3D Ultrasound Research Articles

Development of an integrated dual-modality 3D bioluminescence tomography and ultrasound imaging system for small animal tumor imaging.

Ultrasound (US) is a valuable tool for imaging soft tissue and visualizing tumor contours. Taking the benefits of US, we presented an integrated dual-modality imaging system in this paper that achieves three-dimensional (3D) bioluminescence tomography (BLT) with multi-view bioluminescence images and 3D US imaging. The purpose of this system is to perform non-invasive, long-term monitoring of tumor growth in 3D images. US images can enhance the accuracy of the 3D BLT reconstruction and the bioluminescence dose within an object. Furthermore, an integrated co-registered scanning geometry was used to capture the fused BLT and US images. We validated the system with an in vivo experiment involving tumor-bearing mice. The results demonstrated the feasibility of reconstructing 3D BLT images in the tumor region using 3D US images. We used the dice coefficient and locational error to evaluate the similarity between the reconstructed source region and the actual source region. The dice coefficient was 88.5%, and the locational error was 0.4 mm when comparing the BLT and 3D US images. The hybrid BLT/US system could provide significant benefits for reconstructing the source of tumor location and conducting quantitative analysis of tumor size.

Automatic Diagnosis of Carotid Atherosclerosis Using a Portable Freehand 3-D Ultrasound Imaging System.

The objective of this study is to develop a deep-learning-based detection and diagnosis technique for carotid atherosclerosis (CA) using a portable freehand 3-D ultrasound (US) imaging system. A total of 127 3-D carotid artery scans were acquired using a portable 3-D US system, which consisted of a handheld US scanner and an electromagnetic (EM) tracking system. A U-Net segmentation network was first applied to extract the carotid artery on 2-D transverse frame, and then, a novel 3-D reconstruction algorithm using fast dot projection (FDP) method with position regularization was proposed to reconstruct the carotid artery volume. Furthermore, a convolutional neural network (CNN) was used to classify healthy and diseased cases qualitatively. Three-dimensional volume analysis methods, including longitudinal image acquisition and stenosis grade measurement, were developed to obtain the clinical metrics quantitatively. The proposed system achieved a sensitivity of 0.71, a specificity of 0.85, and an accuracy of 0.80 for diagnosis of CA. The automatically measured stenosis grade illustrated a good correlation ( r = 0.76) with the experienced expert measurement. The developed technique based on 3-D US imaging can be applied to the automatic diagnosis of CA. The proposed deep-learning-based technique was specially designed for a portable 3-D freehand US system, which can provide a more convenient CA examination and decrease the dependence on the clinician's experience.

Hysteroscopic Metroplasty Using Holmium: YAG Laser for Treatment of Septate Uterus

