cases. Additionally, the average measurement time of AI was only 0.49 s, which was more than 65 times faster than the manual measurement method. The present study first established the normal standard reference ranges of fetal intracranial markers based on a large Chinese population data set. Furthermore, the proposed AI model demonstrated its capability to measure multiple fetal intracranial markers automatically, serving as a highly effective tool to streamline sonographer tasks and mitigate manual measurement errors, which can be generalized to first-trimester scanning.

Elevation Resolution Enhancement Oriented 3D Ultrasound Imaging.

Three-dimensional (3D) ultrasound imaging can be accomplished by reconstructing a sequence of two-dimensional (2D) ultrasound images. However, 2D ultrasound images usually suffer from low resolution in the elevation direction, thereby impacting the accuracy of 3D reconstructed results. The lateral resolution of 2D ultrasound is known to significantly exceed the elevation resolution. By combining scanning sequences acquired from orthogonal directions, the effects of poor elevation resolution can be mitigated through a composite reconstructing process. Moreover, capturing ultrasound images from multiple perspectives necessitates a precise probe positioning method with a wide angle of coverage. Optical tracking is popularly used for probe positioning for its high accuracy and environment-robustness. In this paper, a novel large-angle accurate optical positioning method is used for enhancing resolution in 3D ultrasound imaging through orthogonal-view scanning and composite reconstruction. Experiments on two phantoms proved that our method could significantly improve reconstruction accuracy in the elevation direction of the probe compared with single-angle parallel scanning. The results indicate that our method holds the potential to improve current 3D ultrasound imaging techniques.

Two-Dimensional Ultrasound-Based Radiomics Nomogram for Diabetic Kidney Disease: A Pilot Study.

To establish a radiomics nomogram based on two-dimensional ultrasound for risk assessment of diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). This study retrospectively collected two-dimensional ultrasound images and clinical data from 52 patients with T2DM who underwent renal biopsy in our hospital from January 2023 to August 2023. Based on the pathological results, all patients were categorized into two groups: DKD (n=33) and non-DKD (n=19). The radiomic features of the segmented kidney in ultrasound pictures were retrieved and selected to calculate each patient's rad-score. A predictive nomogram based on rad-score and clinical features was then constructed and validated based on the calibration curve. The rad-score for all patients were computed based on five imaging characteristics extracted from the ultrasound images. The predictive nomogram was developed with the rad-score, diabetic retinopathy, duration of diabetes, and glycosylated hemoglobin. Moreover, This radiomics nomogram showed outstanding calibration capability, discrimination as well as therapeutic usefulness. We constructed a nomogram based on two-dimensional ultrasound for DKD in T2DM patientsThe model has been proven to have good predictive performance, showing its potential in identifying DKD in T2DM patients and assisting in making appropriate early interventions.

Volumetric B-mode ultrasound and Doppler Imaging: Automatic Tracking With One Single Camera.

Vascular diseases may occur in the upper extremities, and the lesions can span the entire length of the blood vessel. One of the most popular methods to identify vascular disorders is ultrasound Doppler imaging. However, traditional two-dimensional (2D) ultrasound Doppler imaging cannot capture the entire length of a long vessel in one image. Medical professionals often have to painstakingly reconstruct three-dimensional (3D) data using 2D ultrasound images to locate the lesions, especially for large blood vessels. 3D ultrasound Doppler imaging can display the morphological structure of blood vessels and the distribution of lesions more directly, providing a more comprehensive view compared to 2D imaging. In this work, we propose a wide-range 3D volumetric ultrasound Doppler imaging system with dual modality, in which a high-definition camera is adopted to automatically track the movement of the ultrasound transducer, simultaneously capturing a corresponding sequence of 2D ultrasound Doppler images. We conducted experiments on human arms using our proposed system and separately with X-ray computerized tomography (X-CT). The comparison results prove the potential value of our proposed system in the diagnosis of arm vascular diseases.

