Senior Sonographer Research Articles

Few-shot learning to identify atypical endometrial hyperplasia and endometrial cancer based on transvaginal ultrasonic images

ObjectiveIt is challenging to accurately distinguish atypical endometrial hyperplasia (AEH) and endometrial cancer (EC) under routine transvaginal ultrasonic (TVU) detection. Our research aims to use the few-shot learning (FSL) method to identify non-atypical endometrial hyperplasia (NAEH), AEH, and EC based on limited TVU images. MethodsThe TVU images of pathologically confirmed NAEH, AEH, and EC patients (n = 33 per class) were split into the support set (SS, n = 3 per class) and the query set (QS, n = 30 per class). Next, we used dual pretrained ResNet50 V2 which pretrained on ImageNet first and then on extra collected TVU images to extract 1*64 eigenvectors from the TVU images in SS and QS. Then, the Euclidean distances were calculated between each TVU image in QS and nine TVU images of SS. Finally, the k-nearest neighbor (KNN) algorithm was used to diagnose the TVU images in QS. ResultsThe overall accuracy and macro precision of the proposed FSL model in QS were 0.878 and 0.882 respectively, superior to the automated machine learning models, traditional ResNet50 V2 model, junior sonographer, and senior sonographer. When identifying EC, the proposed FSL model achieved the highest precision of 0.964, the highest recall of 0.900, and the highest F1-score of 0.931. ConclusionsThe proposed FSL model combining dual pretrained ResNet50 V2 eigenvectors extractor and KNN classifier presented well in identifying NAEH, AEH, and EC patients with limited TVU images, showing potential in the application of computer-aided disease diagnosis.

A Video-based Automated Tracking and Analysis System of Plaque Burden in Carotid Artery Using Deep Learning: A Comparison with Senior Sonographers.

The incidence of stroke is rising, and it is the second major cause of mortality and the third leading cause of disability around the globe. The goal of this study was to rapidly and accurately identify carotid plaques and automatically quantify plaque burden using our automated tracking and segmentation US-video system. We collected 88 common carotid artery transection videos (11048 frames) with a history of atherosclerosis or risk factors for atherosclerosis, which were randomly divided into training, test, and validation sets using a 6:3:1 ratio. We first trained different segmentation models to segment the carotid intima and adventitia, and calculate the maximum plaque burden automatically. Finally, we statistically analyzed the plaque burden calculated automatically by the best model and the results of manual labeling by senior sonographers. Of the three Artificial Intelligence (AI) models, the Robust Video Matting (RVM) segmentation model's carotid intima and adventitia Dice Coefficients (DC) were the highest, reaching 0.93 and 0.95, respectively. Moreover, the RVM model has shown the strongest correlation coefficient (0.61±0.28) with senior sonographers, and the diagnostic effectiveness between the RVM model and experts was comparable with paired-t test and Bland-Altman analysis [P= 0.632 and ICC 0.01 (95% CI: -0.24~0.27), respectively]. Our findings have indicated that the RVM model can be used in ultrasound carotid video. The RVM model can automatically segment and quantify atherosclerotic plaque burden at the same diagnostic level as senior sonographers. The application of AI to carotid videos offers more precise and effective methods to evaluate carotid atherosclerosis in clinical practice.

Benign Brenner tumor of the ovary: two-dimensional and contrast-enhanced ultrasound features-a retrospective study from a single center.

