3D Ultrasound Research Articles

Ultrasound Frame-to-Volume Registration via Deep Learning for Interventional Guidance.

Fusing intraoperative 2-D ultrasound (US) frames with preoperative 3-D magnetic resonance (MR) images for guiding interventions has become the clinical gold standard in image-guided prostate cancer biopsy. However, developing an automatic image registration system for this application is challenging because of the modality gap between US/MR and the dimensionality gap between 2-D/3-D data. To overcome these challenges, we propose a novel US frame-to-volume registration (FVReg) pipeline to bridge the dimensionality gap between 2-D US frames and 3-D US volume. The developed pipeline is implemented using deep neural networks, which are fully automatic without requiring external tracking devices. The framework consists of three major components, including one) a frame-to-frame registration network (Frame2Frame) that estimates the current frame's 3-D spatial position based on previous video context, two) a frame-to-slice correction network (Frame2Slice) adjusting the estimated frame position using the 3-D US volumetric information, and three) a similarity filtering (SF) mechanism selecting the frame with the highest image similarity with the query frame. We validated our method on a clinical dataset with 618 subjects and tested its potential on real-time 2-D-US to 3-D-MR fusion navigation tasks. The proposed FVReg achieved an average target navigation error of 1.93 mm at 5-14 fps. Our source code is publicly available at https://github.com/DIAL-RPI/Frame-to-Volume-Registration.

Miniaturized Endoscopic 2D US Transducer for Volumetric Ultrasound Imaging of the Auditory System.

In this paper, we focus on the carrying out and validation of minimally invasive three-dimensional (3D) ultrasound (US) imaging of the auditory system, which is based on a new miniaturized endoscopic 2D US transducer. This unique probe consists of a 18 MHz 24 elements curved array transducer with a distal diameter of 4 mm so it can be inserted into the external auditory canal. Typical acquisition is achieved by rotating such a transducer around its own axis using a robotic platform. Reconstruction of a US volume from the set of acquired B-scans during the rotation is then performed using scan-conversion. The accuracy of the reconstruction procedure is evaluated using a dedicated phantom that includes a set of wires as reference geometry. Twelve acquisitions obtained from different probe poses are compared to a micro-computed tomographic model of the phantom, leading to a maximum error of 0.20 mm. Additionally, acquisitions with a cadaveric head highlight the clinical applicability of this set up. Structures of the auditory system such as the ossicles and the round window can be identified from the obtained 3D volumes. These results confirm that our technique enables the accurate imaging of the middle and inner ears without having to deteriorate the surrounding bone. Since US is a real-time, wide available and non-ionizing imaging modality, our acquisition setup could facilitate the minimally invasive diagnosis and surgical navigation for otology in a fast, cost-effective and safe way.

Evaluation of fatty liver with grey scale 2D ultrasonography and ultrasound elastography and co-relation with lipid profile in adult patient in the state of Chhattisgarh attending Dr. Bhim Rao Ambedkar memorial hospital tertiary care centre Raipur

Background: Several noninvasive imaging techniques have been introduced for the assessment of liver fibrosis. Among these techniques real-time Point shear wave elastography has become a promising imaging modality for the measurement of liver stiffness. The advantage of this technique is that the elasticity displayed using a B-mode image, also a quantitative estimation of liver stiffness is performed. The present study evaluates the fatty liver in patients above 18 years age with grey scale 2D ultrasonography and ultrasound elastography and also study the correlation with lipid profile in patients attending Dr B.R.A.M hospital tertiary care center Raipur, Chhattisgarh. Methods: This was a hospital based observational study conducted in Department of Radio-diagnosis, Dr BRAM Hospital and Pt JNM Medical College, Raipur (C.G). A sample of 198 patient above 18-year age with fatty liver were taken. Grading and quantification of fatty liver was also done by Shear wave elastography. A p-value <0.05 was considered statistically significant. Results: Mean age of study subjects was 48.47±15.21 years and 52.02% were female. 2D ultrasound technique diagnosed 75.25% grade-1 and 24.24% were in grade-II. Elastography technique diagnosed 57.58% with dysfunction (F1) liver stiffness, 28.28% fibrosis present (F2 or F3) and 13.64% normal. Increasing liver stiffness stages was significantly associated with increasing levels of serum VLDL (p=0.04). Conclusions: Ultrasound used in conjunction with elastography has shown utility in diagnosing and follow up of fatty liver patients. Liver stiffness was significantly associated with increasing levels of serum VLDL.

