Ultrasound Physicians Research Articles

Subendometrial blood flow detected by Doppler ultrasound associates with pregnancy outcomes of frozen embryo transfer in patients with thin endometrium.

Multiple factors have been shown to influence the rate of clinical pregnancy after FET in IVF treatment, including embryo quality, synchronization of embryo and endometrium, and endometrial receptivity (ER). The subendometrial blood flow conditions could also contribute potentially major effects toward the establishment and maintenance of pregnancy. We conducted a retrospective cohort study to examine the correlation between subendometrial blood flow, as determined by Doppler ultrasound, and pregnancy outcomes in IVF patients with a thin endometrium (endometrium thickness [EMT] ≤ 0.7cm). This was a retrospective cohort study conducted at a university-affiliated reproductive hospital from January 2017 to April 2023. The EMT and subendometrial blood flows were assessed using transvaginal color Doppler ultrasound and evaluated by experienced clinical ultrasound physicians on the endometrial transformation day. The pregnancy outcomes were followed up and documented in clinical medical records through the IVF cohort study at our center. In the patients with 0.5cm ≤ EMT ≤ 0.7cm, the embryo implantation rate was statistically significant increased in the patients with the presence of subendometrial blood flow (OR 1.484; 95% CI, 1.001-2.200; P = 0.049; aOR 1.425; 95% CI, 1.030-2.123; P = 0.003). Patients with discernible subendometrial blood flow have superior live birth (P = 0.028), clinical pregnancy (P = 0.049), and embryo implantation (P = 0.027) compared to the patients without subendometrial blood flow when the EMT is ≤ 0.7cm. The presence of subendometrial blood flow detected by ultrasound was positively associated with successful embryo implantation and favorable pregnancy outcomes in patients with thin endometrium undergoing FET.

Deep-learning radiomics based on ultrasound can objectively evaluate thyroid nodules and assist in improving the diagnostic level of ultrasound physicians.

The incidence rate of thyroid nodules has reached 65%, but only 5-15% of these modules are malignant. Therefore, accurately determining the benign and malignant nature of thyroid nodules can prevent unnecessary treatment. We aimed to develop a deep-learning (DL) radiomics model based on ultrasound (US), explore its diagnostic efficacy for benign and malignant thyroid nodules, and verify whether it improved the diagnostic level of physicians. We retrospectively included 1,076 thyroid nodules from 817 patients at three institutions. The radiomics and DL features of the US images were extracted and used to construct radiomics signature (Rad_sig) and deep-learning signature (DL_sig). A Pearson correlation analysis and least absolute shrinkage and selection operator (LASSO) regression analysis were used for feature selection. Clinical US semantic signature (C_US_sig) was constructed based on clinical information and US semantic features. Next, a combined model was constructed based on the above three signatures in the form of a nomogram. The model was constructed using a development set (institution 1: 719 nodules), and the model was evaluated using two external validation sets (institution 2: 74 nodules, and institution 3: 283 nodules). The performance of the model was assessed using decision curve analysis (DCA) and calibration curves. Furthermore, the C_US_sigs of junior physicians, senior physicians, and expers were constructed. The DL radiomics model was used to assist the physicians with different levels of experience in the interpretation of thyroid nodules. In the development and validation sets, the combined model showed the highest performance, with areas under the curve (AUCs) of 0.947, 0.917, and 0.929, respectively. The DCA results showed that the comprehensive nomogram had the best clinical utility. The calibration curves indicated good calibration for all models. The AUCs for distinguishing between benign and malignant thyroid nodules by junior physicians, senior physicians, and experts were 0.714-0.752, 0.740-0.824, and 0.891-0.908, respectively; however, with the assistance of DL radiomics, the AUCs reached 0.858-0.923, 0.888-0.944, and 0.912-0.919, respectively. The nomogram based on DL radiomics had high diagnostic efficacy for thyroid nodules, and DL radiomics could assist physicians with different levels of experience to improve their diagnostic level.

Prenatal ultrasound diagnosis and quality control of fetal nuchal translucency.