Benign Brenner tumor (BBT) is a rare ovarian tumor, and there are few discrete reports about its manifestation in an ultrasound. This study sought to investigate the two-dimensional (2D) and contrast-enhanced ultrasound (CEUS) features of this entity. This is a retrospective single-center study. The clinical manifestations, laboratory examination, and ultrasound data of 25 female patients with BBT were confirmed by pathology when they underwent 2D and/or CEUS examination at Ningbo First Hospital from January 2012 to June 2023. The ultrasound findings of the patients were analyzed using the terminology of the International Organization for the Analysis of Ovarian Tumor and were read by two senior sonographers who reached an agreement. Among the all 25 patients, most of them were unilateral, and only one patient was bilateral. Thus, 26 lesions were found: 44.0% (11/25) were in the left and 52.0% (13/25) were in the right. Moreover, 53.84% (14/26) were solid lesions, 15.38% (4/26) were mixed lesions, and 26.92% (7/26) were cystic lesions. Among the solid-type patients, 42.85% (6/14) of the cases were with calcification. Upon laboratory examination, 12.0% (3/25) of the patients had high carbohydrate antigen 125 (CA-125) level, and 19.04% (4/21) of the patients had an elevated carbohydrate antigen724 (CA-724) level in the serum tumor markers. In the hormone test, 14.28% (3/21) were found to have a high postmenopausal estrogen level and 14.28%(3/21) were found to have a high level of follicle-stimulating hormone (FSH). One patient with complex manifestations and three with solid manifestations were examined by CEUS to observe the microcirculation perfusion of the tumor. One with solid and cystic separation was rapidly hyperenhanced and cleared, and the filling subsided faster than the uterus. The postoperative pathological diagnosis was benign Brenner tumor with mucinous cystadenoma. The other three cases were solid adnexal lesions, which showed isoenhancement on CEUS and disappeared slowly, synchronizing with the uterus. The CEUS results were considered as benign tumors and confirmed by pathology. BBT can show ovarian cystic, mixed cystic and solid type, and solid echo in 2D ultrasound. Unilateral ovarian fibrosis with punctate calcification is an important feature of BBT in 2D ultrasound. However, for solid adnexal masses and mixed cystic and solid masses with unclear diagnosis, if CEUS shows isoenhancement or hyperenhancement, the possibility of BBT cannot be excluded.

A deep-learning pipeline to diagnose pediatric intussusception and assess severity during ultrasound scanning: a multicenter retrospective-prospective study

Ileocolic intussusception is one of the common acute abdomens in children and is first diagnosed urgently using ultrasound. Manual diagnosis requires extensive experience and skill, and identifying surgical indications in assessing the disease severity is more challenging. We aimed to develop a real-time lesion visualization deep-learning pipeline to solve this problem. This multicenter retrospective-prospective study used 14,085 images in 8736 consecutive patients (median age, eight months) with ileocolic intussusception who underwent ultrasound at six hospitals to train, validate, and test the deep-learning pipeline. Subsequently, the algorithm was validated in an internal image test set and an external video dataset. Furthermore, the performances of junior, intermediate, senior, and junior sonographers with AI-assistance were prospectively compared in 242 volunteers using the DeLong test. This tool recognized 1,086 images with three ileocolic intussusception signs with an average of the area under the receiver operating characteristic curve (average-AUC) of 0.972. It diagnosed 184 patients with no intussusception, nonsurgical intussusception, and surgical intussusception in 184 ultrasound videos with an average-AUC of 0.956. In the prospective pilot study using 242 volunteers, junior sonographers’ performances were significantly improved with AI-assistance (average-AUC: 0.966 vs. 0.857, P < 0.001; median scanning-time: 9.46 min vs. 3.66 min, P < 0.001), which were comparable to those of senior sonographers (average-AUC: 0.966 vs. 0.973, P = 0.600). Thus, here, we report that the deep-learning pipeline that guides lesions in real-time and is interpretable during ultrasound scanning could assist sonographers in improving the accuracy and efficiency of diagnosing intussusception and identifying surgical indications.

Water immersion ultrasound can improve the repeatability of ultrasonic measurement of dorsalis pedis artery diameter and hemodynamic parameters.

In comparing the repeatability of the internal diameter and hemodynamic parameters of the dorsalis pedis artery measured by immersion ultrasound and contact ultrasound, the factors affecting the accuracy and repeatability of measurement were analyzed. This study aimed to provide a better method for ultrasound evaluation of the dorsalis pedis artery before flap transplantation. Two senior sonographers measured the diameter of the dorsalis pedis artery (D) of 56 healthy volunteers, measuring at the same location and at different time points using water immersion and contact ultrasound. Color Doppler ultrasound was used to measure the hemodynamics of the dorsalis pedis artery, including peak systolic velocity (PSV), end diastolic velocity (EDV), and resistance index (RI). The interclass correlation coefficient (ICC) was used to evaluate the intraobserver and interobserver repeatability for each group's measurements. The intraobserver and interobserver reproducibility of D, PSV, EDV, and RI measurements by water immersion ultrasound was very good. The intraobserver and interobserver reproducibility of the contact ultrasound measurements of D, PSV, EDV, and RI was good. The repeatability of water immersion ultrasound is better than that of contact ultrasound in the measurement of the dorsalis pedis artery. Water immersion ultrasound can improve the near-field resolution of superficial tissues and increase the display of the lengths of blood vessels in images, thereby suggesting its superiority in ultrasound examination of dorsalis pedis arteries.

