Ultrasound Interpretation Research Articles

Deep learning-based age estimation using B-mode ultrasound tongue imaging

The feasibility of age estimation is explored using the ultrasound tongue image of the speakers. Motivated by the success of deep learning, a deep convolutional neural network model is trained on the UltraSuite dataset. The deep model achieves mean absolute error (MAE) of 2.03 years for the data from typically developing children, while MAE is 4.87 for the data from the children with speech sound disorders, which suggest that age estimation using ultrasound is more challenging for the children with speech sound disorder. Also, we explore to visualize what does the deep model learn for the age estimation task. We firstly visualize the convolutional layers in the learned convolutional neural networks. We observe that the deep model not only focuses on the contour in the ultrasound tongue image, but also pays more attention to the regions corresponding to the tendon and tongue root regions, which may provide guidance for future ultrasound tongue imaging interpretation tasks. The developed method can be used a tool to evaluate the performance of speech therapy sessions.

POINT-OF-CARE ULTRASOUND CURRICULUM FOR INTERNAL MEDICINE RESIDENTS: A SINGLE-CENTER EXPERIENCE

TOPIC: Education, Research, and Quality Improvement TYPE: Original Investigations PURPOSE: Point-of-care ultrasound (POCUS) has been used widely by pulmonary and critical care physicians/trainees for years with the recent trend of integrating similar curriculums in internal medicine resident training. It is known to supplement the physical exam, aide to accurate diagnosis and improved patient care. Here, we demonstrate that a curriculum including didactics combined with single hands on session not only increases the knowledge of ultrasound basics among the internal medicine trainees but also enhance their skill level, accuracy and confidence to image acquisition and interpretation. METHODS: Internal medicine residents and internal medicine-pediatric residents were invited to participate in this internal medicine ultrasound curriculum. As a part of curriculum all residents first attended two detailed POCUS didactic sessions and completed online ultrasound modules followed by hands on sessions which started with an hour of quick review of previously held didactics and three hours of performing ultrasound image acquisition and interpretation on standardized patients on three stations. Each station had a specific task assigned including lung ultrasound, limited cardiac views, abdominal ultrasound as well as basics of ultrasound including knobology and artifacts. Residents took a pretest with 20 questions on the subject of POCUS basics and organ system findings then same questions were posed in posttest after conclusion of the session. Standardized feedback was then obtained from residents. Each station was supervised by a critical care physician or an internal medicine physician with formal training in basic ultrasound. Session also included a computerized ultrasound manikin to familiarize residents with pathological ultrasonographic findings. RESULTS: 54 residents of all post graduate years participated in our pilot POCUS curriculum. For the pre-test the mean score is 15.87(81%) (Minimum 11 and maximum 20) whereas for post-test the mean score is 17.47 (88.95%) (Minimum 14 and maximum 20). This difference was statistically significant with p < 0.001 (Mann Whitney U test). Standardized feedback obtained from the trainees revealed that 99% felt the session stimulated their interest and thinking and they would like more hands on session to enhance their skills. 98% of the trainees said the session motivated them to continue learning ultrasound, found it practical and relevant to their field of practice and improved their ability to manage patients. All appreciated practicing ultrasound on a standardized patient to learn normal anatomy. CONCLUSIONS: This pilot confirmed that the didactics combined with single hands on session did improve knowledge, skills and confidence to use ultrasound in the internal medicine residents. CLINICAL IMPLICATIONS: We plan to make this curriculum a yearly activity with integration of new ultrasound elective for two weeks along with continued bedside teaching. DISCLOSURES: No relevant relationships by Harmeen Goraya, source=Web Response No relevant relationships by Gayathri Krishnan, source=Web Response No relevant relationships by Keyur Vyas, source=Web Response No relevant relationships by Cody Webster, source=Web Response

379 Reliability of Cardiopulmonary Ultrasound Interpretation During Resuscitation of Patients With Suspected Septic Shock

Emergency medicine (EM) clinicians who care for critically ill patients often make clinical decisions with relatively little information. Patients with septic shock in particular pose a challenge as they frequently require several time-sensitive decisions. Point-of-care cardiopulmonary ultrasound (CPUS) has emerged as a promising, rapidly available test to assess patient volume and respiratory status to guide interventions. The purpose of this study is to assess the reliability of real-time clinician interpretation of CPUS findings. We performed a prospective, observational, pilot study enrolling patients with hypotension (systolic blood pressure <90) and clinician suspected infection. Clinicians performed a focused CPUS and recorded their interpretation on a data entry form. Two ultrasound fellowship trained physicians recorded an “expert” interpretation of the recorded images. Disagreement between the two experts were resolved in a consensus conference by the study team, and the final expert consensus agreement was compared to the recorded clinician interpretation. Cardiac variables included left ventricular systolic function (LVF), right ventricular (RV) function, RV size. Lung ultrasound (LUS) was interpreted for absence of B-lines and presence of unilateral or bilateral B-lines. We enrolled 51 patients. Cohen’s kappa interrater coefficient and percent agreement are shown in Table 1. LUS showed the highest agreement between expert and clinician, Cohen’s kappa = 0.73 (95% CI: 0.51 to 0.95), indicating substantial agreement. RV function showed very poor agreement, Cohen’s kappa = -0.05 (95% CI: -0.6 to 0.5). Interpretation of LV function and RV size demonstrated fair to moderate agreement, Cohen’s kappa = 0.37 (95% CI: 0.1 to 0.64) and 0.47 (95% CI: 0.07 to 0.88). LUS findings exhibit the highest reliability when interpreted by clinicians compared to expert reviewer. Care must be exercised when interpreting CPUS variables in an acute setting, especially with respect to cardiac findings. Further work is needed to understand patient- and sonographer-specific variables which may contribute to unreliable CPUS interpretation.