Quantitative validation of two model-based methods for the correction of probe pressure deformation in ultrasound.

The acquisition of good quality ultrasound (US) images requires good acoustic coupling between the ultrasound probe and the patient's skin. In practice, this good coupling is achieved by the operator applying a force to the skin through the probe. This force induces a deformation of the tissues underlying the probe. The distorted images deteriorate the quality of the reconstructed 3D US image. In this work, we propose two methods to correct these deformations. These methods are based on the construction of a biomechanical model to predict the mechanical behavior of the imaged soft tissues. The originality of the methods is that they do not use external information (force or position value from sensors, or elasticity value from the literature). The model is parameterized thanks to the information contained in the image. This is allowed thanks to the optimization of two key parameters for the model which are the indentation d and the elasticity ratio α. The validation is performed on real images acquired on a gelatin-based phantom using an ultrasound probe inducing an increasing vertical indentation using a step motor. The results showed a good correction of the two methods for indentations less than 4mm. For larger indentations, one of the two methods (guided by the similarity score) provides a better quality of correction, presenting a Euclidean distance between the contours of the reference image and the corrected image of 0.71mm. The proposed methods ensured the correction of the deformed images induced by a linear probe pressure without using any information coming from sensors (force or position), or generic information about the mechanical parameters. The corrected images can be used to obtain a corrected 3D US image.

Three-dimensional ultrasound image reconstruction based on 3D-ResNet in the musculoskeletal system using a 1D probe: ex vivo and in vivo feasibility studies

Objective. Three-dimensional (3D) ultrasound (US) is needed to provide sonographers with a more intuitive panoramic view of the complex anatomical structure, especially the musculoskeletal system. In actual scanning, sonographers may perform fast scanning using a one-dimensional (1D) array probe .at random angles to gain rapid feedback, which leads to a large US image interval and missing regions in the reconstructed volume. Approach. In this study, a 3D residual network (3D-ResNet) modified by a 3D global residual branch (3D-GRB) and two 3D local residual branches (3D-LRBs) was proposed to retain detail and reconstruct high-quality 3D US volumes with high efficiency using only sparse two-dimensional (2D) US images. The feasibility and performance of the proposed algorithm were evaluated on ex vivo and in vivo sets. Main r esults. High-quality 3D US volumes in the fingers, radial and ulnar bones, and metacarpophalangeal joints were obtained by the 3D-ResNet, respectively. Their axial, coronal, and sagittal slices exhibited rich texture and speckle details. Compared with kernel regression, voxel nearest-neighborhood, squared distance weighted methods, and a 3D convolution neural network in the ablation study, the mean peak-signal-to-noise ratio and mean structure similarity of the 3D-ResNet were up to 28.53 ± 1.29 dB and 0.98 ± 0.01, respectively, and the corresponding mean absolute error dropped to 0.023 ± 0.003 with a better resolution gain of 1.22 ± 0.19 and shorter reconstruction time. Significance. These results illustrate that the proposed algorithm can rapidly reconstruct high-quality 3D US volumes in the musculoskeletal system in cases of a large amount of data loss. This suggests that the proposed algorithm has the potential to provide rapid feedback and precise analysis of stereoscopic details in complex and meticulous musculoskeletal system scanning with a less limited scanning speed and pose variations for the 1D array probe.

A Comparative Study of Deep Learning Methods for Multi-Class Semantic Segmentation of 2D Kidney Ultrasound Images.