Combining deep learning and intelligent biometry to extract ultrasound standard planes and assess early gestational weeks.

To develop and validate a fully automated AI system to extract standard planes, assess early gestational weeks, and compare the performance of the developed system to sonographers. In this three-center retrospective study, 214 consecutive pregnant women that underwent transvaginal ultrasounds between January and December 2018 were selected. Their ultrasound videos were automatically split into 38,941 frames using a particular program. First, an optimal deep-learning classifier was selected to extract the standard planes with key anatomical structures from the ultrasound frames. Second, an optimal segmentation model was selected to outline gestational sacs. Third, novel biometry was used to measure, select the largest gestational sac in the same video, and assess gestational weeks automatically. Finally, an independent test set was used to compare the performance of the system with that of sonographers. The outcomes were analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and mean similarity between two samples (mDice). The standard planes were extracted with an AUC of 0.975, a sensitivity of 0.961, and a specificity of 0.979. The gestational sacs' contours were segmented with a mDice of 0.974 (error less than 2 pixels). The comparison showed that the relative error of the tool in assessing gestational weeks was 12.44% and 6.92% lower and faster (min, 0.17 vs. 16.6 and 12.63) than that of the intermediate and senior sonographers, respectively. This proposed end-to-end tool allows automatic assessment of gestational weeks in early pregnancy and may reduce manual analysis time and measurement errors. The fully automated tool achieved high accuracy showing its potential to optimize the increasingly scarce resources of sonographers. Explainable predictions can assist in their confidence in assessing gestational weeks and provide a reliable basis for managing early pregnancy cases. • The end-to-end pipeline enabled automatic identification of the standard plane containing the gestational sac in an ultrasound video, as well as segmentation of the sac contour, automatic multi-angle measurements, and the selection of the sac with the largest mean internal diameter to calculate the early gestational week. • This fully automated tool combining deep learning and intelligent biometry may assist the sonographer in assessing the early gestational week, increasing accuracy and reducing the analyzing time, thereby reducing observer dependence.

Locating Multiple Standard Planes in First-Trimester Ultrasound Videos via the Detection and Scoring of Key Anatomical Structures

This study was aimed at developing a first-trimester standard plane detection (FTSPD) system that can automatically locate nine standard planes in ultrasound videos and investigating its utility in clinical practice. The FTSPD system, based on the YOLOv3 network, was developed to detect structures and evaluate the quality of plane images by using a pre-defined scoring system. A total of 220 videos from two different ultrasound scanners were collected to compare detection performance between our FTSPD system and sonographers with different levels of experience. The quality of the detected standard planes was quantitatively rated by an expert according to a scoring protocol. Kolmogorov-Smirnov analysis was used to compare the distributions of scores across all nine standard planes. The expert-rated scores indicated that the quality of the standard planes detected by the FTSPD system was on par with that of the planes detected by senior sonographers. There were no significant differences in the distributions of the scores across all nine standard planes. The FTSPD system performed significantly better than junior sonographers in five standard plane types. The results of this study suggest that our FTSPD system has significant potential for detecting standard planes in first-trimester ultrasound screening, which may help to improve the accuracy of fetal ultrasound screening and facilitate early diagnosis of abnormalities. The quality of the standard planes selected by junior sonographers can be significantly improved with the assistance of our FTSPD system.

HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images.