To demonstrate the safety, efficacy, and ease of hysteroscopic metroplasty using holmium:YAG (Ho:YAG) laser for treatment of septate uterus. Stepwise demonstration of surgical technique with narrated video footage. Septate uterus is the most common type of uterine anomaly. The incidence of uterine septum in women presenting with infertility and recurrent abortions is 15.4% [1,2]. Hysteroscopic septal incision is associated with improvement in live-birth rate in these women [3]. Hysteroscopic metroplasty for septate uterus can be done with the use of scissors and energy sources such as monopolar and bipolar electrosurgery and lasers. Ho:YAG laser is commonly used by urologists for various surgeries because of its "Swiss Army Knife" action of cutting, coagulation, and vaporization [4]. Ho:YAG laser is known for its precision. It causes lesser depth of tissue injury and necrosis and minimal collateral thermal damage compared with the electrosurgical devices and other lasers used for hysteroscopic surgery [5-8]. This is advantageous in hysteroscopic metroplasty given that it reduces the risk of uterine perforation during surgery and hence uterine rupture in the subsequent pregnancy. Reduced collateral damage to the surrounding endometrium helps promote early endometrial healing and prevent postoperative intrauterine adhesions. A 28-year-old patient with history of 2 spontaneous abortions came to our hospital for investigations. 3D transvaginal sonography of the patient showed presence of partial septate uterus with a fundal indentation of 1.5 cm (Supplemental video 1). Diagnostic hysteroscopy followed by septal incision using Ho: YAG laser was planned. We used a 2.9 mm BETTOCCHI Hysteroscope (Karl Storz SE & Co.) with a 5 mm operative sheath. Normal saline was used as the distending medium and the intrauterine pressure was maintained at 80 to 100 mm Hg. The procedure was done under total intravenous anesthesia using propofol injection. Vaginoscopic entry into the uterus (without any cervical dilatation) showed evidence of a partial uterine septum with tubal ostia on either side of the septum. A 400 micron quartz fiber was passed through a laser guide into the 5-Fr working channel of the operative hysteroscope. Ho:YAG laser (Auriga XL 50-Watt, Boston Scientific) with power settings of 15 watts (1500 mJ energy at 10 Hz) was used. Incision of the septum was started at the apex of the septum in the midline and continued in a horizontal manner from side to side toward the base (Supplemental video 2). Incision of the septum is continued till the tip of the hysteroscope can move freely from one ostium to the other (Supplemental video 3). The operative time was 12 minutes. There were no intra- or postoperative complications. Postoperative estrogen therapy was given for 2 months in the form of estradiol valerate 2 mg (tablet, Progynova, Zydus Cadila) 12 hourly orally for 25 days and medroxyprogesterone acetate 10 mg (tablet, Meprate, Serum Institute of India, Ltd) 12 hourly orally added in the last 5 days [9]. 3D transvaginal ultrasound was done on day 8 of menses. It showed a triangular uterine cavity with a very small fundal indentation of 0.37 cm. A second look hysteroscopy that was done on day 9 of menses showed an uterine cavity of good shape and size [10]. Few fundal adhesions were seen and they were incised using Ho:YAG laser. The patient conceived 5 months after the primary surgery and delivered by cesarean section at 38 weeks, giving birth to a healthy baby of 2860 grams. There were no complications during her pregnancy and delivery. A comparative study is essential to prove its advantages over other energy sources for this surgery. Hysteroscopic metroplasty using Ho:YAG laser for treatment of septate uterus is a simple, precise, safe, and effective procedure. VIDEO ABSTRACT.

Muscle-Tendon Unit Length Measurement Using 3D Ultrasound in Passive Conditions: OpenSim Validation and Development of Personalized Models.

This study investigated the validity of using OpenSim to measure muscle-tendon unit (MTU) length of the bi-articular lower limb muscles in several postures (shortened, lengthened, a combination of shortened and lengthened involving both joints, neutral and standing) using 3D freehand ultrasound (US), and to propose new personalized models. MTU length was measured on 14 participants and 6 bi-articular muscles (semimembranosus SM, semitendinosus ST, biceps femoris BF, rectus femoris RF, gastrocnemius medialis GM and gastrocnemius lateralis GL), considering 5 to 6 postures. MTU length was computed using OpenSim with three different models: OS (the generic OpenSim scaled model), OS + INSER (OS with personalized 3D US MTU insertions), OS + INSER + PATH (OS with personalized 3D US MTU insertions and path obtained from one posture). Significant differences in MTU length were found between OS and 3D US models for RF, GM and GL (from - 6.3 to 10.9%). Non-significant effects were reported for the hamstrings, notably for the ST (- 1.5%) and BF (- 1.9%), while the SM just crossed the alpha level (- 3.4%, p = 0.049). The OS + INSER model reduced the magnitude of bias by an average of 4% for RF, GM and GL. The OS + INSER + PATH model showed the smallest biases in length estimates, which made them negligible and non-significant for all the MTU (i.e. ≤ 2.2%). A 3D US pipeline was developed and validated to estimate the MTU length from a limited number of measurements. This opens up new perspectives for personalizing musculoskeletal models using low-cost user-friendly devices.

