Ultrasound Recordings Research Articles

Echogenicity as a standalone nodule characteristic is not inferior to the TIRADS systems in the 10-20 mm nodule diameter range in patient selection for fine needle aspiration: a pilot study.

The ultrasound evaluation of thyroid nodules (TNs) in patient selection for fine needle aspiration (FNA) requires both uniformly accepted definitions of each nodule characteristic and extensive experience from the examiner. We hypothesized that nodule echogenicity alone may provide comparable performance to more complex approaches in patient selection for FNA. Seven highly experienced investigators from four countries evaluated, online, the ultrasound (US) video recordings of 123 histologically verified TN by answering 17 nodule characteristics-related questions. The diagnostic performances of five TN image reporting and data systems (TIRADS) were compared to making decisions based solely on the echogenicity of the nodule for indicating FNA in 110 nodules ≥10 mm. In the 10-20 mm size range, the sensitivities and specificities of the five TIRADS systems in identifying malignant nodules were 80.5-91.0% and 31.4-50.9%, respectively. Had FNA been recommended for all hypoechoic nodules, disregarding other US characteristics, comparable sensitivity and specificity (87.5% and 43.4%, respectively) were obtained. Compared to nodules >20 mm, a higher proportion of cancers were hypoechoic in the 10-20 mm size range (87.2% vs 77.8%, P = 0.05). In the 10-20 mm size range, compared to hypoechoic nodules, a significantly lower proportion of isoechoic nodules demonstrated suspicious findings (70.7% vs 30.0%, P < 0.05). In contrast to >20 mm diameter nodules, the recommendation of FNA may rely on a single US feature, echogenicity, in the 10-20 mm size range. If independently confirmed in larger cohorts, this may simplify nodule evaluation in this size range.

An Evaluation of The Older Persons Presentation To The Emergency Department (ED) Following A Fall/Syncope/Presyncope

Abstract Background Falls events are a leading reason for presentations to the ED, particularly in older adults. Often these events are unwitnessed and unexplained. Therefore, there is strong consensus that the management of unexplained falls should be evaluated in a similar fashion to syncope as outlined by the World Falls and European Society of Cardiology guidelines. Methods The aim of this study was to evaluate adherence with current falls/syncope guidelines. Consecutive patients over the age of 75 who presented with a fall or syncope to a university teaching hospital in October 2023 were included. Data was collected on diagnostics completed (ECG, CT Brain, Carotid Doppler Ultrasound, EEG, pro BNP, Troponin, Echocardiogram, and External loop recorder), whether specialist falls review was performed, and readmission within 6 months. Completion of diagnostic tests were compared between those who were and were not reviewed by a specialist service using the Chi squared test. Results Falls/syncope/presyncope comprised 17.5% (160/913) of presentations of older people to the ED. Overall, 43% (n=68) had an ECG completed, 15% (n=23) had a pro BNP, and 24% (n=38) had a troponin level measured, 11% (n=17) had an Echo performed, and 10% (n=16) had prolonged cardiac monitoring (R test), 47% (n=74) had a CT Brain performed. Among those who were reviewed by a specialist falls service, (39% n= 62) completion of recommended investigations was significantly higher; ECG (69% v 26%, p&amp;lt;0.01), pro BNP (24% v 8.3%, p&amp;lt;0.01), echocardiogram (21% v 4.2%, p&amp;lt;0.01), cardiac monitoring (18% v 5.2%, p&amp;lt;0.01). Conclusion Falls and syncope are common presentations to the ED among older adults. Patients who were seen by a specialist falls team were more likely to have the appropriate diagnostics complete. Therefore, a specialist falls/syncope pathway led by a specialist falls service in the ED could result in better outcomes for patients.