Ultrasound (US) imaging is a widely used medical imaging modality for the diagnosis, monitoring, and surgical planning for kidney conditions. Thus, accurate segmentation of the kidney and internal structures in US images is essential for the assessment of kidney function and the detection of pathological conditions, such as cysts, tumors, and kidney stones. Therefore, there is a need for automated methods that can accurately segment the kidney and internal structures in US images. Over the years, automatic strategies were proposed for such purpose, with deep learning methods achieving the current state-of-the-art results. However, these strategies typically ignore the segmentation of the internal structures of the kidney. Moreover, they were evaluated in different private datasets, hampering the direct comparison of results, and making it difficult to determination the optimal strategy for this task. In this study, we perform a comparative analysis of 7 deep learning networks for the segmentation of the kidney and internal structures (Capsule, Central Echogenic Complex (CEC), Cortex and Medulla) in 2D US images in an open access multi-class kidney US dataset. The dataset includes 514 images, acquired in multiple clinical centers using different US machines and protocols. The dataset contains the annotation of two experts, but 321 images with complete segmentation of all 4 classes were used. Overall, the results demonstrate that the DeepLabV3+ network outperformed the inter-rater variability with a Dice score of 78.0% compared to 75.6% for inter-rater variability. Specifically, DeepLabV3Plus achieved mean Dice scores of 94.2% for the Capsule, 85.8% for the CEC, 62.4% for the Cortex, and 69.6% for the Medulla. These findings suggest the potential of deep learning-based methods in improving the accuracy of kidney segmentation in US images.Clinical Relevance- This study shows the potential of DL for improving accuracy of kidney segmentation in US, leading to increased diagnostic efficiency, and enabling new applications such as computer-aided diagnosis and treatment, ultimately resulting in improved patient outcomes and reduced healthcare costs.1.

Implications of use of different intraoperative ultrasound modalities during glioma surgery – A comparative study of factors affecting outcomes

BackgroundThe main goal of glioma surgery is to remove the maximum amount of tumor without worsening the patient's neurological condition. Intraoperative ultrasound (US) imaging technologies (2D and 3D) are available to assist surgeons, providing real-time updates. Considering additional time, personnel, and cost, we investigate if comparable outcomes can be achieved using basic (2D) and advanced (3D) technology. ObjectiveWe propose predictive models for (i) glioma tumor resectability (ii) surgical outcome, and (iii) a model to predict the outcome of surgery aided with a particular ultrasound and compare outcomes between 2D and 3D US. MethodologyWe used real-world surgery data from a tertiary cancer centre. Three groups of cases were analyzed (2D US used, 3D US used, and no US used during resection). The data analysis uses hypothesis testing, bootstrap sampling, and logistic regression. ResultsThe preoperatively anticipated extent of tumor removal correlated with the postoperative MRI measurement of tumor removal for US-supported surgery (p=0.01) but not for no US-supported surgeries (p = 0.13). A combination of delineation, eloquence, and the multifocal/multicentric nature of the tumor effectively predicted resectability. The eventual outcome of surgery (actual extent of resection achieved) can be predicted by prior treatment status, delineation, eloquence, and satellite nodules. Based on our prediction model (training set of 350 cases and test of 40 cases of US-guided surgeries), we identify some cases where 3D US seems to offer superior EORs. ConclusionThe resectability of glioma tumors is crucial in determining surgical objectives, and the type of ultrasound used as support impacts tumor removal. The findings in this study aid informed decision-making and optimize imaging technology usage, providing a decision flow for selecting ultrasound based on tumor characteristics.

Cleft palate in fetuses: feasibility of early diagnosis by Crystal and Realistic Vue rendering 3D ultrasound technology in the first trimester.

This study aimed to evaluate the feasibility of direct visualization of a normal fetal palate and detect cleft palate in the first trimester with a novel three-dimensional ultrasound (3D US) technique, Crystal and Realistic Vue (CRV) rendering technology. Two-dimensional (2D) images and 3D volumes of healthy and cleft palate fetuses at 11-13+6 weeks were obtained prospectively. 2D ultrasound views included the coronal view of the retronasal triangle and the midsagittal view of the face. 3D-CRV views were analyzed by multiplanar mode display. The pregnancy outcomes of all fetuses were determined during the follow-up period. In our study, 124 fetuses were recruited, including 100 healthy fetuses and 24 cleft palate fetuses. The cleft palate with lip was observed in 23 fetuses (bilateral in 15, unilateral in 6, median in 2), and one cleft palate was only found in the abnormal group. The bilateral (n = 12) and median (n = 2) cleft palates with lips and the cleft palate alone (n = 1) were associated with other anatomical or chromosomal abnormalities, and one unilateral cleft palate with cleft lip had concomitant NT thickening. In the cleft palate fetus group, 16 fetuses suffered intrauterine death, which was associated with other structural or chromosomal abnormalities in 14 fetuses, seven cases were terminated after consultation, and one was delivered at term. The coronal view of the retronasal triangle and the midsagittal view was easily obtained in all fetuses. 3D-CRV images of palatal parts were clearly obtained in all cases. Unilateral, bilateral, and median cleft palates with cleft lips were visually demonstrated and classified by the 3D-CRV technique. It is feasible to identify the palate by 3D-CRV in the first trimester in both healthy and cleft palate fetuses. Together with 2D ultrasonography as a complementary diagnostic tool, 3D-CRV is helpful in classifying the cleft palate with a reasonable degree of certainty.

