Dimensional Ultrasound Imaging Research Articles

Three-dimensional volume rendering ultrasound for assessing placenta accreta spectrum severity and discriminating it from simple scar dehiscence

Prenatal ultrasound discrimination between placenta accreta spectrum and scar dehiscence with underlying nonadherent placenta is challenging both prenatally and intraoperatively, which often leads to overtreatment. In addition, accurate prenatal prediction of surgical difficulty and morbidity in placenta accreta spectrum is difficult, which precludes appropriate multidisciplinary planning. The advent of advanced 3-dimensional volume rendering and contrast enhancement techniques in modern ultrasound systems provides a comprehensive prenatal assessment, revealing details that are not discernible in traditional 2-dimensional imaging. This study aimed to evaluate the use of 3-dimensional volume rendering ultrasound techniques in determining the severity of placenta accreta spectrum and distinguishing between placenta accreta spectrum and scar dehiscence with underlying nonadherent placenta. A prospective, cohort study was conducted between July 2022 and July 2023 in the fetal medicine unit of Dr Soetomo Academic General Hospital, Surabaya, Indonesia. All pregnant individuals with anterior low-lying placenta or placenta previa with a previous caesarean section who were referred with suspicion of placenta accreta spectrum were consented and screened using the standardised 2-dimensional and Doppler ultrasound imaging. Additional 3-dimensional volumes were obtained from the sagittal section of the uterus with a filled urinary bladder. These were analyzed by rotating the region of interest to be perpendicular to the uterovesical interface. The primary outcomes were the clinical and histologic severity in the cases of placenta accreta spectrum and correct diagnosis of dehiscence with nonadherent placenta underneath. The strength of association between ultrasound and clinical outcomes was determined. Multivariate logistic regression analyses and diagnostic testing of accuracy were used to analyze the data. A total of 70 patients (56 with placenta accreta spectrum and 14 with scar dehiscence) were included in the analysis. Multivariate logistic regression of all 2-dimensional and 3-dimensional signs revealed the 3-dimensional loss of clear zone (P<.001) and the presence of bridging vessels on 2-dimensional Doppler ultrasound (P=.027) as excellent predictors in differentiating scar dehiscence and placenta accreta spectrum. The 3-dimensional loss of clear zone demonstrated a high diagnostic accuracy with an area under the curve of 0.911 (95% confidence interval, 0.819-1.002), with a sensitivity of 89.3% (95% confidence interval, 78.1-95.97%) and specificity of 92.9% (95% confidence interval, 66.1-99.8%). The presence of bridging vessels on 2-dimensional Doppler demonstrated an area under the curve of 0.848 (95% confidence interval, 0.714-0.982) with a sensitivity of 91.1% (95% confidence interval, 80.4-97.0%) and specificity of 78.6% (95% confidence interval, 49.2-95.3%). A subgroup analysis among the placenta accreta spectrum group revealed that the presence of a 3-dimensional disrupted bladder serosa with obliteration of the vesicouterine space was associated with vesicouterine adherence (P<.001). Three-dimensional volume rendering ultrasound is a promising tool for effective discrimination between scar dehiscence with underlying nonadherent placenta and placenta accreta spectrum. It also shows potential in predicting the clinical severity with urinary bladder involvement in cases of placenta accreta spectrum.

Application of Freehand 3D Ultrasound Guidance in Percutaneous Transluminal Angioplasty for Autogenous Arteriovenous Fistula Stenosis