In clinical ultrasound examinations, it is challenging to perform quality control on the images of each fetal nuchal translucency (NT) and crown-rump length (CRL). However, small measurement differences can increase the probability of false-positive or false-negative diagnosis. Therefore, it is necessary to establish a quality control system for fetal NT examination. This study aims to control the quality of fetal NT and CRL measurements, evaluate the accuracy of ultrasound physicians in early pregnancy NT measurements, and analyze the impact of increased fetal structure screening on the detection rate of chromosomal abnormalities. Data were collected from cases before and after 12 months of NT examination quality control, with 2 214 before quality control and 2 538 cases after quality control. Three quality control data metrics were analyzed: NT multiple of median (NT-MoM), standard deviation (SD) of log10MoM [(SD) log10MoM], and the slope of NT on CRL (SNC). The performance of NT measurements was monitored through the individual CRL NT-MoM within the 0.9-1.1 MoM range of the normal median curve, while grouped based on different years of experience (<3 years, 3-6 years, >6 years), and NT-MoM values among these groups were compared. Data on NT thickening, structural anomalies, and chromosomal abnormalities were retrospectively analyzed during the quality control period. According to the curve equation of the American NTQR project group, the NT-MoM value before quality control was 0.921 7 MoM, the (SD) log10MoM value was 0.091 92, and the SNC value was 12.20%. After quality control, the NT-MoM value was 0.948 3 MoM, the (SD) log10MoM value was 0.094 81, and the SNC value was 11.43%. The comparison of NT-MoM values before and after quality control showed a statistically significant difference (P<0.000 1). The comparison of NT-MoM values measured by ultrasound physicians with different years of experience before and after quality control also showed statistically significant differences (P<0.000 1). The NT-MoM values for the 3-6 years and >6 years groups were higher after quality control (P<0.05), while the <3 years group showed no significant difference before and after quality control (P>0.05). After quality control, cases of NT thickening without significant structural abnormalities accounted for 19.05%, NT thickening with structural abnormalities accounted for 47.62%, and NT normal with structural abnormalities accounted for 33.33%. There were 36 cases of fetal heart abnormalities, accounting for 20.34% of the total abnormality rate, with a positive rate of 36% in chromosome tests. After quality control, ultrasound physicians measure NT more accurately, but differences among measurements remain. Measurements by experienced ultrasound physicians are closer to expected values, usually lower than expected. Monitoring fetal NT and CRL measurements helps improve measurement accuracy. Increasing structural screening during NT examinations, especially for the fetal heart, enhances the detection rate of chromosomal abnormalities.

“Morton’s Neuroma” — Term Etymology: A Review

Background. The urgency of the problem is explained by a high morbidity rate and the need to verify the diagnosis with related specialists (ultrasound physicians, radiologists, trauma surgeons, pathologists), as well as by significant difficulties in patient routing and high probability of primary referral to neurologists, neurosurgeons, and general practitioners. In modern Russian literature, neuromas of all interdigital spaces are identified with Morton’s neuroma.&#x0D; Aim of the review was to determine the accuracy of modern medical terminology, in particular of the term «Morton’s neuroma», to reveal the spectrum of eponyms unacceptable for communication with related specialists and patients, to fill the historical gap and to attract the scientific medical community to discussion on this topic.&#x0D; Methods. We identified 40 articles on this topic published from 1845 to 2022. The search was performed in PubMed/MEDLINE and eLIBRARY databases.&#x0D; Results. Evolution, history, and etymology of several terms used for intermetatarsal neuroma are covered in the study, based on the analysis of literature sources. It has been found that a number of eponyms used to designate neuromas are historically inaccurate. In addition, we have discovered that the reports of «nerve fibrosis» were encountered prior to the introduction of the term «neuroma». However, most authors have popularized the nominal term «Morton’s neuromas».&#x0D; Conclusions. An obvious contradiction between the etiopathogenesis of neuroma and the term itself can be confusing for clinicians and diagnosticians. In our opinion, the disease known nowadays as «Morton’s neuroma» should be named «fibrosis of the plantar nerve of the third toe», and the name terms denoting the number of the corresponding interdigital space should be replaced by the number of the corresponding common plantar digital nerve.

Deep learning based ultrasound analysis facilitates precise distinction between parotid pleomorphic adenoma and Warthin tumor.

Pleomorphic adenoma (PA), often with the benign-like imaging appearances similar to Warthin tumor (WT), however, is a potentially malignant tumor with a high recurrence rate. It is worse that pathological fine-needle aspiration cytology (FNAC) is difficult to distinguish PA and WT for inexperienced pathologists. This study employed deep learning (DL) technology, which effectively utilized ultrasound images, to provide a reliable approach for discriminating PA from WT. 488 surgically confirmed patients, including 266 with PA and 222 with WT, were enrolled in this study. Two experienced ultrasound physicians independently evaluated all images to differentiate between PA and WT. The diagnostic performance of preoperative FNAC was also evaluated. During the DL study, all ultrasound images were randomly divided into training (70%), validation (20%), and test (10%) sets. Furthermore, ultrasound images that could not be diagnosed by FNAC were also randomly allocated to training (60%), validation (20%), and test (20%) sets. Five DL models were developed to classify ultrasound images as PA or WT. The robustness of these models was assessed using five-fold cross-validation. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique was employed to visualize the region of interest in the DL models. In Grad-CAM analysis, the DL models accurately identified the mass as the region of interest. The area under the receiver operating characteristic curve (AUROC) of the two ultrasound physicians were 0.351 and 0.598, and FNAC achieved an AUROC of only 0.721. Meanwhile, for DL models, the AUROC value for discriminating between PA and WT in the test set was from 0.828 to 0.908. ResNet50 demonstrated the optimal performance with an AUROC of 0.908, an accuracy of 0.833, a sensitivity of 0.736, and a specificity of 0.904. In the test set of cases that FNAC failed to provide a diagnosis, DenseNet121 demonstrated the optimal performance with an AUROC of 0.897, an accuracy of 0.806, a sensitivity of 0.789, and a specificity of 0.824. For the discrimination of PA and WT, DL models are superior to ultrasound and FNAC, thereby facilitating surgeons in making informed decisions regarding the most appropriate surgical approach.