Video-based AI module with raw-scale and ROI-scale information for thyroid nodule diagnosis

ObjectivesUltrasound examination is a primary method for detecting thyroid lesions in clinical practice. Incorrect ultrasound diagnosis may lead to delayed treatment or unnecessary biopsy punctures. Therefore, our objective is to propose an artificial intelligence model to increase the precision of thyroid ultrasound diagnosis and reduce puncture rates. MethodsWe consecutively collected ultrasound recordings from 672 patients with 845 nodules across two Chinese hospitals. This dataset was divided into training, validation, and internal test sets in a ratio of 7:1:2. We constructed and tested six different model variants based on different video feature distillation strategies and whether additional information from ROI (Region of Interest) scales was used. The models' performances were evaluated using the internal test set and an additional external test set containing 126 nodules from a third hospital. ResultsThe dual-stream model, which contains both raw-scale and ROI-scale streams with the time dimensional convolution layer, achieved the best performance on both internal and external test sets. On the internal test set, it achieved an AUROC (Area Under Receiver Operating Characteristic Curve) of 0.969 (95 % confidence interval, CI: 0.944–0.993) and an accuracy of 92.6 %, outperforming other variants (AUROC: 0.936–0.955, accuracy: 80.2%–88.3 %) and experienced radiologists (accuracy: 91.9 %). The AUROC of the best model in the external test was 0.931 (95 % CI: 0.890–0.972). ConclusionIntegrating a dual-stream model with additional ROI scale information and the time dimensional convolution layer can improve performance in diagnosing thyroid ultrasound videos.

Diversity and plasticity of vocalisations in an elusive and arboreal small mammal: the edible dormouse (Glis glis)

ABSTRACT The acoustics of small mammals, particularly dormice species, are generally understudied. During this study, we explored the vocalisations and acoustic behaviour of the edible dormouse (Glis glis) in various environments in Catalonia using ultrasound recorders. Up to five different types of calls were identified in various environmental conditions (captivity and free-ranging animals) and developmental stages, from pups to adults. Additionally, one new call type was described. Significant differences were observed between captive and wild dormice (e.g. length of the calls and position of the peak harmonic), enhancing the plasticity of their vocalisations. In addition, ultrasonic sound production was discovered in pups, suggesting ontogenetic changes in the vocal repertoire. The lack of differences in vocalisations between sexes reported in captivity highlight the importance of traditional monitoring methods (i.e. nest boxes) for population monitoring in the case of the edible dormouse. The potential of the acoustic method as a non-invasive tool for studying ecological behaviours and interactions, or early detection of the species in the natural environment is emphasised. This study provides an open call reference library, laying the groundwork for a better understanding of edible dormouse acoustics, and focuses on the importance of future research to explore the acoustic social behaviour of the species.

Photoacoustic imaging for non-invasive assessment of biomarkers of intestinal injury in experimental necrotizing enterocolitis.

Necrotizing enterocolitis (NEC) is an often-lethal disease of the premature infant intestinal tract, exacerbated by significant diagnostic difficulties. In NEC, the intestine exhibits hypoperfusion and dysmotility, contributing to disease pathogenesis. However, these features cannot be accurately and quantitively assessed with current imaging modalities. We have previously demonstrated the ability of photoacoustic imaging (PAI) to non-invasively assess intestinal tissue oxygenation and motility in a healthy neonatal rat model. In this first-in-disease application, we evaluated NEC using PAI to assess intestinal health biomarkers in an experimental model of NEC. NEC was induced in neonatal rats from birth to 4-days. Healthy breastfed (BF) and NEC rat pups were imaged at 2- and 4-days. Intestinal tissue oxygen saturation was measured with PAI, and NEC pups showed significant decreases at 2- and 4-days. Ultrasound and PAI cine recordings were used to capture intestinal peristalsis and contrast agent transit within the intestine. Intestinal motility, assessed using computational intestinal deformation analysis, demonstrated significant reductions in both early and established NEC. NEC damage was confirmed with histology and dysmotility was confirmed by small intestinal transit assay. This preclinical study presents PAI as an emerging diagnostic imaging modality for intestinal disease assessment in premature infants. Necrotizing enterocolitis (NEC) is a devastating intestinal disease affecting premature infants with significant mortality. NEC presents significant clinical diagnostic difficulties, with limited diagnostic confidence complicating timely and effective interventional efforts. This study is an important foundational first-in-disease preclinical study that establishes the utility for PAI to detect changes in intestinal tissue oxygenation and intestinal motility with NEC disease induction and progression. This study demonstrates the feasibility and exceptional promise for the use of PAI to non-invasively assess oxygenation and motility in the healthy and diseased infant intestine.