Ultrasonography is an important routine examination for breast cancer diagnosis, due to its non-invasive, radiation-free and low-cost properties. However, the diagnostic accuracy of breast cancer is still limited due to its inherent limitations. Then, a precise diagnose using breast ultrasound (BUS) image would be significant useful. Many learning-based computer-aided diagnostic methods have been proposed to achieve breast cancer diagnosis/lesion classification. However, most of them require a pre-define region of interest (ROI) and then classify the lesion inside the ROI. Conventional classification backbones, such as VGG16 and ResNet50, can achieve promising classification results with no ROI requirement. But these models lack interpretability, thus restricting their use in clinical practice. In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations.We leverage the anatomical prior knowledge that malignant and benign tumors have different spatial relationships between different tissue layers, and propose a HoVer-Transformer to formulate this prior knowledge. The proposed HoVer-Trans block extracts the inter- and intra-layer spatial information horizontally and vertically. We conduct and release an open dataset GDPH&SYSUCC for breast cancer diagnosis in BUS. The proposed model is evaluated in three datasets by comparing with four CNN-based models and three vision transformer models via five-fold cross validation. It achieves state-of-the-art classification performance (GDPH&SYSUCC AUC: 0.924, ACC: 0.893, Spec: 0.836, Sens: 0.926) with the best model interpretability. In the meanwhile, our proposed model outperforms two senior sonographers on the breast cancer diagnosis when only one BUS image is given (GDPH&SYSUCC-AUC ours: 0.924 vs. reader1: 0.825 vs. reader2: 0.820).

The Two-Stage Ensemble Learning Model Based on Aggregated Facial Features in Screening for Fetal Genetic Diseases.

With the advancement of medicine, more and more researchers have turned their attention to the study of fetal genetic diseases in recent years. However, it is still a challenge to detect genetic diseases in the fetus, especially in an area lacking access to healthcare. The existing research primarily focuses on using teenagers' or adults' face information to screen for genetic diseases, but there are no relevant directions on disease detection using fetal facial information. To fill the vacancy, we designed a two-stage ensemble learning model based on sonography, Fgds-EL, to identify genetic diseases with 932 images. Concretely speaking, we use aggregated information of facial regions to detect anomalies, such as the jaw, frontal bone, and nasal bone areas. Our experiments show that our model yields a sensitivity of 0.92 and a specificity of 0.97 in the test set, on par with the senior sonographer, and outperforming other popular deep learning algorithms. Moreover, our model has the potential to be an effective noninvasive screening tool for the early screening of genetic diseases in the fetus.

Is accuracy of estimated fetal weight improved by better image quality scores?

To assess in a group of ultrasound operators of various levels of experience the predictive value of systematic quality scoring to assess estimated fetal weight (EFW) validity. Screenshots, sonographer experience, and neonate birth weight were collected for 131 ultrasound examinations in the 7 days before birth. The difference (EFW error) between projected birth weight (EFW + [30 g × interval in days to birth]) and actual birth weight was then assessed (absolute value). Three senior sonographers rated all the screenshots (International Society of Ultrasound in Obstetrics and Gynecology 16-point score for image quality) and interobserver reproducibility was assessed concomitantly. The impact of the score on EFW accuracy was then assessed (univariate analysis). Receiver operating characteristic curves allowed us to assess the score's positive predictive value (PPV) for accurate EFW. Mean birth weight was 2998 ± 954 g and mean EFW error was 8.6% ± 7.1%. Both the sonographer's experience and score significantly impacted the EFW error (P< 0.05). The PPVs of systematic image scores for identifying an EFW error greater than 10% and greater than 15% were appropriate for clinical use (areas under the curve 0.61 and 0.70, respectively). Score reproducibility was modest. Low image scores and limited ultrasound expertise are associated with an increased risk of inaccurate EFW.