A Novel Automatic Algorithm to Support Lung Ultrasound Non-Expert Physicians in Interstitial Pneumonia Evaluation: A Single-Center Study.

Lung ultrasound (LUS) is widely used in clinical practice for identifying interstitial lung diseases (ILDs) and assessing their progression. Although high-resolution computed tomography (HRCT) remains the gold standard for evaluating the severity of ILDs, LUS can be performed as a screening method or as a follow-up tool post-HRCT. Minimum training is needed to better identify typical lesions, and the integration of innovative artificial intelligence (AI) automatic algorithms may enhance diagnostic efficiency. This study aims to assess the effectiveness of a novel AI algorithm in automatic ILD recognition and scoring in comparison to an expert LUS sonographer. The "SensUS Lung" device, equipped with an automatic algorithm, was employed for the automatic recognition of the typical ILD patterns and to calculate an index grading of the interstitial involvement. We selected 33 Caucasian patients in follow-up for ILDs exhibiting typical HRCT patterns (honeycombing, ground glass, fibrosis). An expert physician evaluated all patients with LUS on twelve segments (six per side). Next, blinded to the previous evaluation, an untrained operator, a non-expert in LUS, performed the exam with the SensUS device equipped with the automatic algorithm ("SensUS Lung") using the same protocol. Pulmonary functional tests (PFT) and DLCO were conducted for all patients, categorizing them as having reduced or preserved DLCO. The SensUS device indicated different grades of interstitial involvement named Lung Staging that were scored from 0 (absent) to 4 (peak), which was compared to the Lung Ultrasound Score (LUS score) by dividing it by the number of segments evaluated. Statistical analyses were done with Wilcoxon tests for paired values or Mann-Whitney for unpaired samples, and correlations were performed using Spearman analysis; p < 0.05 was considered significant. Lung Staging was non-inferior to LUS score in identifying the risk of ILDs (median SensUS 1 [0-2] vs. LUS 0.67 [0.25-1.54]; p = 0.84). Furthermore, the grade of interstitial pulmonary involvement detected with the SensUS device is directly related to the LUS score (r = 0.607, p = 0.002). Lung Staging values were inversely correlated with forced expiratory volume at first second (FEV1%, r = -0.40, p = 0.027), forced vital capacity (FVC%, r = -0.39, p = 0.03) and forced expiratory flow (FEF) at 25th percentile (FEF25%, r = -0.39, p = 0.02) while results directly correlated with FEF25-75% (r = 0.45, p = 0.04) and FEF75% (r = 0.43, p = 0.01). Finally, in patients with reduced DLCO, the Lung Staging was significantly higher, overlapping the LUS (reduced median 1 [1-2] vs. preserved 0 [0-1], p = 0.001), and overlapping the LUS (reduced median 18 [4-20] vs. preserved 5.5 [2-9], p = 0.035). Our data suggest that the considered AI automatic algorithm may assist non-expert physicians in LUS, resulting in non-inferior-to-expert LUS despite a tendency to overestimate ILD lesions. Therefore, the AI algorithm has the potential to support physicians, particularly non-expert LUS sonographers, in daily clinical practice to monitor patients with ILDs. The adopted device is user-friendly, offering a fully automatic real-time analysis. However, it needs proper training in basic skills.

Study on the Consistency Between Automatic Measurement Based on Convolutional Neural Network Technology and Manual Visual Evaluation in Intracavitary Ultrasonic Cine of Anterior Pelvic.