Inverse Correlation of Cholesterol Efflux Capacity with Peripheral Plaque Volume Measured by 3D Ultrasound.

Cardiovascular disease (CVD) is a systemic multifocal illness called atherosclerosis that causes artery constriction and blockage. By causing cholesterol to build up in the artery wall, hypercholesterolemia is a major factor in the pathophysiology of atherosclerotic plaque development. Reverse cholesterol transport is the process of transporting cholesterol from the periphery back to the liver through cholesterol efflux mediated by high-density lipoprotein (HDL). It was suggested that the cholesterol efflux capacity (CEC), which is inversely linked with cardiovascular risk, can serve as a stand-in measure for reverse cholesterol transport. In this work, we sought to investigate a potential link between the peripheral plaque volume (PV) and CEC. Since lipid-lowering therapy interferes with CEC, we performed a cross-sectional study of 176 patients (48.9% females) with one cardiovascular risk factor or known CVD that did not currently take lipid-lowering medication. CEC was determined using cAMP-treated 3H-cholesterol-labeled J774 cells. Cholesterol ester transfer protein (CETP)-mediated cholesterol ester transfer was measured by quantifying the transfer of cholesterol ester from radiolabeled exogenous HDL cholesterol to Apolipoprotein B-containing lipoproteins. PV in the carotid and the femoral artery, defined as the total PV, was measured using a 3D ultrasound system equipped with semi-automatic software. In our patients, we discovered an inverse relationship between high total PV and CEC (p = 0.027). However, there was no connection between total PV and low-density lipoprotein cholesterol, lipoprotein (a), or CETP-mediated cholesterol ester transfer. In patients not receiving lipid-lowering treatment, CEC inversely correlates with peripheral atherosclerosis, supporting its role in the pathophysiology of atherosclerosis.

A Mobile Two‐Dimensional Ultrasound Focusing System for Personalized Healthcare Applications through a Dodecagonal Quasicrystal Patterned Planar Lens

Ultrasound technology is widely utilized in applications, including tumor treatments, drug delivery, and skin care. However, improvements are required to prevent unwanted damage to non‐targeted tissues. The ultrasound focusing technology, represented by the highly intensive focused ultrasound (HIFU) technology, is actively researched to handle this problem. However, current technology is primarily limited in the point focusing of the ultrasound. Some applications, such as drug delivery and skin care, require 2D‐focusing of the ultrasound for effective utilization. Based on this necessity, this research proposes the rationally designed dodecagonal quasicrystal patterned (DQP) planar lens, which enables ultrasound focusing in 2D. The custom‐built ultrasound scanning setup confirms the 2D focusing behavior of the DQP lens. Furthermore, the developed DQP lens is integrated into the mobile ultrasound 2D focusing (MU2F) system and solved the bulkiness limitation of the HIFU system. The proposed MU2F system is applied in microneedle‐mediated drug delivery. The dramatic enhancement in the dissolution efficiency of the drug‐containing microneedle (≈2.5×) compared with the case without the MU2F system is confirmed. Through the proposed MU2F system, ultrasound‐based medical devices may widen their approachability from the clinic to the home.

RecON: Online learning for sensorless freehand 3D ultrasound reconstruction.