Deep learning based on ultrasound to differentiate pathologically proven atypical and typical medullary thyroid carcinoma from follicular thyroid adenoma

ObjectivesTo investigate the feasibility and value of deep learning based on grayscale ultrasonography in the differentiation of pathologically proven atypical and typical medullary thyroid carcinoma (MTC) from follicular thyroid adenoma (FTA). MethodsThe preoperative 770 ultrasound images consisted of 354 MTCs (66% were typical MTCs with a high suspicion sonographic pattern, 34% were atypical MTCs with a suspicion pattern of intermediate or less) and 416 FTAs. All images were delineated manually by a senior sonographer to achieve the regions of interest. Two deep neural networks of ResNet-34 and ResNet-18 were performed on the training set (n = 690). The test data set (n = 80) was subsequently evaluated by the two models and two sonographers, their diagnostic performances and misdiagnosis lesions were compared and analyzed. ResultsThe ResNet-34 model shows higher diagnostic ability than the junior sonographer with an area under the receiver operating curve of 0.992 (95% CI: 0.840–0.970)versus 0.754 (95% CI:0.645–0.843). Moreover, 12 of 16 atypical MTCs were successfully identified by the ResNet-34, which is significantly better than the senior and junior sonographer, suggesting that these patients could benefit from timely serological examination and surgical strategy at an earlier stage. ConclusionDeep learning to differentiate MTC from FTA on grayscale ultrasound may be a useful diagnostic support tool, especially in atypical MTC and FTA. Moreover, the computing time of deep learning is short, which will help to incorporate it into real-time ultrasound diagnosis.

Differentiating non-lactating mastitis and malignant breast tumors by deep-learning based AI automatic classification system: A preliminary study.

ObjectiveTo explore the application values of deep-learning based artificial intelligence (AI) automatic classification system, on the differential diagnosis of non-lactating mastitis (NLM) and malignant breast tumors, via its comparation with traditional ultrasound interpretations and the following interpretation conclusions made by the sonographers with various seniorities.MethodsA total of 707 patients suffering from breast lesions (475 malignant breast tumors and 232 NLM), were selected from the following three medical centers, including Zhejiang Cancer Hospital, Hebei Province Hospital of Traditional Chinese Medicine, and Yantai Affiliated Hospital of Binzhou Medical University, and the time period was set from April 2020 to September 2021. All selected cases firstly accepted the routine breast ultrasound diagnosis, followed by the interpretations from a senior sonographer with more than 15 years of work experience, and an intermediate-aged sonographer with more than 5 years of work experience, independently. Meanwhile, a third physician also interpreted the same ultrasound images by deep learning–based AI automatic classification system, independent of the interpretation results from the previous two physicians. The kappa test was performed to evaluate the consistency between the conventional ultrasound interpretation results and pathological results interpreted from physicians with different working experiences.ResultsIn total, 475 cases of malignant breast tumors (512 nodules) and 232 cases of NLM (255 nodules) were pathologically diagnosed. The accuracy, sensitivity, and specificity of conventional ultrasound interpretations vary from different sonographers with different working experiences. The accuracy, sensitivity, and specificity for intermediate-aged sonographers and senior sonographers were 76.92% (590/767), 84.71% (216/255), and 73.95% (374/512) and 87.35% (670/767), 86.27% (220/255), and 87.89% (450/512), respectively (P<0.001). In contrast, if the threshold was set as 0.5, the accuracy, sensitivity, and specificity from deep learning–based AI automatic classification system were 83.00%, 87.20%, and 85.33%, separately, and the area under the curve was 92.6. The results of the kappa consistency test indicated that the diagnosis results from the image interpretations by senior physicians and deep-learning based AI automatic classification system showed high consistency with postoperative pathological diagnosis results, and the kappa values are 0.72 and 0.71, respectively, with the P-value of less than 0.001. In contrast, the consistency between the image interpretation results from intermediate-aged physicians with less working experience, and postoperative pathological diagnosis results, seemed to be relatively lower, with a kappa value of only 0.53 and P-value of less than 0.001.ConclusionsThe deep learning–based AI automatic classification system is expected to become a reliable auxiliary way to distinguish NLM and malignant breast tumors due to its high sensitivity, accuracy, and specificity.

Clinical Value of Contrast-Enhanced Ultrasound in Breast Cancer Diagnosis.