Value of radiomics-based two-dimensional ultrasound for diagnosing early diabetic nephropathy

Despite efforts to diagnose diabetic nephropathy (DN) using biochemical data or ultrasound imaging separately, a significant gap exists regarding the development of integrated models combining both modalities for enhanced early DN diagnosis. Therefore, we aimed to assess the ability of machine learning models containing two-dimensional ultrasound imaging and biochemical data to diagnose early DN in patients with type 2 diabetes mellitus (T2DM). This retrospective study included 219 patients, divided into a training or test group at an 8:2 ratio. Features were selected using minimum redundancy maximum relevance and random forest-recursive feature elimination. The predictive performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) for sensitivity, specificity, Matthews Correlation Coefficient, F1 score, and accuracy. K-nearest neighbor, support vector machine, and logistic regression models could diagnose early DN, with AUC values of 0.94, 0.85, and 0.85 in the training cohort and 0.91, 0.84, and 0.84 in the test cohort, respectively. Early DN diagnosing using two-dimensional ultrasound-based radiomics models can potentially revolutionize T2DM patient care by enabling proactive interventions, ultimately improving patient outcomes. Our integrated approach showcases the power of artificial intelligence in medical imaging, enhancing early disease detection strategies with far-reaching applications across medical disciplines.

Development of a novel combined nomogram model integrating deep learning radiomics to diagnose IgA nephropathy clinically

This study aimed to develop and validate a combined nomogram model based on superb microvascular imaging (SMI)-based deep learning (DL), radiomics characteristics, and clinical factors for noninvasive differentiation between immunoglobulin A nephropathy (IgAN) and non-IgAN. We prospectively enrolled patients with chronic kidney disease who underwent renal biopsy from May 2022 to December 2022 and performed an ultrasound and SMI the day before renal biopsy. The selected patients were randomly divided into training and testing cohorts in a 7:3 ratio. We extracted DL and radiometric features from the two-dimensional ultrasound and SMI images. A combined nomograph model was developed by combining the predictive probability of DL with clinical factors using multivariate logistic regression analysis. The proposed model’s utility was evaluated using receiver operating characteristics, calibration, and decision curve analysis. In this study, 120 patients with primary glomerular disease were included, including 84 in the training and 36 in the test cohorts. In the testing cohort, the ROC of the radiomics model was 0.816 (95% CI:0.663–0.968), and the ROC of the DL model was 0.844 (95% CI:0.717–0.971). The nomogram model combined with independent clinical risk factors (IgA and hematuria) showed strong discrimination, with an ROC of 0.884 (95% CI:0.773–0.996) in the testing cohort. Decision curve analysis verified the clinical practicability of the combined nomogram. The combined nomogram model based on SMI can accurately and noninvasively distinguish IgAN from non-IgAN and help physicians make clearer patient treatment plans.

Registration between 2D and 3D Ultrasound Images to Track Liver Blood Vessel Movement.

For the accurate positioning of surgical tools, conventional intraoperative navigation systems have been developed to recognize the relationship between target positions and the tools. However, since an internal organ is deformed during the operation, registration between realtime two-dimensional (2D) ultrasound images and three-dimensional (3D) CT or MRI images is not always effective. Therefore, this study developed image registration between 2D and 3D ultrasound images considering deformation for tracking target vessel movement in the liver. 3D ultrasound image was obtained in advance with 3D coordinates, including the target vessel. Then real-time 2D images and ultrasound probe position were simultaneously acquired using a 3D position sensor. We applied multiple image resolution registration, where rapid and fine optimizations can be expected at higher and lower levels, respectively. Meanwhile, the gradient descent method was adopted for the optimization, which determines the relative arrangements to obtain maximum similarity between 2D and 3D images. We experimentally established resolution level parameters using a phantom before applying it to track liver blood vessel movements in a normal healthy subject. Comparing the 2D images and the registered images, although the approach has some limitations in tracking large displacement, we confirmed that the cross-section of the target blood vessel was clearly visualized. This method has the potential for an ultrasound therapy targeting blood vessels under natural respiration conditions.

The effect of image resolution on convolutional neural networks in breast ultrasound

PurposeThe objective of this research was to investigate the efficacy of various parameter combinations of Convolutional Neural Networks (CNNs) models, namely MobileNet and DenseNet121, and different input image resolutions (REZs) ranging from 64×64 to 512×512 pixels, for diagnosing breast cancer. Materials and methodsDuring the period of June 2015 to November 2020, two hospitals were involved in the collection of two-dimensional ultrasound breast images for this retrospective multicenter study. The diagnostic performance of the computer models MobileNet and DenseNet 121 was compared at different resolutions. ResultsThe results showed that MobileNet had the best breast cancer diagnosis performance at 320×320pixel REZ and DenseNet121 had the best breast cancer diagnosis performance at 448×448pixel REZ. ConclusionOur study reveals a significant correlation between image resolution and breast cancer diagnosis accuracy. Through the comparison of MobileNet and DenseNet121, it is highlighted that lightweight neural networks (LW-CNNs) can achieve model performance similar to or even slightly better than large neural networks models (HW-CNNs) in ultrasound images, and LW-CNNs' prediction time per image is lower.