The nature of abdominal surgery for polycystic kidney disease in animals and the role of sonographic indicators at different stages of surgical intervention: A literature review

Analysis of the method of using sonography during surgery in animals with polycystic kidney disease is an urgent task since firstly, sonography is a safe and non-invasive method of examination, which allows determining the structural features of the kidneys before, during, and after surgery. Secondly, from the standpoint of improving the results of surgery, sonography helps to clarify the localisation of cysts and determine their size. Thirdly, an important factor in the use of sonography is the reduction of pain and the risk of postoperative complications. In addition, due to this method of kidney examination, it is possible to more accurately determine the optimal route of access to cysts, which helps to reduce tissue injury and ensures rapid recovery of the animal after surgery. The purpose of the study is to analyse in detail and describe the method of using sonography during surgery in animals with polycystic kidney disease. The study focuses on the need to determine how sonography affects reducing the duration of surgery, improving the quality of cyst removal, and reducing the risk of complications during abdominal surgery. The approach in this study is based on the analysis of scientific papers on this subject, in particular on the experience of veterinarians who have already used sonography during abdominal operations in animals with polycystic kidney disease. Thus, special techniques of sonography and surgical treatment of kidney cysts include dopplerography, colour dopplerography, 3D and 4D sonography, elastography, introperative sonography, intraperitoneal sonography, and duplex scanning of renal arteries and veins. Surgical methods of treatment include extraction of individual cysts, drainage of cysts, resection, and nephrectomy. The use of sonography at different stages of surgical intervention helps to optimise the operation process, reduce the risk of complications, and contribute to the introduction of new approaches in the treatment of animals with polycystic kidney disease, which will substantially improve their quality of life

Reliability of Panoramic Ultrasound in Assessing Rectus Femoris Size, Shape, and Brightness: An Inter-Examiner Study.

Extended field-of-view ultrasound (US) imaging, also known as panoramic US, represents a technical advance that allows for complete visualization of large musculoskeletal structures, which are often limited in conventional 2D US images. Currently, there is no evidence examining whether the experience of examiners influences muscle shape deformations that may arise during the glide of the transducer in panoramic US acquisition. As no studies using panoramic US have analyzed whether two examiners with differing levels of experience might obtain varying scores in size, shape, or brightness during the US assessment of the rectus femoris muscle, our aim was to analyze the inter-examiner reliability of panoramic US imaging acquisition in determining muscle size, shape, and brightness between two examiners. Additionally, we sought to investigate whether the examiners' experience plays a significant role in muscle deformations during imaging acquisition by assessing score differences. Shape (circularity, aspect ratio, and roundness), size (cross-sectional area and perimeter), and brightness (mean echo intensity) were analyzed in 39 volunteers. Intraclass correlation coefficients (ICCs), standard error of measurements (SEM), minimal detectable changes (MDC), and coefficient of absolute errors (CAE%) were calculated. All parameters evaluated showed no significant differences between the two examiners (p > 0.05). Panoramic US proved to be reliable, regardless of examiner experience, as no deformations were observed. Further research is needed to corroborate the validity of panoramic US by comparing this method with gold standard techniques.

A Comparison of Colour Doppler Ultrasound and 2D Ultrasound as Promising Prediction Methods for the Treatment effect of Patients with Advanced Cervical Cancer.

A number of studies have evaluated the effect of colour Doppler ultrasound in patients with cervical cancer. This study aims to evaluate the efficacy of colour Doppler ultrasound and two-dimensional ultrasound of monitoring patients with cervical cancer. Colour Doppler ultrasound (Experimental group) and two-dimensional ultrasound (Control group) are used to monitor cervical cancer and assess the treatment effects. PFS, CI, HR, DCR, ORR, PR, SD, PD, ROD, sensitivity, and specificity, accuracy between the two groups were collected and analyzed. A total of 50 patients are included in this study, and the results show that PFS (Experimental group (EG) 5.8±2.2 versus Control group (CG) 6.1±2.6), CI (EG 20% versus CG 16%), HR (EG0.31±0.18 versus CG 0.36±0.21), DCR (EG 80% versus CG 84%), ORR(EG 28% versus CG 36%), PR (EG 16% versus CG 20%), SD (EG 48% versus CG 56%), PD (EG 12% versus CG 16%) (EG 12% versus CG 16%), ROD(EG 44% versus CG 52%) between the two groups are >0.05, and the values of sensitivity (EG 75.6% versus CG 40.2%), specificity (EG 78.4% versus CG 43.3%), and accuracy(EG 80.5% versus CG 41.4%) between the two groups are<0.05. Both Colour Doppler ultrasound and two-dimensional ultrasound are effective methods to evaluate the efficacy of concurrent chemo-radiotherapy in patients with cervical cancer.