Objective: Using freehand three dimensional (3D) ultrasound imaging to evaluate arteriovenous fistula stenosis. Comparing the value of freehand 3D ultrasound and Doppler ultrasound in the application of percutaneous transluminal angioplasty (PTA) treatment for stenosis of an arteriovenous fistula. Methods: A retrospective analysis was conducted on 34 patients with arteriovenous fistula (AVF) stenosis who were treated at the 903RD Hospital of PLA and the Kidney Center of Zhejiang Provincial People's Hospital from August 2021 to August 2022. Based on the different types of surgical assistance, the patients were divided into two groups: the Doppler ultrasound group (Group A, n = 17) and the freehand 3D ultrasound imaging group (Group B, n = 17). Freehand 3D ultrasound and Doppler ultrasound were used to assess the narrowing of arteriovenous fistulas, and images and relevant data were collected before and after the PTA procedure. The differences in the time of puncture and sheath placement, guidewire insertion time, the duration of the procedure, complications, and methods to measure stenosis were compared between the two groups of patients, as well as the technical success rate, the initial patency rate, and the primary patency rates at 1, 3, 6 and 9 months post-surgery. This study discusses the clinical efficacy of using these two types of ultrasound to assist in the PTA treatment of arteriovenous fistula stenosis. Results: The differences in baseline demographics between the conventional ultrasound group (Group A) and the 3D ultrasound group (Group B) were not statistically significant (p &gt; 0.05). The intraoperative guidewire insertion time (4.647 ± 1.347 min vs. 2.824 ± 0.326 min) and the operating times (75.941 ± 7.557 min vs. 59.824 ± 8.175 min) between the two groups were statistically significant (t = 2.788, 3.069, p &lt; 0.01). The technical success rates for the two groups were 94.1% vs. 100%, not statistically significant (t = 1.03, p = 0.31). The first-time patency rates were 88.2% vs. 94.1%, with no statistically significant difference (t = 0.366, p = 0.545). No complications occurred in Group A, while one case of hematoma occurred postoperatively in Group B, with an incidence of 5.9% (1/17), which was not statistically significant (t = 1.03, p &gt; 0.05). Comparing the primary patency rates at 1, 3, 6 and 9 months post-surgery between Groups A and B, there were no statistically significant differences (p &gt; 0.05). However, the patency rates at different time points for Group B were consistently higher than Group A (94.1%, 82.4%, 82.4%, 82.4% vs. 88.2%, 82.4%, 76.5%, 76.5%). Conclusion: Freehand 3D ultrasound imaging can provide more intuitive, high-resolution, and high-definition three-dimensional images, clearly defining the lesion site and vascular structures. Its accuracy in assessing complications of arteriovenous fistulas is similar to that with conventional ultrasound. When used as an adjunct to PTA treatment, its efficacy is equivalent. It can significantly reduce guidewire insertion time and operation time, decrease postoperative recovery time, and alleviate the patients' concerns regarding surgical risks. It can be considered a new method for diagnosing, treating, and patients with AVF stenosis.

The role of multimodal ultrasound in diagnosis of fetal bowel dilatation and prediction of adverse neonatal outcomes: A study of 86 cases in a series of 43,562 births

ObjectiveTo investigate the diagnostic utility of multimodal ultrasound for fetal bowel dilatation (FBD) in different parts of the bowel and to examine its prognostic potential in FBD. MethodsThis retrospective study analyzed 86 fetuses with a dilated bowel identified via ultrasound in a 10-month postnatal follow-up. Both two- and three dimensional (2D and 3D, respectively) ultrasound volume imaging were used to characterize dilation across different bowel sections. The optimal intestinal diameter cut-off values for pathological bowel dilatation were determined and a predictive model for neonatal surgery was developed. ResultsThe 86 cases of dilatation were distributed as follows: duodenal (n = 36); jejunum/ileum (n = 35); and colonic (n = 15). Duodenal dilatations presented the earliest during pregnancy compared to the other 2 groups (24.4 versus [vs.] 29 vs. 33.7 weeks respectively; p < 0.05). Cases with small intestinal dilatation were delivered earlier than those with colonic dilatation (p < 0.05). Infants with duodenal dilatation had the lowest birth weight and the highest rate of multi-system abnormalities (30.6% vs. 5.7% vs. 20%; p < 0.001). More than one-half of the multi-system abnormalities had chromosomal abnormalities (multiple, 54% vs. single, 12.5%; p = 0.015). There were 2 stillbirths, 24 induced labors, 44 postnatal surgeries, and 18 normal cases after birth. In predicting adverse neonatal outcomes of jejunum/ileum dilatation using a cut-off value of 15.5 mm small intestine diameter, sensitivity was 81.5%, specificity was 62.5%, and the area under the receiver operating characteristic curve (AUC) was 0.762 (p < 0.05). For colonic dilatation, using a cut-off value of 21.5 mm colon diameter: sensitivity was 83.3%, specificity was 77.8%, and AUC was 0.861 (p < 0.05). In detecting jejunum/ileum and colonic obstruction, 3D ultrasound demonstrated significantly better diagnostic efficiency than 2D ultrasound (p < 0.05). Using the backward stepwise selection method, a predictive model for neonatal surgery in patients with jejunum/ileum and colonic dilatation was established: logit (P) = −1.58 + (2.32 × polyhydramnios) +(2.0 × ascites) +(1.14 × hyperechogenic bowel). The AUC for the prediction model was 0.874 (p < 0.05), with 76% sensitivity and 94.1% specificity. ConclusionsDuodenal dilatation occurred earlier, with a higher incidence of chromosomal abnormalities and multi-system abnormalities than dilatation of other parts of the bowel. 3D ultrasound played an important role in the detection of jejunum/ileum and colon obstructions. Clinical signs, including polyhydramnios, ascites, and strong echoes in the intestine, can be used to predict neonatal surgery.