This study was to evaluate the application of automatic measurement based on convolutional neural network (CNN) technology in intracavitary ultrasound cine of anterior pelvic. A total of 500 patients who underwent pelvic floor ultrasound examination at Peking University Shenzhen Hospital from July 2021 to February 2022 were retrospectively retrieved by the picture archiving and communication system (PACS) system, and 300 cases were used as a training set. The training set was labeled by three experienced ultrasound physicians to train CNN models and develop an automatic measurement software. The remaining 200 cases were used as a test set. Automatic measurement software identified relevant anatomical structures frame by frame and determined the two frames with the greatest difference, calculated the bladder neck descent (BND), urethral rotation angle (URA), and retrovesical angle (RA). Meanwhile, two experienced ultrasound physicians evaluated the resting frame and the maximum Valsalva frame on the cines by manual visual evaluation, labeled the anatomical structures in the corresponding frame, such as the inferoposterior margin of pubic symphysis, the mid-axis of pubic symphysis, bladder contour, and urethra in the front, and calculated BND, URA, and RA. Considering that the residual urine volume (RUV) in the bladder may affect the results, enrolled patients were grouped according to the RUV (10-50 mL, 50-100 mL, and >100 mL). The consistency of the results by automatic measurement and manual visual evaluation was evaluated using the intraclass correlation coefficient (ICC) and the Bland-Altman graph. Of the 200 cases in the test set, 120 cases were successfully identified by the CNN automatic software with a 60% recognition rate. In the case of successful identification, the ICC of manual visual evaluation measurement and automatic measurement was 0.936 (BND), 0.911 (URA), 0.756 (RA in rest), and 0.877 (RA at maximum Valsalva), respectively. In addition, the RUV had a negligible effect on the consistency. The Bland-Altman plot shows the proportion of samples outside the limit was below 5%. CNN-based automatic measurement software exhibited high reliability in anterior pelvic measurement, which results in a significantly enhanced measurement efficiency.

LSMD: Long-Short Memory-Based Detection Network for Carotid Artery Detection in B-mode Ultrasound Video Streams.

Carotid atherosclerotic plaques are a major complication associated with type II diabetes, and carotid ultrasound is commonly used for diagnosing carotid vascular disease. In primary hospitals, less experienced ultrasound physicians often struggle to consistently capture standard carotid images and identify plaques. To address this issue, we propose a novel approach, the long-short memory-based detection network (LSMD), for carotid artery detection in ultrasound video streams, facilitating the identification and localization of critical anatomical structures and plaques. This approach models short- and long-distance spatiotemporal features through Short-term Temporal Aggregation (STA) and Long-term Temporal Aggregation (LTA) modules, effectively expanding the temporal receptive field with minimal delay and enhancing the detection efficiency of carotid anatomy and plaques. Specifically, we introduce memory buffers with a dynamic updating strategy to ensure extensive temporal receptive field coverage while minimizing memory and computation costs. The proposed model was trained on 80 carotid ultrasound videos and evaluated on 50, with all videos annotated by physicians for carotid anatomies and plaques. The trained LSMD was evaluated for performance on the validation and test sets using the single-frame image-based Single Shot Multi-box Detector (SSD) algorithm as a baseline. The results show that the precision, recall, Average Precision at IoU = 0.50 (AP50), and mean Average Precision (mAP) are 6.83%, 12.29%, 11.23%, and 13.21% higher than the baseline (p < 0.001) respectively, while the model's inference latency reaches 6.97ms on a desktop-level GPU (NVIDIA RTX 3090Ti) and 29.69ms on an edge computing device (Jetson Orin Nano). These findings demonstrate that LSMD can accurately localize carotid anatomy and plaques with real-time inference, indicating its potential for enhancing diagnostic accuracy in clinical practice.

Role of echocardiography in heart failure with preserved ejection fraction

This study aimed to investigate and analyze data regarding the role of echocardiographic examination in assessing the diastolic function of the left ventricle and diagnosing heart failure with preserved ejection fraction (HFpEF).Materials and methods. A search of scientific publications and clinical recommendations was conducted in the PubMed and Google Scholar information-analytical systems for the years 2016–2022, using keywords such as diastolic dysfunction, diastolic stress test, heart failure with preserved ejection fraction, and echocardiography. Additionally, literature lists were analyzed to identify articles meeting the search criteria.Results. A total of 140 articles were analyzed, with 27 of them utilized in composing the review. Eleven additional articles from 2003–2015 were included from literature lists. The search results were organized into article blocks, within which articles were analyzed to study the role of echocardiographic examination in assessing the diastolic function of the left ventricle and diagnosing HFpEF.Conclusion: Echocardiographic examination provides crucial information about the structure and function of the heart and is recommended for all patients with suspected HFpEF. Based on routine assessment of tissue Doppler imaging parameters, ultrasound diagnostic physicians can decide on the need to initiate the diagnostic algorithm for HFpEF using the diastolic stress test method. Results of the diastolic stress test, considering its limitations, should be interpreted in accordance with the clinical scenario or the probability of the presence of HFpEF. A reduction in diastolic reserve (E/e &gt; 15) is a cornerstone for confirming HFpEF. The key task of upcoming clinical trials is to better differentiate various clinical phenotypes of HFpEF, thereby improving the treatment of each specific patient with HFpEF.