Breast cancer (BC) ranks first in morbidity and mortality among female malignant tumors worldwide. This study is aimed at clarifying clinical value of contrast-enhanced ultrasound (CEUS) in the diagnosis and differentiation of BC. A total of 108 BC patients admitted to our hospital from January 2019 to December 2021 were enrolled. All patients underwent conventional color Doppler ultrasound and CEUS imaging examination. All ultrasound images were analyzed by a senior (5+ years) sonographer. The lesion location, echo, size, and color Doppler flow imaging (CDFI) blood flow distribution of benign and malignant BC were assessed. The transverse and longitudinal diameters of malignant BC presented significant elevation compared with the control group (P < 0.05). CEUS is more reliable than conventional ultrasound in the differentiation of benign and malignant breast lesions, and CEUS has the best reliability. The comparison of CEUS observation indicators between benign and malignant groups demonstrated that CEUS enhancement patterns (time and intensity) and morphological features (lesion boundary, shape, range, homogeneity, and filling defect) presented statistical significance (P < 0.01). Irregular shape and range expansion were high-specificity indicators (all >90.00%); fast-forward, high enhancement, clear boundary, and range expansion were high-sensitivity (all >90.00%); and fast-forward, high enhancement, and clear boundary were low-specificity indicators (all <50.00%); moderate sensitivity is as follows: homogeneous enhancement and range expansion (all >80.00%). The area under curve of CEUS (0.735 ± 0.053) presented elevation relative to conventional ultrasound (0.901 ± 0.024), with statistical significance (Z1 = 2.462, P < 0.05). Relative to conventional ultrasound, the specificity and positive predictive value of CEUS presented elevation (P < 0.05). In conclusion, in the differentiation of benign and malignant breast lesions, CEUS has better diagnostic accuracy and reliability than conventional ultrasound. The diagnostic advantages of CEUS are to elevate the diagnostic specificity and positive predictive value and reduce the misdiagnosis rate.

Unbowed, unbent, unbroken: predicting pulmonary hypertension using echocardiography

During the first meeting of the World Health Organization (WHO) in 1973, pulmonary hypertension (PH) was defined as mean pulmonary artery pressure (mPAP) ≥25 mmHg measured by right heart catheterisation [1]. This criterion was chosen arbitrarily and was founded on the premise that mPAP at rest in a supine position does not exceed 15 mmHg 2]. In 2009, the landmark paper of Kovacs et al . [3] provided scientific evidence for this statement and showed that normal mPAP at rest was 14 mmHg, with an upper limit of normal of 20 mmHg. In addition, accumulating data has indicated that patients with mPAP ≥19 mmHg but below the haemodynamic threshold of 25 mmHg are at increased mortality risk [4–6]. The probability of pulmonary hypertension can accurately be estimated by current echocardiographic criteria <https://bit.ly/3KMCWQ2> We thank Linda Grutterink, senior sonographer at the Department of Cardiology, Amsterdam UMC, Amsterdam, the Netherlands, for the contribution of the echocardiographic images.

Training in Obstetric Ultrasound Biometry

To assess the intra- and interobserver reproducibility of fetal biometry measurements obtained by trainee (junior) and experienced sonographers (senior) in the contest of two training programs in obstetric ultrasound. This was a prospective study on 192 women recruited ensuring an even distribution throughout gestation (18-41 weeks), at University College London Hospital (UCLH), England (87 cases), and at Maternité Regionale Universitaire de Nancy (MRUN), France (105 cases). The training took place in two training centers with experience in ultrasound training and subspecialist training in fetal medicine. Measurements for head circumference (HC), abdominal circumference (AC), and femur length (FL) were obtained twice by junior and senior sonographers, blind to their own and each other's measurements. Differences between and within sonographers were expressed in millimeters and as a percentage of fetal dimensions. Reproducibility was assessed using Bland-Altman plots. Reproducibility was overall high with 95% confidence intervals (CI) within <6% for intraobserver and <8% for interobserver reproducibility. Intraobserver reproducibility was lower within junior than within senior sonographers' measurements for HC (95% CI: <4% versus <3%) and FL (95% CI: <6% and < 5%). Intraobserver reproducibility was similar between the two centers/training programs (AC 95% CI: <6%). Cumulative interobserver reproducibility in both centers was similar to the reproducibility within a single site (95% CI: <5%, <8%, and <7% for HC, AC, and FL, respectively). Reproducibility of fetal biometry measurement was high in centers with structured training programs regardless of sonographers' experience. Reproducibility was higher in sonographers who completed the training.