Constitutional thinness might be characterized by physiologically adapted and not impaired muscle function and architecture: new results from the NUTRILEAN study.

While muscle mass and skeletal muscle fibers phenotype have been shown atypical in constitutional thinness (CT), force production capacities and its architectural determinants have never been explored. The present study compared muscle functionality and architecture between participants with CT and their normal-weight (NW) counterparts. Anthropometry, body composition (Dual-X-ray Absorptiometry), physical activity/sedentary behavior (ActiGraph wGT3X-BT), ultrasound recording of the Vastus Lateralis (2D-ultrasound system), and functional capacities at maximal isometric and isokinetic voluntary contractions (MVCISO and MVCCON) during knee extension (isokinetic dynamometer chair Biodex) have been measured in 18 women with CT (body mass index < 17.5kg/m2) and 17 NW women. A lower fat-free mass (ES: -1.94, 95%CI: -2.76 to -1.11, p < 0.001), a higher sedentary time, and a trend for a lower time spent at low-intensity physical activity, were observed in CT vs NW participants. While absolute MVCISO, MVCCON, rate of torque development (RTD), and torque work were all markedly lower in CT, these differences disappeared when normalized to body or muscle mass. Muscle thickness and fascicle length were found lower in CT (ES: -1.29, 95%CI: -2.03 to -0.52, p < 0.001; and ES: -0.87, 95%CI: -1.58 to -0.15, p = 0.02, respectively), while pennation angle was found similar. Despite lower absolute strength capacities observed in CT, present findings support the hypothesis of physiological adaptations to the low body and muscle mass than to some intrinsic contractile impairments. These results call for further studies exploring hypertrophy-targeted strategies in the management of CT.

Open cranium model for the study of cerebrovascular dynamics in intracranial hypertension

BackgroundSignificant research has been devoted to developing noninvasive approaches to neuromonitoring. Clinical validation of such approaches is often limited, with minimal data available in the clinically relevant elevated ICP range. New MethodTo allow ultrasound-guided placement of an intraventricular catheter and to perform simultaneous long-duration ICP and ultrasound recordings of cerebral blood flow, we developed a large unilateral craniectomy in a swine model. We also used a microprocessor-controlled actuator for intraventricular saline infusion to reliably and reversibly manipulate ICP according to pre-determined profiles. ResultsThe model was reproducible, resulting in over 80 hours of high-fidelity, multi-parameter physiological waveform recordings in twelve animals, with ICP ranging from 2 to 78 mmHg. ICP elevations were reversible and reproducible according to two predetermined profiles: a stepwise elevation up to an ICP of 30–35 mmHg and return to normotension, and a clinically significant plateau wave. Finally, ICP was elevated to extreme levels of greater than 60 mmHg, simulating extreme clinical emergency. Comparison with existing methodsExisting methods for ICP monitoring in large animals typically relied on burr-hole approaches for catheter placement. Accurate catheter placement can be difficult in pigs, given the thickness of their skull. Additionally, ultrasound is significantly attenuated by the skull. The open cranium model overcomes these limitations. ConclusionsThe hemicraniectomy model allowed for verified placement of the intraventricular catheter, and reversible and reliable ICP manipulation over a wide range. The large dural window additionally allowed for long-duration recording of cerebral blood flow velocity from the middle cerebral artery.

Can 3D Multiparametric Ultrasound Imaging Predict Prostate Biopsy Outcome?