Sensorless freehand 3D ultrasound (US) reconstruction based on deep networks shows promising advantages, such as large field of view, relatively high resolution, low cost, and ease of use. However, existing methods mainly consider vanilla scan strategies with limited inter-frame variations. These methods thus are degraded on complex but routine scan sequences in clinics. In this context, we propose a novel online learning framework for freehand 3D US reconstruction under complex scan strategies with diverse scanning velocities and poses. First, we devise a motion-weighted training loss in training phase to regularize the scan variation frame-by-frame and better mitigate the negative effects of uneven inter-frame velocity. Second, we effectively drive online learning with local-to-global pseudo supervisions. It mines both the frame-level contextual consistency and the path-level similarity constraint to improve the inter-frame transformation estimation. We explore a global adversarial shape before transferring the latent anatomical prior as supervision. Third, we build a feasible differentiable reconstruction approximation to enable the end-to-end optimization of our online learning. Experimental results illustrate that our freehand 3D US reconstruction framework outperformed current methods on two large, simulated datasets and one real dataset. In addition, we applied the proposed framework to clinical scan videos to further validate its effectiveness and generalizability.

Three-Dimensional Ultrasound Evaluation of Lung Volume in Fetuses with Abdominal Wall Defect

Introduction: Abdominal wall defects (AWDs) interfere with postnatal respiratory parameters. We aimed to evaluate lung volume (LV) in fetuses with AWD using three-dimensional (3D) ultrasound (US) and to correlate AWD with the type (omphalocele and gastroschisis) and size of the defect and neonatal morbidity and mortality. Methods: This prospective observational study included 72 pregnant women with fetuses with AWD and a gestational age <25 weeks. The data on abdominal volume, 3D US LV, and herniated volume were acquired every 4 weeks up to 33 weeks. LV was compared with normal reference curves and correlated with abdominal and herniated volumes. Results: Omphalocele (p < 0.001) and gastroschisis (p < 0.001) fetuses had smaller LV than normal fetuses. LV was positively correlated with abdominal volume (omphalocele, r = 0.86; gastroschisis, r = 0.88), whereas LV was negatively correlated with omphalocele-herniated volume/abdominal volume (p < 0.001, r = −0.51). LV was smaller in omphalocele fetuses that died (p = 0.002), were intubated (p = 0.02), or had secondary closure (p < 0.001). In gastroschisis, a smaller LV was observed in fetuses discharged using oxygen (p = 0.002). Conclusion: Fetuses with AWD had smaller 3D LV than normal fetuses. Fetal abdominal volume was inversely correlated with LV. In omphalocele fetuses, a smaller LV was associated with neonatal mortality and morbidity.

Two-dimensional ultrasound results in underestimation of the ovarian follicle size compared to automated three-dimensional imaging in women undergoing IVF.

Traditionally, for the assessment of follicle growth during IVF, two-dimensional (2D) transvaginal ultrasound (US) is used. In the past few years three-dimensional (3D) US has also been introduced. To compare follicular sizes between 2 and 3D ultrasound imaging on the final day of controlled ovarian stimulation. A prospective observational cohort study including 121 women undergoing controlled ovarian stimulation (COS) between January 2017 and July 2018. All women were assessed by transvaginal 2D and 3D ultrasonography to measure ovarian follicle dimensions on the final day of COS. The mean difference in paired comparisons between the 3D and 2D US measurements in 25 women with monofollicular development was + 1.6 ± 2.5mm for the x-dimension and + 1.7 ± 2.4mm for the y-dimension; and in the total number of 1197 paired measurements of follicles the mean difference + 2.1 ± 3.3mm and + 1.8 ± 3.9mm for the x- and y-dimension respectively. In all cases the paired t-test showed that differences were statistically significant (p < 0.01). Further it was conjectured that the 2D underestimation results from the inherent difficulty to precisely place the US probe simultaneously on the perpendicular maximal of the x and y follicle diameters, leading to measurement errors that, by theory, are normally distributed. Running Monte-Carlo simulations based on these measurement errors it was found that both the mean difference and standard deviation are of the same magnitude as the ones found in real measurements, thus proving the conjecture. The utilisation of 3D US results in different measurements of the follicular dimensions, and volumes, when compared to conventional 2D US. The differences in the x- and y-dimensions may affect the outcome of an IVF cycle as they are used to define the day of triggering final oocyte maturation, which is associated with the yield of mature oocytes and the probability of live birth.