Deep learning-based pelvic levator hiatus segmentation from ultrasound images

PurposeTo automatically segment and measure the levator hiatus with a deep learning approach and evaluate the performance between algorithms, sonographers, and different devices. MethodsThree deep learning models (UNet-ResNet34, HR-Net, and SegNet) were trained with 360 images and validated with 42 images. The trained models were tested with two test sets. The first set included 138 images to evaluate the performance between the algorithms and sonographers. An independent dataset including 679 images assessed the performances of algorithms between different ultrasound devices. Four metrics were used for evaluation: DSC, HDD, the relative error of segmentation area, and the absolute error of segmentation area. ResultsThe UNet model outperformed HR-Net and SegNet. It could achieve a mean DSC of 0.964 for the first test set and 0.952 for the independent test set. UNet was creditable compared with three senior sonographers with a noninferiority test in the first test set and equivalent in the two test sets collected by different devices. On average, it took two seconds to process one case with a GPU and 2.4 s with a CPU. ConclusionsThe deep learning approach has good performance for levator hiatus segmentation and good generalization ability on independent test sets. This automatic levator hiatus segmentation approach could help shorten the clinical examination time and improve consistency.

A novel PDX modeling strategy and its application in metabolomics study for malignant pleural mesothelioma

BackgroundMalignant pleural mesothelioma (MPM) is a rare and aggressive carcinoma located in pleural cavity. Due to lack of effective diagnostic biomarkers and therapeutic targets in MPM, the prognosis is extremely poor. Because of difficulties in sample extraction, and the high rate of misdiagnosis, MPM is rarely studied. Therefore, novel modeling methodology is crucially needed to facilitate MPM research.MethodsA novel patient-derived xenograft (PDX) modeling strategy was designed, which included preliminary screening of patients with pleural thickening using computerized tomography (CT) scan, further reviewing history of disease and imaging by a senior sonographer as well as histopathological analysis by a senior pathologist, and PDX model construction using ultrasound-guided pleural biopsy from MPM patients. Gas chromatography-mass spectrometry-based metabolomics was further utilized for investigating circulating metabolic features of the PDX models. Univariate and multivariate analysis, and pathway analysis were performed to explore the differential metabolites, enriched metabolism pathways and potential metabolic targets.ResultsAfter screening using our strategy, 5 out of 116 patients were confirmed to be MPM, and their specimens were used for modeling. Two PDX models were established successfully. Metabolomics analysis revealed significant metabolic shifts in PDX models, such as dysregulations in amino acid metabolism, TCA cycle and glycolysis, and nucleotide metabolism.ConclusionsTo sum up, we suggested a novel modeling strategy that may facilitate specimen availability for MM research, and by applying metabolomics in this model, several metabolic features were identified, whereas future studies with large sample size are needed.

Diagnosis of Ovarian Neoplasms Using Nomogram in Combination With Ultrasound Image-Based Radiomics Signature and Clinical Factors.

Objectives: To establish and validate a nomogram integrating radiomics signatures from ultrasound and clinical factors to discriminate between benign, borderline, and malignant serous ovarian tumors. Materials and methods: In this study, a total of 279 pathology-confirmed serous ovarian tumors collected from 265 patients between March 2013 and December 2016 were used. The training cohort was generated by randomly selecting 70% of each of the three types (benign, borderline, and malignant) of tumors, while the remaining 30% was included in the validation cohort. From the transabdominal ultrasound scanning of ovarian tumors, the radiomics features were extracted, and a score was calculated. The ability of radiomics to differentiate between the grades of ovarian tumors was tested by comparing benign vs borderline and malignant (task 1) and borderline vs malignant (task 2). These results were compared with the diagnostic performance and subjective assessment by junior and senior sonographers. Finally, a clinical-feature alone model and a combined clinical-radiomics (CCR) model were built using predictive nomograms for the two tasks. Receiver operating characteristic (ROC) analysis, calibration curve, and decision curve analysis (DCA) were performed to evaluate the model performance. Results: The US-based radiomics models performed satisfactorily in both the tasks, showing especially higher accuracy in the second task by successfully discriminating borderline and malignant ovarian serous tumors compared to the evaluations by senior sonographers (AUC = 0.789 for seniors and 0.877 for radiomics models in task one; AUC = 0.612 for senior and 0.839 for radiomics model in task 2). We showed that the CCR model, comprising CA125 level, lesion location, ascites, and radiomics signatures, performed the best (AUC = 0.937, 95%CI 0.905–0.969 in task 1, AUC = 0.924, 95%CI 0.876–0.971 in task 2) in the training as well as in the validation cohorts (AUC = 0.914, 95%CI 0.851–0.976 in task 1, AUC = 0.890, 95%CI 0.794–0.987 in task 2). The calibration curve and DCA analysis of the CCR model more accurately predicted the classification of the tumors than the clinical features alone. Conclusion: This study integrates novel radiomics signatures from ultrasound and clinical factors to create a nomogram to provide preoperative diagnostic information for differentiating between benign, borderline, and malignant ovarian serous tumors, thereby reducing unnecessary and risky biopsies and surgeries.