ObjectivesTo assess the value of 3D multiparametric ultrasound imaging, combining hemodynamic and tissue stiffness quantifications by machine learning, for the prediction of prostate biopsy outcomes. MethodsAfter signing informed consent, 54 biopsy-naïve patients underwent a 3D dynamic contrast-enhanced ultrasound (DCE-US) recording, a multi-plane 2D shear-wave elastography (SWE) scan with manual sweeping from base to apex of the prostate, and received 12-core systematic biopsies (SBx). 3D maps of 18 hemodynamic parameters were extracted from the 3D DCE-US quantification and a 3D SWE elasticity map was reconstructed based on the multi-plane 2D SWE acquisitions. Subsequently, all the 3D maps were segmented and subdivided into 12 regions corresponding to the SBx locations. Per region, the set of 19 computed parameters was further extended by derivation of eight radiomic features per parameter. Based on this feature set, a multiparametric ultrasound approach was implemented using five different classifiers together with a sequential floating forward selection method and hyperparameter tuning. The classification accuracy with respect to the biopsy reference was assessed by a group-k-fold cross-validation procedure, and the performance was evaluated by the Area Under the Receiver Operating Characteristics Curve (AUC). ResultsOf the 54 patients, 20 were found with clinically significant prostate cancer (csPCa) based on SBx. The 18 hemodynamic parameters showed mean AUC values varying from 0.63 to 0.75, and SWE elasticity showed an AUC of 0.66. The multiparametric approach using radiomic features derived from hemodynamic parameters only produced an AUC of 0.81, while the combination of hemodynamic and tissue-stiffness quantifications yielded a significantly improved AUC of 0.85 for csPCa detection (p-value < 0.05) using the Gradient Boosting classifier. ConclusionsOur results suggest 3D multiparametric ultrasound imaging combining hemodynamic and tissue-stiffness features to represent a promising diagnostic tool for biopsy outcome prediction, aiding in csPCa localization.

WILL ULTRASOUND REVOLUTIONIZE THE DIAGNOSIS OF PNEUMONIA IN CHILDREN POPULATION?

Worldwide, pneumonia continues to be a major cause of morbidity and mortality in children. The effectiveness of ultrasonography and chest radiography (X-ray) in the diagnosis of pneumonia in pediatric patients is examined in this paper. Although chest radiography has been the norm for years, worries about radiation exposure have made ultrasonography seem like a viable substitute. This article assesses both modalities' diagnostic value and accuracy through a review of recent literature. As a potentially useful diagnostic tool, ultrasonography has advantages over chest X-rays, including accessibility, low radiation dose, and similar diagnostic efficacy. Ultrasound has a high negative predictive value, which indicates that it may be used to efficiently triage patients in emergencies. The decision between an X-ray and an ultrasound ultimately comes down to several variables, such as patient condition, physician skill, and equipment accessibility. However, considering ultrasound's safety record and diagnostic capabilities, it offers a strong substitute for diagnosing pneumonia in kids, in line with WHO guidelines to reduce radiation exposure in this susceptible group.

Proposal for Diagnostic Criteria of Y-Shaped Dysmorphic Uterus Based on 3-Dimensional Transvaginal Ultrasound Measurements

Study ObjectiveTo define objective and readily applied diagnostic criteria for Y-shaped uteri using 3-dimensional transvaginal ultrasound (3D-TVUS) volume recordings. DesignA retrospective case-control diagnostic measurements study. SettingA tertiary university hospital's reproductive health and research center. PatientsTwo hundred thirteen patients who presented with infertility between January 2020 and December 2022. InterventionsTwo blinded physicians re-evaluated the 3D-TVUS images of all patients for the presence of a uterine abnormality. The images of patients with a Y-shaped uterus were re-evaluated, and descriptive measurements were done. Measurements and Main ResultsThe most common uterine abnormality in this cohort was the Y-shaped uterus with a prevalence of 12.2%, followed by the arcuate, T-shaped, and septate uteri, respectively. Reviewers identified 26 and 28 Y-shaped uteri, respectively, and came to a consensus on 25 images. Diagnostic criteria for the Y-shaped uterus based on 3D-TVUS findings have been specified as: lateral indentation depths between 4 and 7 mm, fundal indentation depth between 5 and 9 mm, lateral indentation angles between 121° and 149°, fundal indentation angle between 121° and 145°, and Y-angles 25° to 46°. ConclusionSome subtypes of dysmorphic uteri, such as the Y-shaped uterus, whose clinical significance is unknown and may be variants of the normal, may actually be more common than thought. Determining objective diagnostic criteria with 3D-TVUS will allow standard research on these anomalies and their clinical significance.