Comparative diagnostic accuracy of the IOTA SRR and LR2 scoring systems for discriminating between malignant and Benign Adnexal masses by junior physicians in Chinese patients: a retrospective observational study

BackgroundThe accuracy of ultrasound in distinguishing benign from malignant adnexal masses is highly correlated with the experience of ultrasound physicians. In China, most of ultrasound differentiation is done by junior physicians.PurposeTo compare the diagnostic performance of the International Ovarian Tumour Analysis (IOTA) Simple Rules Risk (SRR) and IOTA Logistic Regression Model 2 (LR2) scoring systems in Chinese patients with adnexal masses.MethodsRetrospective analysis of ovarian cancer tumor patients who underwent surgery at a hospital in China from January 2016 to December 2021. Screening patients with at least one adnexal mass on inclusion and exclusion criteria. Two trained junior physicians evaluated each mass using the two scoring systems. A receiver operating characteristic curve was used to test the diagnostic performance of each system.ResultsA total of 144 adnexal masses were retrospectively collected. Forty masses were histologically diagnosed as malignant. Compared with premenopausal women, postmenopausal women had a much higher rate of malignant masses. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) of the SRR was 97.5% (95% CI: 86.8 -99.9%), 82.7% (95% CI: 74.0 -89.4%), 68.4% (95% CI: 58.7 -76.8%) and 98.9% (95% CI: 92.5 -99.8%). The sensitivity, specificity, PPV, NPV of the LR2 were 90.0% (95% CI: 76.5 -97.2%), 89.4% (95% CI: 81.9 -94.6%), 76.6% (95% CI: 65.0 -85.2%), and 95.9% (95% CI: 90.2 -98.3%). There was good agreement between two scoring systems, with 84.03% total agreement and a kappa value of 0.783 (95% CI: 0.70-0.864). The areas under the curve for predicting malignant tumours using SRR and LR2 were similar for all patients (P > 0.05 ).ConclusionThe two scoring systems can effectively distinguish benign from malignant adnexal masses. Both scoring systems have high diagnostic efficacy, and diagnostic efficacy is stable, which can provide an important reference for clinical decision making.

Myocardial Segmentation Algorithm of U-Net Network Based on Cardiac Ultrasound Images

The myocardial state is always regarded as an important basis for identifying cardiac diseases. In order to assist physicians in diagnosis in an accurate manner, this paper proposes myocardial segmentation using a U-Net network based on cardiac ultrasound images. Firstly, we collected a large amount of clinical data and employed professional cardiac ultrasound imaging physicians to mark the myocardial regions as the gold standard. Then, we built an optimized U-Net network to establish the relationship between images and semantics to extract original image features. Finally, a newly fused loss function for training the network is created. According to the experiments, it shows that the accuracy, precision, and recall rate of U-Net indexes proposed in this paper reaches more than 96%, and MIOU more than 94%, which can effectively assist doctors in diagnosis in an accurate manner.

Clinical Ultrasound Training in Emergency Medicine Advanced Practice Provider Residencies.

Clinical ultrasound training is essential to any emergency medicine (EM) clinician's skill set. We aim to understand the current training patterns of clinical ultrasound training within Advanced Practice Provider (APP) residencies. In a survey sent electronically to 17 active EM APP residencies, data were obtained from 21 responses to questions about structure of ultrasound faculty, quality assessment, feedback, and competency evaluation. We had a response rate of 88%. Of programs surveyed, 93% were associated with EM physician residencies with 87% led by an ultrasound fellowship-trained EM physician. Ninety-three percent of programs required proctored scanning. Sixty percent of programs do not have any required number of scans to graduate. We found that most EM APP residencies share clinical ultrasound faculty, structures, and processes with associated EM physician residencies. We believe that quality training within clinical ultrasound is attainable; however, proficiency guidelines across EM APP residency programs are lacking.

Exploring a Cadaver-Based Model for Teaching Emergency Medicine Residents Ultrasound-Guided Serratus Anterior Plane Blocks.