A multimodal breast cancer diagnosis method based on Knowledge-Augmented Deep Learning

Breast cancer is a worldwide medical challenge that requires Early diagnosis. While there are numerous diagnostic methods for breast cancer, many primarily focus on network structure, neglecting the guidance of professional medical knowledge. Moreover, these methods limit their analysis to 2-dimensional B-mode ultrasound images and rarely consider the potential insights provided by Contrast-Enhanced Ultrasound (CEUS) videos, which offer more detailed dynamic pathological information. Therefore, how to effectively utilize prior medical knowledge to achieve a precise diagnosis of breast cancer based on CEUS videos has emerged as a pressing issue. To address this challenge, we propose a multimodal breast cancer diagnostic method based on Knowledge-Augmented Deep Learning named KAMnet. This method integrates three types of prior knowledge into deep neural networks through different integration strategies. First, we devise a temporal segment selection strategy guided by Gaussian sampling through data-level integration, guiding the model to focus on keyframes. Second, we construct a feature fusion network for architecture-level integration and achieve collaborative inference through decision-level integration, facilitating multimodal information exchange. Finally, a spatial attention-guided loss function through training-level integration helps the model target lesion regions. We validate our model on our breast cancer video dataset consisting of 332 cases. The result shows that our model can achieve a sensitivity of 90.91% and an accuracy of 88.238%. Extensive ablation experiments demonstrate the effectiveness of our knowledge enhancement modules. The code is released at https://github.com/tobenan/BCCAD_torch.

Cross-sectional reliability and concurrent validity of a quantitative 2-dimensional ultrasound image analysis of effusion and synovial hypertrophy in knee osteoarthritis

ObjectiveEffusion-synovitis is related to pain and progression in knee osteoarthritis (OA), but current gold standard ultrasound (US) measures are limited to semi-quantitative grading of joint distension or 1-dimensional thickness measures. A novel quantitative 2-dimensional image analysis methodology is applied to US images of effusion-synovitis; reliability and concurrent validity was assessed in patients with knee OA. MethodsCross sectional analysis of US images collected from 51 patients with symptomatic knee OA were processed in ImageJ and segmented in 3DSlicer to produce a binary mask of the supra-patellar synovitis region of interest (ROI). Area measures (mm2) of total synovitis, effusion and hypertrophy components were exported. Intra-rater reliability and test-retest reliability (1–14 days washout) were estimated with intra-class correlation coefficients (ICCs). Concurrent validity was measured by Spearman correlations between quantitative measures and gold standard OMERACT and caliper measurements of synovitis. ResultsIntra-rater reliability for hypertrophy area was estimated at 0.98, 0.99 for effusion area, and 0.99 for total synovitis area. The test-retest reliability for total synovitis area was 0.63 (SEM 87.8 ​mm2), 0.59 for hypertrophy area (SEM 21.0 ​mm2), and 0.64 for effusion area (SEM 73.8 ​mm2). Correlation between total synovitis area and OMERACT grade was 0.84, 0.81 between total synovitis area and effusion-synovitis calipers, and 0.81 between total effusion area and effusion calipers. ConclusionThis new research tool for image analysis demonstrated excellent intra-rater reliability, good concurrent validity, and moderate test-retest reliability. Quantitative 2D US measures of effusion-synovitis and its individual components may enhance the study and management of knee OA.

Assessment of First-Trimester Utero-Placental Vascular Morphology by 3D Power Doppler Ultrasound Image Analysis Using a Skeletonization Algorithm: The Rotterdam Periconception Cohort