A pipeline to generate large-scale, realistic cardiac ultrasound recordings including clinically relevant artefacts

Simulated ultrasound (US) data are widely used to develop and validate (machine learning-based) US data processing algorithms. In this regard, the quantity and quality of the simulated US data are crucial. Here, we have developed an US simulation pipeline to generate realistic cardiac US recordings on a large scale. In this pipeline, we used clinical cardiac US scans to sample the echogenicity of the US scattering sites. In parallel, a non-linear US simulator, k-wave, was employed to generate clinical artifacts due to the presence of ribs and lungs, including reverberation and shadowing. The position of the ventricle, the probe, and the simulated artifact data were then spatially registered in order to modify the originally sampled echogenicities. Motion of the myocardial scattering sites was kinematically governed by a stable mechanical heart model (CircAdapt). The resulting dynamic echogenicity map was fed into a fast convolution-based ultrasound simulator (COLE) to generate cardiac US recordings with clinical appearance including artefacts. The generated US data follow realistic speckle statistics and is a potential augmentation tool for machine learning based US data processing algorithms. [Work funded by European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 860745.]

Exceptionally Uniform Bat Assemblages across Different Forest Habitats Are Dominated by Single Hyperabundant Generalist Species

Woodland bat assemblages are usually structured in a space according to the distance from the ground, water, and obstacles, features that often define chiropteran hunting tactics. Consequently, the bat species composition differs strongly among various habitats, even within the same forest patch. However, when conducting local bat surveys in Wolin National Park (WPN), we revealed an unexpected uniformity in the qualitative and quantitative structure of bat assemblages, based on mist netting and ultrasound recording. In total, 10 vespertilionid species were detected. Across all methods and sampled habitats, a single species, Pipistrellus pygmaeus, predominated, while no Barbastella barbastellus, an old forest specialist, were detected, despite the abundance of their preferred daily roosts. We also reviewed the literature for mist-netted bat samples in four different habitats in lowland Polish forests. The samples usually clustered based on habitats, and the same habitat classes often clustered very closely despite representing geographically distant forests. The exception was WPN, where all four habitat classes formed a tightly packed cluster. We hypothesize that P. pygmaeus might act as a hyperabundant native species, a successful generalist that reduces the contribution of more specialized taxa in the assemblage. It probably benefits from both forest renaturation and anthropogenic cross-boundary subsidy.

First characterisation and conservation needs of a large maternity colony of lesser horseshoe bats (Rhinolophus hipposideros) in Aljezur, Portugal

A new maternity colony of lesser horseshoe bats (Rhinolophus hipposideros) was found and described in an abandoned building in Aljezur, Portugal. Between June 25 and July 4, 2022, we conducted emergence and juvenile counts, took light intensity measurements during emergence times and evaluated microclimatic conditions inside the roost, namely temperature and relative humidity. Moreover, we took ultrasound recordings in the open and performed transects to locate foraging areas and commuting corridors. We found the colony amounted to at least 501 individuals (371 adults and 130 juveniles), currently the largest known in Portugal and one of the biggest in Europe. Sixteen matching echolocation calls were recorded away from the colony near a water reservoir, a probable foraging area together with the Vale da Telha valley connecting the roost to the water body, which may also serve as a commuting corridor. Considering the threatened conservation status of the lesser horseshoe bat, the large colony size and its lack of protection, we proposed several conservation measures aimed at preserving the colony. We hope our recommendations will be included in the management plan currently being prepared for the Natura 2000 site Costa Sudoeste. Following up on this research, a radio-tracking study would definitively confirm the bats’ movements and foraging grounds.

Navigated ultrasound bronchoscopy with integrated positron emission tomography-A human feasibility study.