Echocardiography and 3D printing: cardiac models for the education of dog owners

Three-dimensional (3D) printing is a new method for creating human and veterinary anatomical models, which makes the education of students and professionals in the health area more complete, in addition to helping the patients themselves understand. In the area of ​​cardiology, this technique can efficiently help the assessment of cardiac alterations for the patient during medical consultations, tying a feeling of involvement with the medical team. Likewise, it is possible to use 3D printing to understand the echocardiographic technique, where conceptual knowledge of the anatomy of the heart and the ability to translate a two-dimensional ultrasound image into a 3D idea is required. This research aimed to develop printable 3D cardiac models, to demonstrate cardiac sections used in echocardiography and use them to teach dog owners, evaluating their suitability as a tool for a better understanding of the echocardiographic exam. The 3D cardiac models were validated by dog owners through an evaluation questionnaire prepared on a Likert scale, after monitoring the echocardiographic examination with an explanation by the echocardiographer using the printed models. A total of 30 dog owners participated in the study. In all seven questions of the questionnaire, the vast majority of positive responses were observed, with partial or total agreement by the participants. These results showed that the use of 3D printed models is effective in improving the understanding of the echocardiographic examination and is feasible in the daily workflow.

Automatic measurement of kidney dimensions in two-dimensional ultrasonography is comparable to expert sonographers.

Length and width measurements of the kidneys aid in the detection and monitoring of structural abnormalities and organ disease. Manual measurement results in intra- and inter-rater variability, is complex and time-consuming, and is fraught with error. We propose an automated approach based on machine learning for quantifying kidney dimensions from two-dimensional (2D) ultrasound images in both native and transplanted kidneys. An nnU-net machine learning model was trained on 514 images to segment the kidney capsule in standard longitudinal and transverse views. Two expert sonographers and three medical students manually measured the maximal kidney length and width in 132 ultrasound cines. The segmentation algorithm was then applied to the same cines, region fitting was performed, and the maximum kidney length and width were measured. Additionally, single kidney volume for 16 patients was estimated using either manual or automatic measurements. The experts resulted in length of [95% CI: 80.0, 89.6] and a width of [49.9, 53.7]. The algorithm resulted a length of [81.5, 91.1] and a width of [43.6, 50.6]. Experts, novices, and the algorithm did not statistically significant differ from one another (). Bland-Altman analysis showed the algorithm produced a mean difference of 2.6mm (SD = 1.2) from experts, compared to novices who had a mean difference of 3.7mm (SD = 2.9mm). For volumes, mean absolute difference was 47mL (31%) consistent with error in all three dimensions. This pilot study demonstrates the feasibility of an automatic tool to measure in vivo kidney biometrics of length, width, and volume from standard 2D ultrasound views with comparable accuracy and reproducibility to expert sonographers. Such a tool may enhance workplace efficiency, assist novices, and aid in tracking disease progression.

Histogram analysis of based on two-dimensional ultrasound images to differentiate medullary thyroid carcinoma and thyroid adenoma

Objective: To investigate the feasibility and value of histogram analysis based on two-dimensional gray-scale ultrasonography in the differential diagnosis of medullary thyroid carcinoma (MTC) and thyroid adenoma (TA). Methods: The preoperative ultrasound images of 86 newly diagnosed MTC patients and 100 TA patients treated in the Cancer Hospital of Chinese Academy of Medical Sciences from January 2015 to October 2021 were collected. Histograms were performed based on the regions of interest (ROIs) delineated manually by two radiologists, thereafter, mean, variance, skewness, kurtosis, percentiles (1st, 10th, 50th, 90th, 99th) were generated. The histogram parameters between the MTC group and the TA group were compared, and the independent predictors were screened by multivariate logistic regression analysis. Receiver operating characteristic (ROC) analysis was used to compare the individual diagnostic efficacy and joint diagnostic efficacy of independent predictors. Results: Multivariate regression analysis showed that mean, skewness, kurtosis and 50th percentile were independent factors. The skewness and kurtosis in the MTC group were significantly higher than those in the TA group, and the mean and 50th percentile were significantly lower than those in the TA group. The area under the individual ROC curve of mean, skewness, kurtosis and 50th percentile is 0.654-0.778. The area under the combined ROC curve is 0.826. Conclusion: Histogram analysis based on two-dimensional gray-scale ultrasonography is a promising tool to distinguish MTC from TA, in which the joint diagnosis value of mean, skewness, kurtosis and 50th percentile is the highest.