Fully-automatic software to estimate optimal resected regions considering practical conditions for liver surgery

AimRecent advances in three-dimensional (3D) imaging have been remarkable, and 3D simulation has become an indispensable item in liver surgery. Furthermore, image processing is currently shifting from simulation software (SM) to NAVIGATIONS SOFTWARE (NS) development. The Aim of this study is to report on a new version of SM (Hariyama Shimoda software; HSS) with added preoperative liver function evaluation, and to report the results of NS development using 3D ultrasound (US) images. ResultsWe evaluated 21 cases with solitary liver tumors that underwent hepatic resection between February 2021 and June 2023 in our department. Estimated liver resection volume was positively correlated between Synaptic Vincent (SV) conventional SM software and newly developed HSS software (p < 0.001 r: 0.813), and actual resected liver volume was also positively correlated between SV and HSS (p = 0.002 r: 0.467, p = 0.002 r: 0. 641, respectively). In addition, by using the magnetic sensor “AURORA”, we were able to produce 3DUS images and were able to extract PV from US images using deep learning and region growing. ConclusionHSS is as effective a 3D NS as SV, and 3D US could be used as navigation for hepatectomy in the future.

Prior-knowledge Embedded U-Net based Fully Automatic Vessel Wall Volume Measurement of the Carotid Artery in 3D Ultrasound Image.

The vessel-wall-volume (VWV) measured based on three-dimensional (3D) carotid artery (CA) ultrasound (US) images can help to assess carotid atherosclerosis and manage patients at risk for stroke. Manual involvement for measurement work is subjective and requires well-trained operators, and fully automatic measurement tools are not yet available. Thereby, we proposed a fully automatic VWV measurement framework (Auto-VWV) using a CA prior-knowledge embedded U-Net (CAP-UNet) to measure the VWV from 3D CA US images without manual intervention. The Auto-VWV framework is designed to improve the repeated VWV measuring consistency, which resulted in the first fully automatic framework for VWV measurement. CAP-UNet is developed to improve segmentation accuracy on the whole CA, which composed of a U-Net type backbone and three additional prior-knowledge learning modules. Specifically, a continuity learning module is used to learn the spatial continuity of the arteries in a sequence of image slices. A voxel evolution learning module was designed to learn the evolution of the artery in adjacent slices, and a topology learning module was used to learn the unique topology of the carotid artery. In two 3D CA US datasets, CAP-UNet architecture achieved state-of-the-art performance compared to eight competing models. Furthermore, CAP-UNet-based Auto-VWV achieved better accuracy and consistency than Auto-VWV based on competing models in the simulated repeated measurement. Finally, using 10 pairs of real repeatedly scanned samples, Auto-VWV achieved better VWV measurement reproducibility than intra- and inter-operator manual measurements.

781 Multiethnic Growth Standards for Fetal Body Composition and Organ Volumes Derived from 3D Ultrasonography

781 Multiethnic Growth Standards for Fetal Body Composition and Organ Volumes Derived from 3D Ultrasonography

Comparison of pre-mortem 2D-3D ultrasound examination to post-mortem micro-CT of carotid arteries - first experiences.