P-355 Thin endometrium is associated to higher risk of having a displaced window of implantation (WOI)

Abstract Study question Is thin endometrium (&amp;lt;6 mm) associated to an abnormal receptivity status? Summary answer Thin endometrium (&amp;lt;6 mm) is significantly associated with a displaced WOI. What is known already The measurement of endometrial thickness by 2D vaginal ultrasound (US) is a routine practice in Assisted Reproduction Techniques (ART). Thin endometrium (&amp;lt;6 mm) is associated with poor reproductive outcome; however, the potential reason is unknown. Study design, size, duration Retrospective cohorts study including 25,888 patients in which endometrial lining was measured by 2D US the day before progesterone supplementation in HRT cycles for frozen embryo transfers and Endometrial Receptivity Analysis (ERA) was performed after 5 days of progesterone administration. Endometrial thickness was classified as &amp;lt; 6 mm, 6-12 mm, or &amp;gt; 12 mm; ERA results were considered as receptive or displaced WOI (Pre-receptive, post-receptive, proliferative, and late-receptive) that needs a personalized embryo transfer (pET). Participants/materials, setting, methods Endometrial thickness was measured from one endometrial layer to the other on a longitudinal transvaginal scan at the site of maximum thickness evidenced by 2D US. For ERA analysis, RNA was extracted and sequenced by NGS. Then, the ERA computational predictor obtained the diagnosis as standard or displaced WOI. Main results and the role of chance RA results reveal that women with thin endometrium (&amp;lt;6mm) present significantly higher incidence of displaced WOI (47.49%) than 6-12mm (38.20%) (p = 0.0038), and &amp;gt;12mm (39.75%) (p = 0.026). No other differences were found. *Significant different against other two groups. Global Chi-square test for association P = 0.002. Limitations, reasons for caution This is a retrospective study, having innate limitations of its nature. Wider implications of the findings Thin endometrium (&amp;lt;6mm) is associated to a higher displaced WOI compared to normal lining or hypertrophic endometrium. Normal endometrial thickness (6-12 mm) considered as “receptive” does not preclude a transcriptomic receptivity status in 38.20% of the cases. This finding should be considered when embryo transfer is planned. Trial registration number Not applicable

Accelerated Measurement of Carotid Plaque Volume Using Artificial Intelligence Enhanced 3D Ultrasound

Carotid plaque volume (CPV) can be measured by 3D ultrasound and may be a better predictor of stroke than stenosis, but analysis time limits clinical utility. This study tested the accuracy, reproducibility, and time saved of using an artificial intelligence (AI) derived semiautomatic software to measure CPV ("auto-CPV"). Three-dimensional (3D) ultrasound images for 121 individuals were analyzed by 2 blinded operators to measure auto-CPV. Corresponding endarterectomy specimen volumes were calculated by the validated saline suspension technique. Inter-rater and intrarater agreement plus accuracy compared with the volume of the endarterectomized plaque were calculated. Measurement times were compared with previous manual CPV measurement. The mean difference between auto-CPV and surgical volume was small at (±s.d.) [95% confidence interval [CI]] 0.06 (0.24) [-0.41 to 0.54] cm3. The intraclass correlation (ICC) was strong at 0.91; 95% CI 0.86-0.94. Interobserver and intraobserver error was low with mean difference (±s.d.) [95%CI] 0.01 (0.26) [-0.5 to 0.5] cm3 and 0.03 (0.19) [-0.35 to 0.40] cm3 respectively. Both showed excellent ICC with narrow confidence intervals, ICC=0.90; 95% CI (0.85-0.94) and ICC=0.95; 95% CI (0.92-0.96). Auto-CPV measurement took 43% the time of manual planimetry; median (IQR) 05:39 (01:58) minutes compared to 13:05 (04:15) minutes, Wilcoxon rank-sum test, P<0.01. Auto-CPV assessment is accurate, reproducible, and significantly faster than manual planimetry. Improved feasibility means that the utility of CPV can be assessed in large population studies to stratify risk in asymptomatic carotid disease or assess response to medical treatment.