ABSTRACT Abnormal uteroplacental vascular development is one of the primary causes of the major disorders of pregnancy. Identification of this aberrant development in the preconception stage and in the first trimester, when measures to prevent complications are most effective, remains a challenge. Recent advances in offline imaging processing and Doppler techniques have allowed ultrasonographic analysis of placental volume (PV) and uteroplacental vascular volume (uPVV) in the first trimester. The ability of ultrasound to assess specific vascular morphology is not fully understood. The aim of this study was to investigate morphologic development of the first-trimester human uteroplacental vasculature in vivo using 3-dimensional power Doppler ultrasound and advanced image processing to generate the uteroplacental vascular skeleton (uPVS). Data were obtained from the VIRTUAL Placenta study, an ongoing observational study including adult women carrying a singleton pregnancy at less than 10-week gestational age (GA). At least 2 study visits were scheduled in the first trimester, at 7, 9, and 11 weeks' GA. The image quality of ultrasound scans was scored on a 4-point scale ranging between 0 (optimal) and 3 (unusable), and PV was measured using VOCAL software. The uPVV was measured using a virtual reality desktop system with the V-scope volume-rendering application. A skeletonization algorithm was then applied to the uPVV segmentation to generate the uPVS, and 7 morphological uPVS characteristics were used to determine the density of vascular branching within the placenta. A total of 214 women from the VIRTUAL cohort were eligible for inclusion, and 81% of all ultrasound data were of sufficient quality for generation of the uPVS. The distribution of endpoints, vessel points, bifurcation points, and crossing points in the uPVS and the distribution of uPVS characteristics per cm3 uPVV show consistent morphologic patterns throughout the first trimester. Moderate to strong positive correlations between uPVS characteristics and PV and strong positive correlations between uPVS characteristics and uPVV were identified. All uPVS characteristics increased significantly through the first trimester, except for uPVS average length, which remained constant between 7, 9, and 11 weeks' GA. When stratifying for placenta-related complications among the cohort, no significant differences in the uPVS characteristics were seen at 7 weeks' GA (n = 94). However, at 9 weeks (n = 170), there were significantly fewer number of vessel points (P = 0.040), bifurcation points (P = 0.050), crossing points (P = 0.020), and a shorter total network length (P = 0.023) among pregnancies with placenta-related complications. At 11 weeks' GA (n = 129), uPVS average vascular thickness was significantly lower in pregnancies with placenta-related complications (P = 0.007), but no other uPVS differences were observed. At 11 weeks' GA, pregnancies with placenta-related complications were found to have an increased density of vascular branching in the uPVV. The results of this study demonstrate a quantitative morphologic analysis of the human uteroplacental vasculature in the first trimester of pregnancy and key differences in the vascular morphology between pregnancies with and without placenta-related complications.

A Review of the Existing Literature on 3D Reconstruction Methods

Abstract: Using deep neural networks, supervised 3D reconstruction has made significant progress. However, large-scale annotations of 2D/3D data are necessary for this performance boost [4]. How to effectively represent 3D data to feed deep networks remains a challenge in 3D deep learning. Volumetricor point cloud representations have been used inrecent works, but these methods have a number of drawbacks, including computational complexity, unorganized data, and a lack of finer geometry [7]. The ultrasound (US) examination is onemethod usedto diagnose carotid artery disease. The flow conditions in the artery also play a role in the onset and progression of vascular diseases [5]. Stenting the carotid artery is a treatment option for carotid atherosclerosis. It is impossible to know for sure where an injection with a needle will begin. The place of the conduits is in the body, thusly, decidingthe beginning stage of needle infusion is finished byassessment just and can't not entirely set in stone. The first thing that must be done is to locate the carotid artery in order to identify it. To determine it,we propose a modified template matching based on the ellipse feature for a 3D reconstruction of the carotid artery [1]. Data acquisition, pre-processing, segmentation, outlier selection for ellipse parameterfitting, and visualization are all used to process it. In comparison to the template matching method and the Hough Circle method, the proposed procedure with pre-processing produces the highest accuracy [1]. The objective of this research was to create three- dimensional (3D) ultrasound imaging of the carotid arteries to lessen the variability of volume measurements between and within examiners duringfollow-up scans of atherosclerotic plaques.

A new approach to automatic measure fetal head circumference in ultrasound images using convolutional neural networks

Fetal head circumference (HC) is an important biological index in prenatal ultrasound screening. In the clinic, fetal HC is usually measured manually by sonographers in two dimensional (2D) ultrasound images. The manual method is significantly affected by the inter/intra-observer difference and the process of manual measurement is inconvenient and time-consuming for sonographers. Although several artificial intelligence (AI) approaches had been applied to fetal HC measurement, they had weak generalization ability, especially for the incomplete or blurred skull edge. In this study, a fast and accurate method for fetal HC auto-measurement was proposed. Different from the common region segmentation method, an end-to-end convolutional neural network (CNN) for fetal skull boundary segmentation in 2D ultrasound images is proposed, which is an efficient method to directly segment the boundary of fetal skull by using the proposed double-branch structure. The segmentation results can be directly used to calculate fetal HC without complex post-processing. The proposed approach achieved excellent results: Mean Dice Sore (MDS)±std: 97.98 ± 1.30, Mean Hausdorff Distance (MHD)±std: 1.20 ± 0.68 mm, Mean Absolute Difference (MAD)±std: 1.75 ± 1.60 mm, Mean Difference (MD)±std: 0.08 ± 2.37 mm. Additionally, we drew a Bland–Altman plot to demonstrate that HC measured by the proposed approach has high agreement with the real value. Comprehensive results show that the proposed approach is comparable to the state-of-the-art methods for fetal HC measurement. Meanwhile, our approach belongs to a lightweight network with less parameters, which is convenient for deployment. We hope it could provide help for precision medicine in prenatal ultrasound screening.

Repeatability of Ultrasound-Defined Bladder Shape Metrics in Healthy Volunteers.