<p>A prerequisite for the treatment of carotid atherosclerosis is the accurate measurement of the stenosis, that is most commonly evaluated by duplex ultrasonography. In this study, we aimed to verify the reliability of 2D and 3D ultrasonography, comparing the data to results of post-mortem micro-CT examination.</p>. <p>Neurological patients with any life-threatening, presumably fatal neurological disease were enrolled. Ultrasound examinations were performed with a Philips Epiq 5G machine, using a VL13-5 broadband linear volume array transducer. Plaque length, diameter and vessel area reduction (stenosis) were calculated using the 2D images. Finally, the stenosis was reassessed using automatized, 3D application as well. After the death of the patient, autopsy was performed, during which the previously examined carotid artery was removed. The samples were examined with micro-CT. Similar to the ultrasound examination, plaque length, diameter and vessel area reduction (stenosis) were determined.</p>. <p>Ten vessels of seven patients were eligible for complex comparison. Plaque diameter and length measured by CT did not correlate with the ultrasound data. CT-measured axial plaque and vessel areas showed no correlation with ultrasound results either. While determining the strength of correlation between stenoses measured by the different modalities, significant correlation was found between the results measured by ultrasound (2D) and CT (Pearson r: 0.902, P&lt;0.001).</p>. <p>Three-dimensional ultrasound analysis is a spectacular method for examining carotid plaques, as it can assist in a more detailed evaluation of the plaque morphology and composition, thereby identifying plaques with a particularly high risk of stroke. Micro-CT is an excellent tool for the exact determination of calcified plaque areas, but ultrasound images are not suitable yet for such a precise examination due to acoustic shadowing and artifacts.</p>.

3D ultrasound-augmented image guidance for surgery of high-grade gliomas - A quantitative analysis focused on the extent of resection.

We have retrospectively reviewed our series of brain tumor patients operated on using 3D IntraOperative UltraSound (IOUS) to report technical advantages and areas of improvement. Clinical and radiological data of patients with a diagnosis of high-grade glioma IV operated with and without IOUS were retrieved and analyzed. We have found 391 patients operated using IOUS coupled with neuronavigation and 257 using neuronavigation standalone. We have selected a pool of 60 patients with a diagnosis of GlioBlastoma (GB), comparing two equally sized groups operated with and without IOUS, respectively. The average extent of resection (EOR) in the IOUS group was 93%, while in the control group, it was 80%. IOUS was significantly associated with improved EOR (P < 0.0004), even when accounting for other factors affecting EOR. The average overall survival (OS) was 13.4 months, and the average progression-free survival (PFS) was 7.4 months. The Cox proportional hazard model showed an advantage in OS on patients operated using the IOUS. No statistically significant effect was observed on PFS. Intraoperative ultrasound coupled with image guidance is associated with an improved EOR and possibly an improved OS. While we are aware of several limitations related to the present analysis, these data support the routine use of IOUS as a safe and reliable technology. Larger, prospective series with updated IOUS technology are desirable to verify the accuracy of these results.

Advancing Digital Health using AI and Machine Learning Solutions for Early Ultrasonic Detection of Breast Disorders in Women

Background: Breast cancer is a significant global health concern accounting for 685,000 deaths in 2020 and 2.3 million cases worldwide. By 2070, the cases are expected to rise to 4.4 million, because it is usually discovered at a later stage when it is too late to help the patients. For the past two decades, innovations made in mobile health have improved the lives of people and accessibility in multiple disciplines. This abstract explores the feasibility of using a portable ultrasound device integrated with artificial intelligence (AI) technology for the purpose of early screening and detection of breast cancer in women living in remote and rural areas, between the ages of 18 years to 75 years. Intervention: Training healthcare professionals to use this portable ultrasound with the integration of AI technology will provide convenience and accuracy. This technology can provide high-resolution information regarding anatomic and tissue changes and holds promise for early detection of lumps in the breast. This is a critical screening and diagnostic tool for females living in rural and remote areas. The results will be compared with images of mammography testing for accuracy and patients will then be referred for further evaluation and biopsy of their lesions. Learning Objectives: To assess the feasibility and effectiveness of using AI Assisted 3D Ultrasound as a first line investigation for lesion screening To Develop high-fidelity phantom tissue models as well as simulated images that mimic real tissue properties in ultrasound imaging and simulated images and provide anatomical variations for realistic AI training purposes. To evaluate the feasibility of using portable ultrasound integrated with AI technology for early screening and detection of breast lesion Methods: Combining portable ultrasound with AI assisted technology holds significant promise for non- invasive and accessible early screening and detection of breast cancer. Here are some methods that can be employed: Using phantom lab to create tissue mimicking materials to screen breast cancer tissues and use portable ultrasound to screen the created tissue mimicking materials to train AI Automated Image Analysis: AI algorithms can analyze ultrasound images to detect abnormalities such as suspicious masses or microcalcifications. Integration with clinical data: the ultrasound findings of the patient will be added with the patient’s demographics, medical history and other medically relevant information which can improve the accuracy of cancer detection and provide more personalized care.