Patients suspected to have lung cancer, undergo endobronchial ultrasound bronchoscopy (EBUS) for the purpose of diagnosis and staging. For presumptive curable patients, the EBUS bronchoscopy is planned based on images and data from computed tomography (CT) images and positron emission tomography (PET). Our study aimed to evaluate the feasibility of a multimodal electromagnetic navigation platform for EBUS bronchoscopy, integrating ultrasound and segmented CT, and PET scan imaging data. The proof-of-concept study included patients with suspected lung cancer and pathological mediastinal/hilar lymph nodes identified on both CT and PET scans. Images obtained from these two modalities were segmented to delineate target lymph nodes and then incorporated into the CustusX navigation platform. The EBUS bronchoscope was equipped with a sensor, calibrated, and affixed to a 3D printed click-on device positioned at the bronchoscope's tip. Navigation accuracy was measured postoperatively using ultrasound recordings. The study enrolled three patients, all presenting with suspected mediastinal lymph node metastasis (N1-3). All PET-positive lymph nodes were displayed in the navigation platform during the EBUS procedures. In total, five distinct lymph nodes were sampled, yielding malignant cells from three nodes and lymphocytes from the remaining two. The median accuracy of the navigation system was 7.7 mm. Our study introduces a feasible multimodal electromagnetic navigation platform that combines intraoperative ultrasound with preoperative segmented CT and PET imaging data for EBUS lymph node staging examinations. This innovative approach holds promise for enhancing the accuracy and effectiveness of EBUS procedures.

Inspiratory Muscle Dysfunction Mediates and Predicts a Disease Continuum of Hypercapnic Failure in Chronic Obstructive Pulmonary Disease.

Advanced chronic obstructive pulmonary disease (COPD) is associated with chronic hypercapnic failure. The present work aimed to comprehensively investigate inspiratory muscle function as a potential key determinant of hypercapnic respiratory failure in patients with COPD. Prospective patient recruitment encompassed 61 stable subjects with COPD across different stages of respiratory failure, ranging from normocapnia to isolated nighttime hypercapnia and daytime hypercapnia. Arterialized blood gas analyses and overnight transcutaneous capnometry were used for patient stratification. Assessment of respiratory muscle function encompassed body plethysmography, maximum inspiratory pressure (MIP), diaphragm ultrasound, and transdiaphragmatic pressure recordings following cervical magnetic stimulation of the phrenic nerves (twPdi) and a maximum sniff manoeuvre (Sniff Pdi). Twenty patients showed no hypercapnia, 10 had isolated nocturnal hypercapnia, and 31 had daytime hypercapnia. Body plethysmography clearly distinguished patients with and without hypercapnia but did not discriminate patients with isolated nocturnal hypercapnia from those with daytime hypercapnia. In contrast to ultrasound parameters and transdiaphragmatic pressures, only MIP reflected the extent of hypercapnia across all three stages. MIP values below -48 cmH2O predicted nocturnal hypercapnia (area under the curve = 0.733, p = 0.052). In COPD, inspiratory muscle dysfunction contributes to progressive hypercapnic failure. In contrast to invasive tests of diaphragm strength only MIP fully reflects the pathophysiological continuum of hypercapnic failure and predicts isolated nocturnal hypercapnia.

Combining ultrasound and microelectrode recordings for postoperative localization of subthalamic electrodes in Parkinson’s disease

ObjectiveTo assess transcranial sonography (TCS) as stand-alone tool and in combination with microelectrode recordings (MER) as a method for the postoperative localization of deep brain stimulation (DBS) electrodes in the subthalamic nucleus (STN). MethodsIndividual dorsal and ventral boundaries of STN (n = 12) were determined on intraoperative MER. Postoperatively, a standardized TCS protocol was applied to measure medio-lateral, anterior-posterior and rostro-caudal electrode position using visualized reference structures (midline, substantia nigra). TCS and combined TCS-MER data were validated using fusion-imaging and clinical outcome data. ResultsTest-retest reliability of standard TCS measures of electrode position was excellent. Computed tomography and TCS measures of distance between distal electrode contact and midline agreed well (Pearson correlation; r = 0.86; p < 0.001). Comparing our “gold standard” of rostro-caudal electrode localization relative to STN boundaries, i.e. combining MRI-based stereotaxy and MER data, with the combination of TCS and MER data, the measures differed by 0.32 ± 0.87 (range, −1.35 to 1.25) mm. Combined TCS-MER data identified the clinically preferred electrode contacts for STN-DBS with high accuracy (Coheńs kappa, 0.86). ConclusionsCombined TCS-MER data allow for exact localization of STN-DBS electrodes. SignificanceOur method provides a new option for monitoring of STN-DBS electrode location and guidance of DBS programming in Parkinson’s disease.