PurposeRecent studies demonstrate the potential value of using non-invasive abdominal ultrasound to quantify bladder shape and its association with disorders of bladder filling and voiding. The aim of the present study was to assess the repeatability of ultrasound-defined bladder shape metrics within the same individual from multiple bladder fills and study visits.Patients and MethodsHealthy volunteers completed an oral hydration protocol with two weekly visits, each with two consecutive bladder fill-void cycles, providing four total fills per participant. Throughout filling, 3-dimensional (3-D) ultrasound images were recorded at 5-minute intervals. Perimeters were manually traced in six cross-sectional planes 30° apart using GE 4D-View software. Diameters, perimeters and cross-sectional areas for the transverse, sagittal and coronal planes were interpolated at three standard bladder volumes of 200, 300, and 400mL. To quantify repeatability, intraclass correlation coefficients (ICCs) and normalized mean absolute differences were calculated for each metric at each standard volume. Moderate and good repeatability were defined as ICC ≥0.5 and ICC ≥0.75, respectively.ResultsData from 16 healthy volunteers (9 females, 7 males) were analyzed. ICCs for the transverse vertical and horizontal diameters showed good repeatability, and five of nine perimeter ICCs showed moderate or good repeatability. The mean absolute difference/mean ratio was ≤4% for all perimeter measurements, indicating repeatability was consistent for multiple fills and visits.ConclusionInitial evidence indicates that bladder shape metrics are relatively repeatable and therefore feasible to pursue as a non-invasive tool for potential evaluation of bladder function.

Fetal ultrasound image segmentation using dilated multi-scale-LinkNet

Ultrasound imaging is routinely conducted for prenatal care in many countries to determine the health of the fetus, the pregnancy's progress, as well as the baby's due date. The intrinsic property of fetal images during different stages of pregnancy creates difficulty in automatic extraction of fetal head from ultrasound image data. The proposed work develops a deep learning model called Dilated Multi-scale-LinkNet for segmenting fetal skulls automatically from two dimensional ultrasound image data. The network is modeled to work with Link-Net since it offers better interpretation in biomedicine applications. Convolutional layers with dilations are added following the encoders. The Dilated convolution is used to expand the size of an image to prevent data loss. Training and evaluating the model is done using the HC18 grand challenge dataset. It contains 2D ultrasound images at different pregnancy stages. The results of experiments performed on an ultrasound images of women in different pregnancy stages. It reveals that we achieved 94.82% Dice score, 1.9 mm ADF, 0.72 DF and 2.02 HD when segmenting the fetal skull. Employing Dilated Multi-Scale-LinkNet improves the accuracy as well as all the evaluation parameters of the segmentation compared with the existing methods.

441. Placental volume in gestational week 27 measured by three dimensional (3d) ultrasound and magnetic resonance imaging (mri)

Introduction and aims of the study: Ultrasound is the diagnostic tool of choice in pregnancy. We lack valid ultrasound methods for placental size measurements. Our aim was therefore to compare three-dimensional (3D) ultrasound with magnetic resonance imaging (MRI) for measurements of placental volume. Methods: We measured placental volume by 3D ultrasound and MRI in 100 unselected pregnancies at 27 weeks of gestation (25+4 - 28+4 weeks). The 3D ultrasound acquisitions were analysed offline, and the placental outline was manually traced using the virtual organ computer-aided analysis (VOCAL) 30° rotational technique.

An interstitial ectopic pregnancy managed with laparoscopic cornual resection

Introduction: Interstitial ectopic pregnancy is a rare type of tubal ectopic pregnancy associated with increased case fatality rate due to profuse haemorrhage. It is initially asymptomatic and ruptured later than other tubal ectopic pregnancies. Case report: A 31 years old primigravida presented with per vaginal bleeding at period of amenorrhoea of six weeks. Her examination findings were unremarkable and transvaginal scan revealed left sided interstitial pregnancy. Her initial serum beta human Chorionic Gonadotropin (β-hCG) level was 7300 mIU/ml. As she was haemodynamically stable, there were no signs of rupture and serum β-hCG was dropping, she was initially managed expectantly. As she developed abdominal pain with per vaginal bleeding and drop in serum β-hCG was slow, expectant management was abandoned and surgical management was planned. Laparoscopy was performed and revealed a left sided interstitial pregnancy with thinned out myometrium. As laparoscopy guided transcervical suction evacuation has failed, laparoscopic corneal resection was performed after vasopressin infiltration into myometrium. She had uneventful recovery and was followed up until her serum β-hCG became less than 30 IU/L. Discussion: An Interstitial ectopic pregnancy must be differentiated from cornual and angular pregnancies with clearly defined ultrasound diagnostic criteria. Three dimensional (3D) ultrasound and magnetic resonance imaging (MRI) will further help in diagnosis of interstitial ectopic pregnancy. It can be managed expectantly, medically or surgically depending on the patient’s clinical condition, preference and serum β-hCG level.