Role of 4D Ultrasonography in Assessment of Amniotic Fluid Disorders of Fetal Renal Origin

Role of 4D Ultrasonography in Assessment of Amniotic Fluid Disorders of Fetal Renal Origin

Gray scale 2D Ultrasound in Relation to Coagulation Profile and Uterine Artery Doppler Indices in Women with Postmenopausal Bleeding

Gray scale 2D Ultrasound in Relation to Coagulation Profile and Uterine Artery Doppler Indices in Women with Postmenopausal Bleeding

Value of 2D ultrasonography in the diagnosis and evaluation of intrauterine adhesions – a prospective study

Research questionWhat is the value of 2D ultrasonography in the diagnosis and assessment of intrauterine adhesions (IUA)? DesignThis was a prospective study conducted at a hysteroscopy centre. ResultsOf a total of 600 subjects recruited, 41 dropped out and 559 were finally enrolled and analysed. The observed 2D ultrasonography features, in decreasing order of frequency, were ‘irregular endometrium’ (37.9%), ‘broken endometrial echo’ (23.4%), ‘thin endometrium’ (13.7%), ‘loss of endometrial echo’ (13.1%,), ‘hyperechoic focus’ (12.5%) and ‘fluid in the cavity’ (8.8%). The sensitivity of individual ultrasound features ranged from 8.8% to 37.9%, whereas the specificity of individual ultrasound features ranged from 78.9% to 100%. When all the six ultrasound features were considered together, the sensitivity and specificity were 71.7% and 66.2% respectively. The sensitivity, specificity and accuracy of ultrasound diagnosis in the mid-proliferative phase, peri-ovulatory phase and mid-luteal phase did not appear to be significantly different statistically, although the results in the mid-proliferative phase appeared to be consistently higher than those in the mid-luteal phase. In women confirmed to have IUA, the likelihood of the adhesions being severe in nature in the presence of zero, one, two or three or more ultrasound features was 8.7%, 23.0%, 40.2% and 80.5%, respectively (P < 0.001). ConclusionsThe findings in this study support the notions that ultrasonography examination in women suspected to have IUA cannot replace hysteroscopy in the diagnosis of the condition. However, it does provide useful clinical information regarding severity and could help in the planning of hysteroscopy to optimize management.

What is the Optimum Endometrium Needed for Implantation?