Background Ultrasound-guided regional anesthesia (USGRA) is increasingly being incorporated into ED clinical practice to provide pain control for a variety of traumatic injuries. The serratus anterior plane block (SAPB) has been shown to be effective at reducing intravenous opioid use and improving pulmonary function for patients with rib fractures, but there is limited prior research about how to safely teach this procedure to emergency medicine (EM) residents. Our goal was to examine the effect of a cadaver-based education model on EM residents' confidence in performing USGRA and provide a review of commonly encountered errors. Methods EM residents participated in a half-day cadaver-based education session that included a variety of less-commonly performed procedures including SAPB and fascia iliaca compartment block (FICB) USGRA. Residents received a didactic lecture and hands-on simulation practice during the month prior to the session. During the session, residents performed a SAPB and FICB on the cadaver patient using the same nerve block kit and ultrasound machine they would use for a living patient, with 1:1 supervision by an emergency ultrasound fellowship-trained physician who provided real-time feedback during the procedure. Representative ultrasound video clips were saved and reviewed. Surveys that were completed by residents after the session were analyzed. Results There were 23 residents who participated, and most had not performed any FICB (74%) or SAPB (87%) previously. The percentage of residents comfortable with general USGRA increased from 8.7% to 91.3% (p<0.001). Comfort with FICB increased from 9.1% to 77.3% (p<0.001), and comfort with SAPB increased from 9.1% to 77.3% (p<0.001). Instructors identified and corrected several common errors, such as overly aggressive needle insertion, instillation of air, and instillation of anesthetic into muscle rather than the fascial plane. Conclusion We found that a cadaver-based education model for teaching EM residents the SAPB and the FICB was associated with significant increases in resident confidence in performing the procedure and facilitated identification and correction of common procedural errors that may otherwise have gone undetected.

Differences between CEUS LI-RADS and CECT LI-RADS in the diagnosis of focal liver lesions in patients at risk for HCC

ObjectivesTo compare the inter-modality consistency and diagnostic performances of the contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) and contrast-enhanced computed tomography (CECT) LI-RADS in patients at risk for hepatocellular carcinoma (HCC), so as to help clinicians to select a more appropriate modality to follow the focal liver lesions (FLLs).MethodsThis retrospective study included untreated 277 FLLs from 247 patients who underwent both CEUS and CECT within 1 month. The ultrasound contrast medium used was SonoVue. FLL categories were independently assigned by two ultrasound physicians and two radiologists using CEUS LI-RADS v2017 and CECT LI-RADS v2018, respectively. The diagnostic performances of CEUS and CECT LI-RADS were evaluated using sensitivity, specificity, positive predictive value (PPV), and negative predictive value. Cohen’s Kappa was employed to evaluate the concordance of the LI-RADS category.ResultsThe inter-modality consistency for CEUS and CECT LI-RADS was 0.31 (p < 0.001). HCC was more frequently observed in CECT LR-3 and LR-4 hepatic lesions than in CEUS (7.3% vs. 19.5%, p < 0.001). The specificity and PPV of CEUS and CECT LR-5 for the diagnosis of HCC were 89.5%, 95.0%, and 82.5%, 94.4%, respectively. The sensitivity of CEUS LR-5 + LR-M for the diagnosis of hepatic malignancies was higher than that of CECT (93.7% vs. 82.7%, p < 0.001). The specificity and PPV of CEUS LR-M for the diagnosis of non-HCC malignancies were lower than those of CECT (59.7% vs. 95.5%, p < 0.001; 23.4% vs. 70.3%, p < 0.001).ConclusionsThe inter-modality consistency between the CEUS and CECT LI-RADS categories is fair. CEUS LI-RADS was more sensitive than CECT LI-RADS in terms of identifying hepatic malignancies, but weaker in terms of separating HCC from non-HCC malignancies.

Development and Evaluation of a Mixed-Reality Tele-ultrasound System.

The objective of this feasibility study was to develop and assess a tele-ultrasound system that would enable an expert sonographer (situated at the remote site) to provide real-time guidance to an operator (situated at the imaging site) using a mixed-reality environment. An architecture along with the operational workflow of the system is designed and a prototype is developed that enables guidance in form of audiovisual cues. The visual cues comprise holograms (of the ultrasound images and ultrasound probe) and is rendered to the operator using a head-mounted display device. The position and orientation of the ultrasound probe's hologram are remotely controlled by the expert sonographer and guide the placement of a physical ultrasound probe at the imaging site. The developed prototype was evaluated for its performance on a network. In addition, a user study (with 12 participants) was conducted to assess the operator's ability to align the probe under different guidance modes. The network performance revealed the view of the imaging site and ultrasound images were transferred to the remote site in 233 ± 42 and 158 ± 38 ms, respectively. The expert sonographer was able to transfer, to the imaging site, data related to position and orientation of the ultrasound probe's hologram in 78 ± 13 ms. The user study indicated that the audiovisual cues are sufficient for an operator to position and orient a physical probe for accurate depiction of the targeted tissue (p < 0.001). The probe's placement translational and rotational errors were 1.4 ± 0.6 mm and 5.4 ± 2.2º. The work illustrates the feasibility of using a mixed-reality environment for effective communication between an expert sonographer (ultrasound physician) and an operator. Further studies are required to determine its applicability in a clinical setting during tele-ultrasound.