Expert recommendations on data collection and annotation of two dimensional ultrasound images in azoospermic males for evaluation of testicular spermatogenic function in intelligent medicine

Testicular two-dimensional ultrasound is a testing modality that is often used to evaluate azoospermia and other related diseases. With the continuous development of deep learning in recent years, the combination of deep learning and testicular ultrasound appears unstoppable despite a lack of relevant standards. One of the major problems associated with the digitization of ultrasound images is the uneven quality of data however, and a standardized data source and acquisition process has not yet been developed. Such a standard could fill the current gap, and establish acquisition criteria for ultrasound images of testes during the male reproductive period, including grayscale ultrasound, shear wave elastography, and contrast-enhanced ultrasound. By following these guidelines the quality of testicular ultrasound images would be improved and standardized, which would lay a solid foundation for the standardization of testicular ultrasound images, and assist automated evaluation of testicular spermatogenic function of whole testis in azoospermic males.

3-D Super-Resolution Ultrasound Imaging for Monitoring Early Changes in Breast Cancer after Treatment with a Vascular-Disrupting Agent.

The purpose of this research project was to evaluate the use of 3-dimensional (3-D) super-resolution ultrasound (SR-US) imaging to assess any early changes in breast cancer after treatment with a vascular-disrupting agent (VDA). A Vevo 3100 ultrasound system (FUJIFILM VisualSonics Inc) equipped with an MX 201 transducer was used for image acquisition. A total of 2.5 × 107 microbubbles (MBs) were injected into the tail vein of anesthetized breast cancer-bearing mice using repeat bolus injections every 5 min. A total of 10 stacks of ultrasound images were collected as the transducer was mechanically moved across the tumor at 0.6 mm intervals yielding a 6-mm thick volume. At each tumor location, a stack contained 1 × 104 frames of ultrasound data that were acquired at 463 frames/sec and stored as in-phase/quadrature (IQ) format. After motion correction, each temporal stack of ultrasound images was processed separately for clutter signal removal, which was followed by MB localization and enumeration before generation of the final SR-US image. After reconstruction of the 3-D SR-US volume dataset, the tumor microvasculature was enhanced using a multiscale vessel enhancement filter. Vessels from the resultant microvascular network were then segmented using an adaptive thresholding method. Finally, mean microvascular density (MVD) measurements from each tumor volume were computed as a summarizing statistic. While no differences were found between baseline SR-US image-derived measures of MVD (p = 0.76), these same measurements were significantly lower at 24 h after VDA treatment (p < 0.001). Overall, 3-D SR-US imaging detected early tumor changes following treatment with a vascular-targeted drug.

Automated Segmentation of Fetal Ultrasound Images Using Feature Attention Supervised Network.

Segmentation of anatomical structures from ultrasound images requires the expertise of an experienced clinician, but developing a machine automated segmentation process is complicated because of the existence of characteristic artifacts. In this article, we present a novel end-to-end network that enables automated measurements of the fetal head circumference (HC) and fetal abdomen circumference (AC) to be made from 2-dimensional (2D) ultrasound images during each pregnancy trimester. These measurements are necessary, because the HC and AC are used to predict gestational age and to monitor fetal growth. Automated HC and AC assessments are valuable for providing independent and objective results and are particularly useful for application in developing countries where trained sonographers are in short supply. We propose a scale attention expanding network that builds a feature pyramid inside the network, and the intermediate result of each scale is then concatenated to the feature with a fusion scheme for the next layer. Furthermore, a scale attention module is proposed for selecting the most useful scale and for reducing scale noise. To optimize the network, a deep supervision method based on boundary attention is employed. Results of experiments show that the scale attention expanding network obtained an absolute difference, Hausdorff distance, and dice similarity coefficient of 1.81 ± 1.69%, 1.22 ± 0.77%, and 97.94%, respectively, which were top results in the HC18 data set, and respective results on the abdomen set were 2.23 ± 2.38%, 0.42 ± 0.56%, and 98.04%. The experiments conducted demonstrate that our method provides a superior performance to existing fetal ultrasound segmentation methods.