Implantation most critical step in reproduction. A complex process where blastocyst becomes intimately connected with maternal endometrium/decidua and requires; Competent embryo at blastocyst stage Receptive endometrium Synchronized dialogue between maternal and embryonic tissues Endometrial Changes for Implantation include architectural, morphological, cytochemical, molecular and genetic. These Changes Induce Endometrial receptivity, which is endometrial lining in a state of readiness for blastocyst implantation. It involves acquisition of adhesion ligands and loss of inhibitory components that may act as a barrier to an attaching embryo. Receptive endometrium is capable of selecting good quality embryos and reject the incompetent embryos. Endometrial Evaluation includes 1. Non-Invasive Assessment of Endometrial Receptivity by USG 2. Detection of abnormal Uterine cavity by 3D USG/SIS, HSG and Hysteroscopy 3. Diagnose Chronic Endometritis by hysteroscopy and Molecular tests? 4. Endometrial Microbiome by molecular tests 5. Endometrial asynchrony - Proteomics and transcriptomics 2D and 3D Ultrasound can Identify patients with poor implantation prognosis but has low predictive value in determining endometrial receptivity and IVF outcome. Ideal endometrial thickness for optimal outcome is between 7-14 mm. No Association was seen between clinical pregnancy rates (CPR) and endometrial pattern for women undergoing in IVF with fresh ET and FET. Minimum Endometrial Volume associated with pregnancy is 1.59 mL – 3D. But most pregnancies occur in volumes of 2-13 mL. Evaluation of endometrial volume is particularly useful in synechiae, adenomyosis and uterine anomalies. Vascularity demonstrated within Zone 3 or within Zones 3 and 4 prior to transfer is associated with good implantation rate. Presence of &gt;3 peristaltic contractions of the sub endometrial myometrium/2 minutes interval on Day of hCG administration associated with poor implantation. Diagnosis of chronic endometritis is based on hysteroscopy, endometrial biopsy with plasma cells being identified histologically and specific treatment is determined based on microbial culture. Existence of non-Lactobacillus bacteria in the endometrium is correlated with negative impacts on reproductive function and should be considered as an emerging cause of implantation failure and pregnancy loss. Endometrial Receptivity Array (ERA) is validated for analysing the expression of 238 genes that are intimately related to endometrial receptivity. Abnormality in endometrial receptivity is displayed a specific gene expression profile. Intrauterine secretory profile directly linked to successful implantation and evaluation of endometrial fluid for cytokine, interleukin and growth factor secretions can be used to assess the endometrium. Conclusion: Identification of one or more of endometrial parameters that definitely indicate receptivity for implantation remains an elusive goal. None of the endometrial receptivity markers have sufficient discriminatory value to act as a diagnostic test for endometrial receptivity based on their ability to predict clinical pregnancy. Due to the dynamic, cyclic nature of the endometrium it may be difficult, to reliably assess endometrial function on the basis of a single test.

A nomogram based on ultrasound radiomics for predicting the invasiveness of cN0 single papillary thyroid microcarcinoma.

Up to 15.3% of papillary thyroid microcarcinoma (PTMC) patients with negative clinical lymph node metastasis (cN0) were confirmed to have pathological lymph node metastasis in level VI. Conventional ultrasound (US) focuses on the characteristics of tumor capsule and the periphery to determine whether the tumor has invasive growth. However, due to its small size, the typical features of invasiveness shown by conventional 2-dimensional (2D) US are not well visualized. US-based radiomics makes use of artificial intelligence and big data to build a model that can help improving diagnostic accuracy and providing prognostic implication of the disease. We hope to establish and assess the value of a nomogram based on US radiomics combined with independent risk factors in predicting the invasiveness of a single PTMC without clinical lymph node metastasis (cN0). A total of 317 patients with cN0 single PTMC who underwent US examination and operation were included in this retrospective cohort study. Patients were randomly divided into training and testing set in the ratio of 8:2. The US images of all patients were segmented, and the radiomics features were extracted. In the training dataset, the US with features of minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) were selected and radiomics signatures were then established according to their respective weighting coefficients. Univariate and multivariate logistic regression analyses were employed to generate the risk factors of possible invasive PTMC. The nomogram is then made by combining high risk factors and the radiomics signature. The efficiency of the nomogram was evaluated by the receiver operating characteristic (ROC) curve and calibration curve, and its clinical application value was assessed by decision curve analysis (DCA). The testing dataset was used to validate the model. In the model, seven radiomics features were selected to establish the radiomics signature. A nomogram was made by incorporating clinically independent risk factors and the radiomics signature. Both the ROC curve and calibration curve showed good prediction efficiency. The area under the curve (AUC), accuracy, sensitivity, and specificity of the nomogram in the training data were 0.76 [95% confidence interval (CI): 0.71-0.82], 0.811, 0.914, and 0.727, respectively whereas the results of the testing dataset were 0.71 (95% CI: 0.58-0.84), 0.841, 0.533, and 0.868. As such, the efficacy of the nomogram in predicting the invasiveness of PTMC was subsequently validated by the DCA. Nomogram based on thyroid US radiomics has an excellent predictive value of the potential invasiveness of a single PTMC without clinical lymph node metastasis. With these promising results, it can potentially be the imaging marker used in daily clinical practice.