P-749 Increased accuracy in infertility workup by the additional use of new modern diagnostic methods (“diagnostic TRIO”): results from a large retrospective analysis

Abstract Study question Is there any positive effect of adding new modalities to the traditional infertility work-up, like 3D sonography, office hysteroscopy and endometrial biopsy? Summary answer During infertility workup conventional diagnostic tests should be combined with new approaches (3D-TVS, OHSC and endometrial biopsy) to achieve more accurate and less invasive diagnostics. What is known already Female infertility can be explained by functional or organic abnormalities affecting the reproductive system. The most common organic causes include abnormalities within the uterine cavity (e.g. endometrial polyp, submucosal fibroid, intrauterine adhesion), morphological disorders (e.g. dysmorphic uterus, uterine septum) and abnormalities of the endometrium (e.g. chronic endometritis). Study design, size, duration In our retrospective study, we examined patients with primary and secondary infertility. All the patients were assessed by 3D-TVS and OHSC to detect morphological and intrauterine disorders, and in special cases (repeated implantation failure – RIF), endometrial biopsies were carried out to detect endometrial disorders. Participants/materials, setting, methods Data of 606 patients examined between 2018 and 2022 were analyzed retrospectively. Main results and the role of chance In 606 cases 3D-TVS and OHSC were performed in patients (65.51 % primary, 34.49 % secondary infertility), who had unknown reason to infertility. By the combination of 3D-TVS and OHSC we could verify uterine disorders in 39.93 % of cases. Together these two diagnostic methods found the probable infertility causing lesion almost 40 % of our patients. In the subgroup of 40 repeated implantation failure (RIF) patients, the “diagnostic TRIO” confirmed a disorder in 57.50 % of the cases. Limitations, reasons for caution Number of patients should be more to conclude more accurate data. Wider implications of the findings The proper condition of the uterine milieu, through correction of uterine cavity if necessary, endometrial receptivity are of paramount importance for the success of the treatment; as a result, intrauterine surgery as a new subspecialty has been developing. Trial registration number DE RKEB/IKEB: H.0250-2020

Bridging the simulation-to-real gap for AI-based needle and target detection in robot-assisted ultrasound-guided interventions

BackgroundArtificial intelligence (AI)-powered, robot-assisted, and ultrasound (US)-guided interventional radiology has the potential to increase the efficacy and cost-efficiency of interventional procedures while improving postsurgical outcomes and reducing the burden for medical personnel.MethodsTo overcome the lack of available clinical data needed to train state-of-the-art AI models, we propose a novel approach for generating synthetic ultrasound data from real, clinical preoperative three-dimensional (3D) data of different imaging modalities. With the synthetic data, we trained a deep learning-based detection algorithm for the localization of needle tip and target anatomy in US images. We validated our models on real, in vitro US data.ResultsThe resulting models generalize well to unseen synthetic data and experimental in vitro data making the proposed approach a promising method to create AI-based models for applications of needle and target detection in minimally invasive US-guided procedures. Moreover, we show that by one-time calibration of the US and robot coordinate frames, our tracking algorithm can be used to accurately fine-position the robot in reach of the target based on 2D US images alone.ConclusionsThe proposed data generation approach is sufficient to bridge the simulation-to-real gap and has the potential to overcome data paucity challenges in interventional radiology. The proposed AI-based detection algorithm shows very promising results in terms of accuracy and frame rate.Relevance statementThis approach can facilitate the development of next-generation AI algorithms for patient anatomy detection and needle tracking in US and their application to robotics.Key points• AI-based methods show promise for needle and target detection in US-guided interventions.• Publicly available, annotated datasets for training AI models are limited.• Synthetic, clinical-like US data can be generated from magnetic resonance or computed tomography data.• Models trained with synthetic US data generalize well to real in vitro US data.• Target detection with an AI model can be used for fine positioning of the robot.Graphical

Sagittal Spinal Alignment in People with Chronic Spinal Cord Injury and Normal Individual: A Comparison Study Using 3D Ultrasound Imaging.