Recognition of abnormal changes in echocardiographic videos by an artificial intelligence assisted diagnosis model based on 3D CNN

Objective: To investigate the diagnostic efficiency and clinical application value of an artificial intelligence-assisted diagnosis model based on a three-dimensional convolutional neural network (3D CNN) on echocardiographic videos of patients with hypertensive heart disease, chronic renal failure (CRF) and hypothyroidism with cardiac involvement. Methods: This study is a retrospective study. The patients with hypertensive heart disease, CRF and hypothyroidism with cardiac involvement, who admitted in Henan Provincial People's Hospital from April 2019 to October 2021, were enrolled. Patients were divided into hypertension group, CRF group, and hypothyroidism group. Additionally, a simple random sampling method was used to select control healthy individuals, who underwent physical examination at the same period. The echocardiographic video data of enrolled participants were analyzed. The video data in each group was divided into a training set and an independent testing set in a ratio of 5 to 1. The temporal and spatial characteristics of videos were extracted using an inflated 3D convolutional network (I3D). The artificial intelligence assisted diagnosis model was trained and tested. There was no case overlapped between the training and validation sets. A model was established according to cases or videos based on video data from 3 different views (single apical four chamber (A4C) view, single parasternal left ventricular long-axis (PLAX) view and all views). The statistical analysis of diagnostic performance was completed to calculate sensitivity, specificity and area under the ROC curve (AUC). The time required for the artificial intelligence and ultrasound physicians to process cases was compared. Results: A total of 730 subjects aged (41.9±12.7) years were enrolled, including 362 males (49.6%), and 17 703 videos were collected. There were 212 cases in the hypertensive group, 210 cases in the CRF group, 105 cases in the hypothyroidism group, and 203 cases in the normal control group. The diagnostic performance of the model predicted by cases based on single PLAX view and all views data was excellent: (1) in the hypertensive group, the sensitivity, specificity and AUC of models based on all views data were 97%, 89% and 0.93, respectively, while those of models based on a single PLAX view were 94%, 95%, and 0.94, respectively; (2) in the CRF group, the sensitivity, specificity and AUC of models based on all views data were 97%, 95% and 0.96, respectively, while those of models based on a single PLAX view were 97%, 89%, and 0.93, respectively; (3) in the hypothyroidism group, the sensitivity, specificity and AUC of models based on all views data were 64%, 100% and 0.82, respectively, while those of models based on a single PLAX view were 82%, 89%, and 0.86, respectively. The time required for the 3D CNN model to measure and analyze the echocardiographic videos of each subject was significantly shorter than that for the ultrasound physicians ((23.96±6.65)s vs. (958.25±266.17)s, P<0.001). Conclusions: The artificial intelligence assisted diagnosis model based on 3D CNN can extract the dynamic temporal and spatial characteristics of echocardiographic videos jointly, and quickly and efficiently identify hypertensive heart disease and cardiac changes caused by CRF and hypothyroidism.

Comparison of Commonly Carried Liquids Against Commercial Ultrasound Gel for Use in the Backcountry Setting.

Point-of-care ultrasound (POCUS) is utilized in austere environments because it is lightweight, durable, battery powered, and portable. In austere settings, weight and space constraints are limitations to carrying dedicated ultrasound gel. Few studies have assessed commonly carried liquids as gel alternatives. The study objective was to assess the suitability of common food and personal care products as ultrasound coupling agents compared with that of commercial gel. A noninferiority study compared 9 products to commercial gel. Each substance was independently tested on 2 subjects by 2 sonographers covering 8 standardized ultrasound windows. Clips were recorded, blinded, and independently graded by 2 ultrasound fellowship-trained physicians on the ability to make clinical decisions and technical details, including contrast, resolution, and artifact. A 20% noninferiority margin was set, which correlates to levels considered to be of reliably sufficient quality by American College of Emergency Physicians' guidelines. The substances included water, soap, shampoo, olive oil, energy gel, maple syrup, hand sanitizer, sunscreen, and lotion. A total of 300 of 318 (94%) clips met the primary endpoint of adequacy to make a clinical decision. All media, except sunscreen, were noninferior to commercial gel in the ability to make a clinical decision (α=0.05). In terms of secondary outcomes, resolution, artifact, and contrast, all substances were noninferior to commercial gel (α=0.05). The sonographers concluded that all gel alternatives' usability performed similarly to commercial gel, with the exception of energy gel. Of the 9 substances tested, 8 were noninferior to commercial gels for clinical decisions. Our study indicates that several POCUS gel substitutes are serviceable to produce clinically adequate images.

Differentiation between Phyllodes Tumors and Fibroadenomas through Breast Ultrasound: Deep-Learning Model Outperforms Ultrasound Physicians.