Investigating the diagnostic efficiency of a computer-aided diagnosis system for thyroid nodules in the context of Hashimoto's thyroiditis.

This study aims to investigate the efficacy of a computer-aided diagnosis (CAD) system in distinguishing between benign and malignant thyroid nodules in the context of Hashimoto's thyroiditis (HT) and to evaluate the role of the CAD system in reducing unnecessary biopsies of benign lesions. We included a total of 137 nodules from 137 consecutive patients (mean age, 43.5 ± 11.8 years) who were histopathologically diagnosed with HT. The two-dimensional ultrasound images and videos of all thyroid nodules were analyzed by the CAD system and two radiologists with different experiences according to ACR TI-RADS. The diagnostic cutoff values of ACR TI-RADS were divided into two categories (TR4 and TR5), and then the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of the CAD system and the junior and senior radiologists were compared in both cases. Moreover, ACR TI-RADS classification was revised according to the results of the CAD system, and the efficacy of recommended fine-needle aspiration (FNA) was evaluated by comparing the unnecessary biopsy rate and the malignant rate of punctured nodules. The accuracy, sensitivity, specificity, PPV, and NPV of the CAD system were 0.876, 0.905, 0.830, 0.894, and 0.846, respectively. With TR4 as the cutoff value, the AUCs of the CAD system and the junior and senior radiologists were 0.867, 0.628, and 0.722, respectively, and the CAD system had the highest AUC (P < 0.0001). With TR5 as the cutoff value, the AUCs of the CAD system and the junior and senior radiologists were 0.867, 0.654, and 0.812, respectively, and the CAD system had a higher AUC than the junior radiologist (P < 0.0001) but comparable to the senior radiologist (P = 0.0709). With the assistance of the CAD system, the number of TR4 nodules was decreased by both junior and senior radiologists, the malignant rate of punctured nodules increased by 30% and 22%, and the unnecessary biopsies of benign lesions were both reduced by nearly half. The CAD system based on deep learning can improve the diagnostic performance of radiologists in identifying benign and malignant thyroid nodules in the context of Hashimoto's thyroiditis and can play a role in FNA recommendations to reduce unnecessary biopsy rates.

Diagnostic accuracy of ultrasound-based multimodal radiomics modeling for fibrosis detection in chronic kidney disease

ObjectivesTo predict kidney fibrosis in patients with chronic kidney disease using radiomics of two-dimensional ultrasound (B-mode) and Sound Touch Elastography (STE) images in combination with clinical features.MethodsThe Mindray Resona 7 ultrasonic diagnostic apparatus with SC5-1U convex array probe (bandwidth frequency of 1–5 MHz) was used to perform two-dimensional ultrasound and STE software. The severity of cortical tubulointerstitial fibrosis was divided into three grades: mild interstitial fibrosis and tubular atrophy (IFTA), fibrotic area < 25%; moderate IFTA, fibrotic area 26–50%; and severe IFTA, fibrotic area > 50%. After extracting radiomics from B-mode and STE images in these patients, we analyzed two classification schemes: mild versus moderate-to-severe IFTA, and mild-to-moderate versus severe IFTA. A nomogram was constructed based on multiple logistic regression analyses, combining clinical and radiomics. The performance of the nomogram for differentiation was evaluated using receiver operating characteristic (ROC), calibration, and decision curves.ResultsA total of 150 patients undergoing kidney biopsy were enrolled (mild IFTA: n = 74; moderate IFTA: n = 33; severe IFTA: n = 43) and randomized into training (n = 105) and validation cohorts (n = 45). To differentiate between mild and moderate-to-severe IFTA, a nomogram incorporating STE radiomics, albumin, and estimated glomerular filtration (eGFR) rate achieved an area under the ROC curve (AUC) of 0.91 (95% confidence interval [CI]: 0.85–0.97) and 0.85 (95% CI: 0.77–0.98) in the training and validation cohorts, respectively. Between mild-to-moderate and severe IFTA, the nomogram incorporating B-mode and STE radiomics features, age, and eGFR achieved an AUC of 0.93 (95% CI: 0.89–0.98) and 0.83 (95% CI: 0.70–0.95) in the training and validation cohorts, respectively. Finally, we performed a decision curve analysis and found that the nomogram using both radiomics and clinical features exhibited better predictability than any other model (DeLong test, p < 0.05 for the training and validation cohorts).ConclusionA nomogram based on two-dimensional ultrasound and STE radiomics and clinical features served as a non-invasive tool capable of differentiating kidney fibrosis of different severities.Key Points• Radiomics calculated based on the ultrasound imaging may be used to predict the severities of kidney fibrosis.• Radiomics may be used to identify clinical features associated with the progression of tubulointerstitial fibrosis in patients with CKD.• Non-invasive ultrasound imaging-based radiomics method with accuracy aids in detecting renal fibrosis with different IFTA severities.