Fetal magnetic resonance imaging at 36 weeks predicts neonatal macrosomia: the PREMACRO study

Large-for-gestational-age fetuses are at increased risk of perinatal morbidity and mortality. Magnetic resonance imaging seems to be more accurate than ultrasound in the prediction of macrosomia; however, there is no well-powered study comparing magnetic resonance imaging with ultrasound in routine pregnancies. This study aimed to prospectively compare estimates of fetal weight based on 2-dimensional ultrasound and magnetic resonance imaging with actual birthweights in routine pregnancies. From May 2016 to February 2019, women received counseling at the 36-week clinic. Written informed consent was obtained for this Ethics Committee-approved study. In this prospective, single-center, blinded study, pregnant women with singleton pregnancies between 36 0/7 and 36 6/7 weeks' gestation underwent both standard evaluation of estimated fetal weight with ultrasound according to Hadlock etal and magnetic resonance imaging according to the formula developed by Baker etal, based on the measurement of the fetal body volume. Participants and clinicians were aware of the results of the ultrasound but blinded to the magnetic resonance imaging estimates. Birthweight percentile was considered as the gold standard for the ultrasound and magnetic resonance imaging-derived percentiles. The primary outcome was the area under the receiver operating characteristic curve for the prediction of large-for-gestation-age neonates with birthweights of ≥95th percentile. Secondary outcomes included the comparative prediction of large-for-gestation-age neonates with birthweights of ≥90th, 97th, and 99th percentiles and small-for-gestational-age neonates with birthweights of ≤10th, 5th, and 3rd percentiles for gestational age and maternal and perinatal complications. Of 2914 women who were initially approached, results from 2378 were available for analysis. Total fetal body volume measurements were possible for all fetuses, and the time required to perform the planimetric measurements by magnetic resonance imaging was 3.0 minutes (range, 1.3-5.6). The area under the receiver operating characteristic curve for the prediction of a birthweight of ≥95th percentile was 0.985 using prenatal magnetic resonance imaging and 0.900 using ultrasound (difference=0.085, P<.001; standard error, 0.020). For a fixed false-positive rate of 5%, magnetic resonance imaging for the estimation of fetal weight detected 80.0% (71.1-87.2) of birthweight of ≥95th percentile, whereas ultrasound for the estimation of fetal weight detected 59.1% (49.0-68.5) of birthweight of ≥95th percentile. The positive predictive value was 42.6% (37.8-47.7) for the estimation of fetal weight using magnetic resonance imaging and 35.4% (30.1-41.1) for the estimation of fetal weight using ultrasound, and the negative predictive value was 99.0% (98.6-99.3) for the estimation of fetal weight using magnetic resonance imaging and 98.0% (97.6-98.4) for the estimation of fetal weight using ultrasound. For a fixed false-positive rate of 10%, magnetic resonance imaging for the estimation of fetal weight detected 92.4% (85.5-96.7) of birthweight of ≥95th percentile, whereas ultrasound for the estimation of fetal weight detected 76.2% (66.9-84.0) of birthweight of ≥95th percentile. The positive predictive value was 29.9% (27.2-32.8) for the estimation of fetal weight using magnetic resonance imaging and 26.2% (23.2-29.4) for the estimation of fetal weight using ultrasound, and the negative predictive value was 99.6 (99.2-99.8) for the estimation of fetal weight using magnetic resonance imaging and 98.8 (98.4-99.2) for the estimation of fetal weight using ultrasound. The area under the receiver operating characteristic curves for the prediction of large-for-gestational-age neonates with birthweights of ≥90th, 97th, and 99th percentiles and small-for-gestational-age neonates with birthweights of ≤10th, 5th, and 3rd percentiles was significantly larger in prenatal magnetic resonance imaging than in ultrasound (P<.05 for all). At 36 weeks' gestation, magnetic resonance imaging for the estimation of fetal weight performed significantly better than ultrasound for the estimation of fetal weight in the prediction of large-for-gestational-age neonates with birthweights of ≥95th percentile for gestational age and all other recognized cutoffs for large-for-gestational-age and small-for-gestational-age neonates (P<.05 for all).

Critical Role of 3D ultrasound in the diagnosis and management of Robert's uterus: a single-centre case series and a review.

A septate uterus with a non-communicating hemicavity was first described by Robert in 1969/70 as a specific malformation of the uterus. The condition is commonly associated with a blind uterine hemicavity, unilateral haematometra, a contralateral unicornuate uterine cavity and a normal external uterine fundus. The main symptoms are repetitive attacks of pain at four-weekly intervals around menarche, repeated dysmenorrhea, recurrent pregnancy loss and infertility.In this report, we review the disease, its diagnosis and treatment, and describe five cases of Robert's uterus. Three dimensional (3D) ultrasound (US) imaging was performed by the transvaginal route in four cases. In the fifth case of a 13-year-old girl, we avoided the vaginal route and magnetic resonance imaging (MRI) and 3D transrectal US yielded the correct diagnosis.The following treatment procedures were undertaken: laparoscopic endometrectomy, hysteroscopic septum resection, laparoscopic uterine hemicavity resection and total laparoscopic hysterectomy (TLH). The diagnosis and optimum treatment of Robert's uterus remains difficult for clinicians because of its rarity. A detailed and careful assessment by 3D US should be performed, followed by hysteroscopy in combination with laparoscopy, to confirm the diagnosis.