Bedside Ultrasound to Identify and Predict Severity of Dysphagia Following Ischemic Stroke: Human Versus Artificial Intelligence

Dysphagia is a significant ischemic stroke complication that can lead to aspiration. Identification of at-risk patients can be logistically difficult and costly. Researchers investigated whether quantitative ultrasound assessment of hyoid bone movement during induced swallowing would predict failure of videofluoroscopy (VFS) or fiberoptic endoscopic evaluation of swallowing (FEES), as determined by a penetration-aspiration scale (PAS) score. Additionally, ability of a machine learning (ML) algorithm to predict PAS success or failure from real-time ultrasound video recordings was assessed. A prospective, single-blinded, observational pilot study was conducted from June 2019 through March 2020 at a comprehensive stroke center on a convenience sample of patients admitted with diagnosis of acute ischemic stroke undergoing VFS or FEES as part of dysphagia assessment. Researchers performed a midsagittal airway ultrasound during swallowing in patients receiving an objective swallowing assessment by speech language pathologists who were blinded to ultrasound results. Sonologists measured hyoid bone movement, and researchers then constructed an ML algorithm designed for real-time video analysis using a long short-term memory network with an embedded VGG16 convolutional neural network. Videos from 69 patients were obtained with their respective PAS results. In total, 90% of available videos were used for algorithm training. After training, the ML algorithm was challenged with the 10% previously unseen videos and then compared with PAS outcomes. Statistical analysis included logistic regression and correlation matrix testing on human ultrasound measurements. Cohen's κ was calculated to compare deep learning algorithm prediction with PAS results. Measurement of hyoid bone elevation, forward displacement, total displacement and mandible length was unable to predict PAS assessment outcome (p values=0.36, 0.13, 0.11 and 0.32, respectively). The ML algorithm showed substantial agreement with PAS testing results for predicting test outcome (κ=0.79; 95% confidence interval: 0.52-1.0) CONCLUSION: Manual ultrasound measurement of hyoid movement during swallowing in stroke patients failed to predict PAS swallowing results. However, an ML algorithm showed substantial agreement with PAS results despite a small data set, which could greatly improve access to dysphagia assessment in the future.

Central-to-peripheral blood pressure amplification: role of the recording site, technology, analysis approach, and calibration scheme in invasive and non-invasive data agreement.

Systolic blood pressure amplification (SBPA) and pulse pressure amplification (PPA) can independently predict cardiovascular damage and mortality. A wide range of methods are used for the non-invasive estimation of SBPA and PPA. The most accurate non-invasive method for obtaining SBPA and/or PPA remains unknown. This study aims to evaluate the agreement between the SBPA and PPA values that are invasively and non-invasively obtained using different (1) measurement sites (radial, brachial, carotid), (2) measuring techniques (tonometry, oscillometry/plethysmography, ultrasound), (3) pulse waveform analysis approaches, and (4) calibration methods [systo-diastolic vs. approaches using brachial diastolic and mean blood pressure (BP)], with the latter calculated using different equations or measured by oscillometry. Invasive aortic and brachial pressure (catheterism) and non-invasive aortic and peripheral (brachial, radial) BP were simultaneously obtained from 34 subjects using different methodologies, analysis methods, measuring sites, and calibration methods. SBPA and PPA were quantified. Concordance correlation and the Bland-Altman analysis were performed. (1) In general, SBPA and PPA levels obtained with non-invasive approaches were not associated with those recorded invasively. (2) The different non-invasive approaches led to (extremely) dissimilar results. In general, non-invasive measurements underestimated SBPA and PPA; the higher the invasive SBPA (or PPA), the greater the underestimation. (3) None of the calibration schemes, which considered non-invasive brachial BP to estimate SBPA or PPA, were better than the others. (4) SBPA and PPA levels obtained from radial artery waveform analysis (tonometry) (5) and common carotid artery ultrasound recordings and brachial artery waveform analysis, respectively, minimized the mean errors. Overall, the findings showed that (i) SBPA and PPA indices are not "synonymous" and (ii) non-invasive approaches would fail to accurately determine invasive SBPA or PPA levels, regardless of the recording site, analysis, and calibration methods. Non-invasive measurements generally underestimated SBPA and PPA, and the higher the invasive SBPA or PPA, the higher the underestimation. There was not a calibration scheme better than the others. Consequently, our study emphasizes the strong need to be critical of measurement techniques, to have methodological transparency, and to have expert consensus for non-invasive assessment of SBPA and PPA.