The preoperative differentiation of breast phyllodes tumors (PTs) from fibroadenomas (FAs) plays a critical role in identifying an appropriate surgical treatment. Although several imaging modalities are available, reliable differentiation between PT and FA remains a great challenge for radiologists in clinical work. Artificial intelligence (AI)-assisted diagnosis has shown promise in distinguishing PT from FA. However, a very small sample size was adopted in previous studies. In this work, we retrospectively enrolled 656 breast tumors (372 FAs and 284 PTs) with 1945 ultrasound images in total. Two experienced ultrasound physicians independently evaluated the ultrasound images. Meanwhile, three deep-learning models (i.e., ResNet, VGG, and GoogLeNet) were applied to classify FAs and PTs. The robustness of the models was evaluated by fivefold cross validation. The performance of each model was assessed by using the receiver operating characteristic (ROC) curve. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were also calculated. Among the three models, the ResNet model yielded the highest AUC value, of 0.91, with an accuracy value of 95.3%, a sensitivity value of 96.2%, and a specificity value of 94.7% in the testing data set. In contrast, the two physicians yielded an average AUC value of 0.69, an accuracy value of 70.7%, a sensitivity value of 54.4%, and a specificity value of 53.2%. Our findings indicate that the diagnostic performance of deep learning is better than that of physicians in the distinction of PTs from FAs. This further suggests that AI is a valuable tool for aiding clinical diagnosis, thereby advancing precision therapy.

Learning curve in ultrasound-guided vacuum-assisted excision of breast lesions for surgeons and ultrasound physicians.

The varying experience of surgeons and ultrasound physicians, and their collaboration with physicians, may affect operation time and efficiency. We evaluated the learning curve of ultrasound-guided vacuum-assisted excision (VAE) of breast lesion with collaboration between different physicians, and assessed characteristics associated with operation time. The sample population of this retrospective study was divided into two groups: 49 consecutive patient surgeries completed by skilled surgeons and novice ultrasound physicians (U group); and 30 consecutive patient surgeries completed by skilled ultrasound physicians and novice surgeons (S group). Cumulative summation graphs were used to evaluate operation time and calculate the turning point of the learning curve. Patients in the U and S groups were divided into exploration stage and proficiency stage according to the turning point, and the differences in influencing factors were compared. A total of 548 patients who underwent vacuum-assisted breast excision performed by a combination of skilled surgeons and skilled ultrasound physicians were selected as the reference group (R group). The differences among the three groups were compared. The relationship between the operation time and other factors in the different groups was analyzed using linear regression. The best learning curve of the sample population was the quadratic fitting equation, and the turning point was the 19th case in the U group and the 14th case in the S group. The total operation times in the proficiency stage were significantly shorter than those in the exploration stage in the U and S groups (P=0.012 and P=0.003, separately). Patient age, long diameter, short diameter, and depth of masses related to the operation time. Our data suggest the existence of different learning curves in ultrasound-guided vacuum-assisted excision for the collaborations of different stages surgeons and ultrasound physicians. Through the accumulation of experience, it is feasible to safely perform ultrasound-guided VAE of breast lesions.

Ultrasound image-based deep learning to differentiate tubal-ovarian abscess from ovarian endometriosis cyst.

Objectives: We developed ultrasound (US) image-based convolutional neural networks (CNNs) to distinguish between tubal-ovarian abscess (TOA) and ovarian endometriosis cyst (OEC). Methods: A total of 202 patients who underwent US scanning and confirmed tubal-ovarian abscess or ovarian endometriosis cyst by pathology were enrolled in retrospective research, in which 171 patients (from January 2014 to September 2021) were considered the primary cohort (training, validation, and internal test sets) and 31 patients (from September 2021 to December 2021) were considered the independent test cohort. There were 68 tubal-ovarian abscesses and 89 OEC, 4 TOA and 10 OEC, and 10 TOA and 21 OEC patients belonging to training and validation sets, internal sets, and independent test sets, respectively. For the model to gain better generalization, we applied the geometric image and color transformations to augment the dataset, including center crop, random rotation, and random horizontal flip. Three convolutional neural networks, namely, ResNet-152, DenseNet-161, and EfficientNet-B7 were applied to differentiate tubal-ovarian abscess from ovarian endometriosis cyst, and their performance was compared with three US physicians and a clinical indicator of carbohydrate antigen 125 (CA125) on the independent test set. The area under the receiver operating characteristic curves (AUROCs) of accuracy, sensitivity, and specificity were used to evaluate the performance. Results: Among the three convolutional neural networks, the performance of ResNet-152 was the highest, with AUROCs of 0.986 (0.954-1). The AUROCs of the three physicians were 0.781 (0.620-0.942), 0.738 (0.629-848), and 0.683 (0.501-0.865), respectively. The clinical indicator CA125 achieved only 0.564 (0.315-0.813). Conclusion: We demonstrated that the CNN model based on the US image could discriminate tubal-ovarian abscess and ovarian endometriosis cyst better than US physicians and CA125. This method can provide a valuable predictive reference for physicians to screen tubal-ovarian abscesses and ovarian endometriosis cysts in time.