Estimating 3-dimensional liver motion using deep learning and 2-dimensional ultrasound images.

The main purpose of this study is to construct a system to track the tumor position during radiofrequency ablation (RFA) treatment. Existing tumor tracking systems are designed to track a tumor in a two-dimensional (2D) ultrasound (US) image. As a result, the three-dimensional (3D) motion of the organs cannot be accommodated and the ablation area may be lost. In this study, we propose a method for estimating the 3D movement of the liver as a preliminary system for tumor tracking. Additionally, in current 3D movement estimation systems, the motion of different structures during RFA could reduce the tumor visibility in US images. Therefore, we also aim to improve the estimation of the 3D movement of the liver by improving the liver segmentation. We propose a novel approach to estimate the relative 6-axial movement (x, y, z, roll, pitch, and yaw) between the liver and the US probe in order to estimate the overall movement of the liver. We used a convolutional neural network (CNN) to estimate the 3D displacement from two-dimensional US images. In addition, to improve the accuracy of the estimation, we introduced a segmentation map of the liver region as the input for the regression network. Specifically, we improved the extraction accuracy of the liver region by using a bi-directional convolutional LSTM U-Net with densely connected convolutions (BCDU-Net). By using BCDU-Net, the accuracy of the segmentation was dramatically improved, and as a result, the accuracy of the movement estimation was also improved. The mean absolute error for the out-of-plane direction was 0.0645mm/frame. The experimental results show the effectiveness of our novel method to identify the movement of the liver by BCDU-Net and CNN. Precise segmentation of the liver by BCDU-Net also contributes to enhancing the performance of the liver movement estimation.

Utility of Ultrasound as a Valid and Accurate Diagnostic Tool for Sarcopenia

Patients with chronic kidney disease (CKD) have aberrant changes in body composition, including low skeletal muscle mass, a feature of "sarcopenia." The measurement of the (quadriceps) rectus femoris (RF) cross-sectional area (CSA) is widely used as a marker of muscle size. Cutoff values are needed to help discriminate the condition of an individual's muscle (eg, presence of sarcopenia) quickly and accurately. This could help distinguish those at greater risk and aid in targeted treatment programs. Transverse images of the RF were obtained by B-mode 2-dimensional ultrasound imaging. Sarcopenic levels of muscle mass were defined by established criteria (1, appendicular skeletal muscle mass [ASM]; 2, ASM/height2 ; and 3, ASM/body mass index) based on the ASM and total muscle mass measured by a bioelectrical impedance analysis. The discriminative power of RF-CSA was assessed by receiver operating characteristic curves, and optimal cutoffs were determined by the maximum Youden index (J). One hundred thirteen patients with CKD (mean age [SD], 62.0 [14.1] years; 48% male; estimated glomerular filtration rate, 38.0 [21.5] mL/min/1.73m2 ) were included. The RF-CSA was a moderate predictor of ASM (R2 = 0.426; P < .001) and total muscle mass (R2 = 0.438; P < .001). With a maximum J of 0.47, in male patients, an RF-CSA cutoff of less than 8.9 cm2 was deemed an appropriate cutoff for detecting sarcopenic muscle mass. In female patients, an RF-CSA cutoff of less than 5.7 cm2 was calculated on the basis of ASM/height2 (J = 0.71). Ultrasound may provide a low-cost and simple means to diagnose sarcopenia in patients with CKD. This would allow for early management and timely intervention to help mitigate the effects in this group.

Diagnosis of foetal vein of galen aneurysmal malformation by ultrasound combined with magnetic resonance imaging: a case series

BackgroundFoetal vein of Galen aneurysmal malformation (VGAM) is a very rare congenital malformation of the cerebral blood vessels. We sought to evaluate the diagnostic value of ultrasound in combination with magnetic resonance imaging (MRI) in foetal VGAM.Case presentationPrenatal ultrasound combined with MRI diagnosed five cases of VGAM. Two dimensional ultrasound images were used to find the echo-free cystic structure below the thalamus and above the cerebellum with five cases. Colour blood flow showed dilated VGAM in five cases, while the arteriovenous spectrum was explored in two cases and foetal heart failure was found in other three cases. MRI was manifested as a dilated VGAM found at the midline of the brain, demonstrating widening or dilation of the straight sinus in four cases, ventricular dilatation in one case, brain parenchyma bleeding in two cases, and grey matter softening in one case. One infant died on the day of its birth, while the other four infants died within one month to six months after birth.ConclusionsUltrasound combined with MRI can more accurately and comprehensively observe the pathological characteristics of VGAM, diagnose related complications early and determine its prognosis.