Densely connected convolutional networks for ultrasound image based lesion segmentation

Delineating lesion boundaries play a central role in diagnosing thyroid and breast cancers, making related therapy plans and evaluating therapeutic effects. However, it is often time-consuming and error-prone with limited reproducibility to manually annotate low-quality ultrasound (US) images, given high speckle noises, heterogeneous appearances, ambiguous boundaries etc., especially for nodular lesions with huge intra-class variance. It is hence appreciative but challenging for accurate lesion segmentations from US images in clinical practices. In this study, we propose a new densely connected convolutional network (called MDenseNet) architecture to automatically segment nodular lesions from 2D US images, which is first pre-trained over ImageNet database (called PMDenseNet) and then retrained upon the given US image datasets. Moreover, we also designed a deep MDenseNet with pre-training strategy (PDMDenseNet) for segmentation of thyroid and breast nodules by adding a dense block to increase the depth of our MDenseNet. Extensive experiments demonstrate that the proposed MDenseNet-based method can accurately extract multiple nodular lesions, with even complex shapes, from input thyroid and breast US images. Moreover, additional experiments show that the introduced MDenseNet-based method also outperforms three state-of-the-art convolutional neural networks in terms of accuracy and reproducibility. Meanwhile, promising results in nodular lesion segmentation from thyroid and breast US images illustrate its great potential in many other clinical segmentation tasks.

Reference intervals for carotid artery intima-media thickness measurements in the multi-ethnic Asian population: relationship with cardiometabolic risk factors

Abstract Background Carotid artery intima-media thickness (cIMT) is an intermediate surrogate marker for cardiovascular disease (CVD). It has been reported that although the distribution of cIMT values is very heterogeneous and values vary widely between different ethnicity, geographic location, and ultrasound protocol, the prediction of vascular events with study-specific cIMT values is consistent across all ethnicities and regions (1). Hence, Consensus Statement from the American Society of Echocardiography suggests that cIMT greater than or equal to 75th percentile for the patient’s age, sex, and ethnicity is indicative of increased CVD risk (2). Aims We aimed to establish age, sex, and ethnic-specific reference intervals in the multi-ethnic Asian population comprising Chinese, Malays, and Indians. Methods We analysed data from 8762 healthy individuals who had a 3D carotid ultrasonography done as part of the Health for Life in Singapore study. Carotid ultrasonography measurements were taken from the distal common carotid artery (CCA) at both the lateral and posterior angles bilaterally during the end-diastolic phase. The mean of all 4 measurements were taken as average cIMT (avgcIMT). For this analysis, we excluded individuals on treatment for diabetes, hypertension, hyperlipidemia, and ischemic heart disease to derive a healthy population subset comprising of 6522 individuals (Chinese: 69%, Malays: 14%, Indians: 17%). We then assessed the 75th percentile as a marker of cardiovascular risk in all individuals, by testing associations with Framingham risk scores (locally adapted) and with cardiometabolic risk factors (3). Results Ethnic- and sex-specific 75th percentiles (95% CI) of CIMT for our Asian populations are summarised in Table 1. Compared to reference intervals reported in European and African American populations, the 75th centiles are lower in all Asian ethnic subgroups (p&amp;lt;0.05). Framingham risk score, BMI, LDL-C, HbA1c and systolic blood pressure were higher in Asians with cIMT more than 75th percentile (p&amp;lt;0.001), compared to Asians with normal cIMT. Conclusions We estimated race- and sex-specific 75th percentiles of avgcIMT across age in the multi-ethnic Asian population. The thresholds for Asian populations are substantially lower than reported in European and African populations. The 75th centiles identify people with raised cardiovascular risk factors, supporting the validity of cIMT as marker of vascular risk in the population. The 75th centiles will be useful in interpretation of cIMT measures obtained both in research and clinical settings in different ethnic populations in Asia. Longitudinal evaluation is needed to determine the prediction of our Asian specific thresholds for predicting hard cardiovascular outcomes.