Automated estimation of mitral annular plane systolic excursion by artificial intelligence from 3D ultrasound recordings

Perioperative monitoring of cardiac function is beneficial for early detection of cardiovascular complications. The standard of care for cardiac monitoring performed by trained cardiologists and anesthesiologists involves a manual and qualitative evaluation of ultrasound imaging, which is a time-demanding and resource-intensive process with intraobserver- and interobserver variability. In practice, such measures can only be performed a limited number of times during the intervention. To overcome these difficulties, this study presents a robust method for automatic and quantitative monitoring of cardiac function based on 3D transesophageal echocardiography (TEE) B-mode ultrasound recordings of the left ventricle (LV). Such an assessment obtains consistent measurements and can produce a near real-time evaluation of ultrasound imagery. Hence, the presented method is time-saving and results in increased accessibility. The mitral annular plane systolic excursion (MAPSE), characterizing global LV function, is estimated by landmark detection and cardiac view classification of two-dimensional images extracted along the long-axis of the ultrasound volume. MAPSE estimation directly from 3D TEE recordings is beneficial since it removes the need for manual acquisition of cardiac views, hence decreasing the need for interference by physicians. Two convolutional neural networks (CNNs) were trained and tested on acquired ultrasound data of 107 patients, and MAPSE estimates were compared to clinically obtained references in a blinded study including 31 patients. The proposed method for automatic MAPSE estimation had low bias and low variability in comparison to clinical reference measures. The method accomplished a mean difference for MAPSE estimates of (−0.16±1.06) mm. Thus, the results did not show significant systematic errors. The obtained bias and variance of the method were comparable to inter-observer variability of clinically obtained MAPSE measures on 2D TTE echocardiography. The novel pipeline proposed in this study has the potential to enhance cardiac monitoring in perioperative- and intensive care settings.

Studying the discipline of free choice «Ultrasound Diagnostics in Obstetrics and Gynaecology»

Today, in the education system, an important opportunity for higher education applicants is the right to form an individual educational trajectory according to the relevant qualification level. Higher education seekers have received not only academic mobility but also the opportunity to study disciplines to consciously choose their specialty and study it more deeply. The skills of ultrasound diagnostics increase the professional level of a doctor of any specialization and open wide diagnostic possibilities.The article reveals the peculiarity of studying one of the subjects of free choice by medical higher education applicants on the basis of Odesa National Medical University – “Ultrasound Diagnostics in Obstetrics and Gynaecology”. The adaptation of the educational process in a mixed format with the possibility of using digital learning technologies and mastering professional skills on ultrasound machines of different classes is described. In the course of studying the discipline, the necessary basic digital skills of using an ultrasound scanner and knowledge of the main visualization modes, adjustment principles, as well as sets of functional capabilities inherent in all modern devices are formed.The method of presentation of theoretical information and the use of case scenarios during the discussion of clinical tasks with mandatory visualization of ultrasound video recordings is described. The applicants’ digital skills are directly related to the course being studied and are necessary to master the proposed professional field. The possibility of learning using the latest medical equipment in combination with the use of digital learning tools and video resources contributes to the acquisition of professional competence and the formation of responsibility and interest of students. In the process of training manual scanning skills, the doctor’s thinking and the ability to analyze and interpret the received ultrasound data are formed. Practical classes help to discuss the most interesting issues for this specific group of higher education applicants in a comfortable and trusting environment. The use of a combined approach in the presentation of the material, the author’s style and the format of the transfer of professional skills by experienced teachers who are engaged in constant practical activities motivate, improve the training process and give a high result.