New sonographic feature (C-sign) to improve the prenatal accuracy of jejunal atresia.

ObjectivesTo describe a new sonographic feature of the C‐sign for prenatal diagnosis of jejunal atresia and evaluate its role in prenatal jejunal atresia, particularly preceding bowel dilatation and polyhydramnios.MethodsThis was a retrospective study from a tertiary maternal hospital. Patients with prenatal sonographic examination and confirmed small bowel atresia postdelivery were included. All sonographic images were reviewed by two senior sonographers. Comparison of sonographic images between prenatal jejunal and ileal atresia using the C‐sign resembles the shape of the entire duodenum and other traditional sonographic features. The control group without bowel atresia was assessed for the presence of the C‐sign.ResultsThe C‐sign and combined bowel dilatation with polyhydramnios were more frequent in jejunal atresia than ileal atresia, but the C‐sign can be used to detect jejunal atresia earlier. The C‐sign can be more likely to diagnose jejunal atresia in persisting bowel dilatation and polyhydramnios. The C‐sign was not reported in any of the control fetuses.ConclusionThe C‐sign is a new sonographic feature that can be used to improve the prenatal accuracy and early detection of jejunal atresia. However, further prospective validation is needed.

Clinical value of SMI Combined with Low-Dose CT Scanning in differential diagnosis of Thyroid Lesions and Tumor Staging.

Objectives:To investigate the clinical value of Superb Microvascular Imaging (SMI) combined with low dose CT scanning in differential diagnosis of thyroid lesions and tumor staging.Methods:A total of 120 patients with thyroid nodules admitted to the Chinese PLA General Hospital from January 2017 to July 2020 were selected. Paired design was adopted in this study. SMI and SMI combined with low-dose CT scanning were respectively carried out to these patients. The results were judged by two senior imaging physicians and two senior sonographers respectively. And t-test, χ2 test, Pearson correlation coefficient check and other methods were adopted to comparatively analyze the above two methods and the pathological results after operation or puncture.Results:Compared with pathologic findings, the coincidence rate of SMI was 40%, and the coincidence rate of SMI combined with low dose CT scanning was 84%. The difference was significant (p=0.00); among the 120 thyroid nodule patients, 50 were diagnosed as malignant by pathological diagnosis, and 70 as benign; 27 malignant cases and 93 benign cases were detected by SMI; 48 malignant cases and 72 benign cases were detected by SMI combined with low dose CT scanning. The sensitivity and accuracy of the latter were significantly higher than those of the former, and the difference was statistically significant (p=0.00); the enhancement, edge sharpness and homogeneity of SMI increased with the increase of tumor malignancy, showing positive correlation property.Conclusion:SMI combined with low dose CT scanning has a higher diagnostic coincidence rate. Its sensitivity and accuracy are significantly superior. With the increase of tumor malignancy, the enhancement and unhomogeneity of SMI increase, and the edge is more blurred. That suggests: with the increase of tumor malignancy, neovascularization in the tumor is more obvious and more unevenly distributed; the increase of edge blur indicates more obvious tumor infiltration. The method has considerable clinical value for predicting the malignancy of tumors.