The aim of this study was to compare the sagittal spinal alignment of people with chronic spinal cord injury (SCI) with normal individuals and to determine whether transcutaneous electrical spinal cord stimulation (TSCS) could cause a change in the thoracic kyphosis (TK) and lumbar lordosis (LL) to re-establish normal sagittal spinal alignment. A case series study was conducted, wherein twelve individuals with SCI and ten neurologically intact subjects were scanned using 3D ultrasonography. In addition, three people with SCI having complete tetraplegia participated further to receive a 12-week treatment (TSCS with task-specific rehabilitation) after evaluation of sagittal spinal profile. Pre- and post-assessments were conducted to evaluate the differences in sagittal spinal alignment. The results showed that the TK and LL values for a person with SCI in a dependent seated posture were greater than those of normal subjects for: standing (by TK: 6.8° ± 1.6°; LL: 21.2° ± 1.9°), sitting straight (by TK: 10.0° ± 4.0°; LL: 1.7° ± 2.6°), and relaxed sitting (by TK: 3.9° ± 0.3°; LL: 7.7° ± 1.4°), respectively, indicating an increased risk for spinal deformity. In addition, TK decreased by 10.3° ± 2.3° after the TSCS treatment, showing a reversible change. These results suggest that the TSCS treatment could be used to restore normal sagittal spinal alignment for individuals with chronic SCI.

Longitudinal Study to Assess the Reliability and Predictive Validity of Ultrasound Measurements in Tracking Fetal Growth and Development Throughout Pregnancy

The utilization of ultrasound in obstetrics is extremely common due to its accurate fetal imaging capabilities. By early identifying anomalies such intrauterine growth restrictions and macrosomia, ultrasonography scanning during pregnancy primarily aims to reduce the risk of obstetric problems. Fetal weight is currently estimated using morphometric formulas. They employ fundamental biometric variables. Hadlock's formula, which is used for estimation of fetal weight, has 20 percent error rate, though. Due to this particular cause, the researchers from all around world had already searching for the additional sonographic characteristics having a stronger predictive value that correlate with fetal weight. According to recent scientific studies, assessing fetal weight can benefit from using novel parameters of sonograph such measurements of the thickness of soft tissue. The fetus's body can be measured in a number of locations, including upper arm, the thigh, abdomen, and the subscapular region. Diverse measurements have varying degrees of connection with some other anthropometric &amp; sonographic factors, including body mass &amp; gestational age. Numerous research using novel formulas for calculating fetal weight have been produced in response to the reports. For measuring fetal weight, measurements other than those including soft tissue, including such those lean and adipose tissue or utilising 3D ultrasonography are acquired. For the purpose of sonographic pregnancy assessment, ultrasound examination of the thicknesses of subcutaneous tissue in the several body regions might evidence to become reliable indicator of the fetal weight. Keywords: Pregnancy, postpartum hypoglycaemia, foetus, Intra-uterine, pregnancy ultrasound

Comparison of image quality of 3D ultrasound: motorized acquisition versus freehand navigated acquisition, a phantom study

PurposeIntra-operative assessment of resection margins during oncological surgery is a field that needs improvement. Ultrasound (US) shows the potential to fulfill this need, but this imaging technique is highly operator-dependent. A 3D US image of the whole specimen may remedy the operator dependence. This study aims to compare and evaluate the image quality of 3D US between freehand acquisition (FA) and motorized acquisition (MA).MethodsMultiple 3D US volumes of a commercial phantom were acquired in motorized and freehand fashion. FA images were collected with electromagnetic navigation. An integrated algorithm reconstructed the FA images. MA images were stacked into a 3D volume. The image quality is evaluated following the metrics: contrast resolution, axial and elevation resolution, axial and elevation distance calibration, stability, inter-operator variability, and intra-operator variability. A linear mixed model determined statistical differences between FA and MA for these metrics.ResultsThe MA results in a statistically significant lower error of axial distance calibration (p < 0.0001) and higher stability (p < 0.0001) than FA. On the other hand, the FA has a better elevation resolution (p < 0.003) than the MA.ConclusionMA results in better image quality of 3D US than the FA method based on axial distance calibration, stability, and variability. This study suggests acquiring 3D US volumes for intra-operative ex vivo margin assessment in a motorized fashion.