Speckle tracking imaging evaluation of left ventricular myocardial work comparing right ventricular septal pacing with His-Purkinje system area pacing.

We sought to objectively assess left ventricular myocardial work (MW) parameters after right ventricular septal pacing (VSP) and His-Purkinje system area pacing (HPSAP) procedures. Patients undergoing double-chamber pacemaker implantation for III-degree atrioventricular block (III° AVB) were assessed 1 year after implantation. VSP and HPSAP groups (20 and 23 patients, respectively) were compared against 40 healthy age-matched volunteers. Two-dimensional ultrasound speckle tracking imaging was used to obtain the global myocardial work index (GWI), global myocardial work efficiency (GWE), global myocardial constructive work (GCW), global myocardial wasted work (GWW), left ventricular stratified strain, and peak strain dispersion (PSD). GWI, GWE, and GCW parameters were improved in HPSAP compared to VSP, while GWW was significantly larger in the VSP group compared to the HPSAP group (all p < 0.05). HPSAP outperformed the VSP group in comparisons of global left ventricular longitudinal strain and stratified strain. Compared to controls, the GCW of all segmental myocardium (17/17 segments) in the VSP group was significantly reduced, while 70.59% (12/17 segments) in the HPSAP group was lower than the control group. GCW in the left ventricular segment of the HPSAP group was bigger than the VSP group (29.41%; 5/17 segments) and mainly concentrated in the ventricular septum and inferior wall. Our findings suggest that HPSAP performance outcomes are improved over VSP after 1 year, especially in left ventricular contractile synchrony, and HPSAP is beneficial to the effective myocardial work of the left ventricle.

Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction.

Ultrasound is one of the most commonly used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. Specifically, ultrasound images are routinely utilized to gather fetal information, including body measurements, anatomy structure, fetal movements, and pregnancy complications. Recent developments in artificial intelligence and computer vision provide new methods for the automated analysis of medical images in many domains, including ultrasound images. We present a full end-to-end framework for segmenting, measuring, and estimating fetal gestational age and weight based on two-dimensional ultrasound images of the fetal head. Our segmentation framework is based on the following components: (i) eight segmentation architectures (UNet, UNet Plus, Attention UNet, UNet 3+, TransUNet, FPN, LinkNet, and Deeplabv3) were fine-tuned using lightweight network EffientNetB0, and (ii) a weighted voting method for building an optimized ensemble transfer learning model (ETLM). On top of that, ETLM was used to segment the fetal head and to perform analytic and accurate measurements of circumference and seven other values of the fetal head, which we incorporated into a multiple regression model for predicting the week of gestational age and the estimated fetal weight (EFW). We finally validated the regression model by comparing our result with expert physician and longitudinal references. We evaluated the performance of our framework on the public domain dataset HC18: we obtained 98.53% mean intersection over union (mIoU) as the segmentation accuracy, overcoming the state-of-the-art methods; as measurement accuracy, we obtained a 1.87 mm mean absolute difference (MAD). Finally we obtained a 0.03% mean square error (MSE) in predicting the week of gestational age and 0.05% MSE in predicting EFW.