Virtual multispecialty point-of-care ultrasound rotation for fourth-year medical students during COVID-19: Innovative teaching techniques improve ultrasound knowledge and image interpretation.

ObjectivesPoint‐of‐care ultrasound (PoCUS) has been integrated into undergraduate medical education. The COVID‐19 pandemic forced medical schools to evolve clinical rotations to minimize interruption through implementation of novel remote learning courses. To address the students’ need for remote clinical education, we created a virtual PoCUS course for our fourth‐year class. We present details of the course's development, implementation, quality improvement processes, achievements, and limitations.MethodsA virtual PoCUS course was created for 141 fourth‐year medical students. The learning objectives included ultrasound physics, performing and interpreting ultrasound applications, and incorporating PoCUS into clinical decisions and procedural guidance. Students completed a 30‐question pre‐ and posttest focused on ultrasound and knowledge of clinical concepts. PoCUS educators from 10 different specialties delivered the course over 10 days using video‐conferencing software. Students watched live scanning demonstrations and practiced ultrasound probe maneuvers using a cellular telephone to simulate ultrasound probe. Students completed daily course evaluations that were used as a continuous needs assessment to make improvements.ResultsA total of 141 students participated in the course; all received a passing grade. The mean pre‐ and posttest scores improved from 58% to 88% (p < 0.001) through the course duration. Daily evaluations revealed the percentage of students who rated the course's live scanning sessions and didactic components as “very well” increased from 32.7% on day 1 to 69.7% on day 10. The end‐of‐course evaluation revealed that 91% of students agreed they received effective teaching.ConclusionsIn response to the COVID‐19 pandemic, our multispecialty faculty expeditiously developed a virtual PoCUS curriculum for the entire fourth‐year class. This innovative course improved students’ ultrasound knowledge, image interpretation, and clinical application while utilizing novel techniques to teach a hands‐on skill virtually. As the demand for PoCUS instruction continues to increase, the accessibility of virtual training and blended learning will be beneficial.

The Inter-Rater Reliability of Pediatric Point-of-Care Lung Ultrasound Interpretation in Children With Acute Respiratory Failure.

Use of point-of-care lung ultrasound (POC-LUS) has increased significantly in pediatrics yet it remains under-studied in the pediatric intensive care unit (PICU). No studies explicitly evaluate the reliability of POC-LUS artifact interpretation among critically ill children with acute respiratory failure (ARF) in the PICU. We thus designed this study to determine the inter-rater reliability of POC-LUS interpretation in pediatric ARF among pediatric intensivists trained in POC-LUS and an expert intensivist. We compared the interpretation of lung sliding, pleural line characteristics, ultrasound artifacts, and POC-LUS diagnoses among pediatric intensivists and an expert intensivist in a cohort of children admitted to the PICU for ARF. Kappa statistics (k) adjusted for maximum attainable agreement (k/kmax ) were used to quantify chance-correct agreement between the pediatric intensivist and expert physician. We enrolled 88 patients, evaluating 3 zones per hemithorax (anterior, lateral, and posterior) for lung sliding, pleural line characteristics, ultrasound artifacts, and diagnosis. There was moderate agreement between the PICU intensivist and expert-derived diagnoses with 56% observed agreement (k/kmax = 0.46, 95% confidence interval [CI] 0.31-0.65). Agreement in identification of lung sliding (k= 0.19, 95% CI -0.17 to 0.56) and pleural line characteristics (k= 0.24, 95% CI 0.08-0.40) was slight and fair, respectively, while agreement in the interpretation of ultrasound artifacts ranged from moderate to substantial. Evidence supporting the evaluation of neonatal and adult patients with POC-LUS should not be extrapolated to critically ill pediatric patients. This study adds to the evidence supporting use of POC-LUS in the PICU by demonstrating moderate agreement between PICU intensivist and expert-derived POC-LUS diagnoses.

Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries.

Wrist trauma is common in children, typically requiring radiography for diagnosis and treatment planning. However, many children do not have fractures and are unnecessarily exposed to radiation. Ultrasound performed at bedside could detect fractures prior to radiography. Modern tools including three-dimensional ultrasound (3DUS) and artificial intelligence (AI) have not yet been applied to this task. Our purpose was to assess (1) feasibility, reliability, and accuracy of 3DUS for detection of pediatric wrist fractures, and (2) accuracy of automated fracture detection via AI from 3DUS sweeps. Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned on both the affected and unaffected limb. Radiographs of the symptomatic limb were obtained for comparison. Ultrasound scans were read by three individuals to determine reliability. An AI network was trained and compared against the human readers. Thirty participants were enrolled, resulting in scans from fifty-five wrists. Readers had a combined sensitivity of 1.00 and specificity of 0.90 for fractures. AI interpretation was indistinguishable from human interpretation, with all fractures detected in the test set of 36 images (sensitivity = 1.0). The high sensitivity of 3D ultrasound and automated AI ultrasound interpretation suggests that ultrasound could potentially rule out fractures in the emergency department.

Examining ultrasound diagnostic performance improvement with utilization of maternal-fetal medicine tele-interpretation

Telemedicine can extend essential health services to under-resourced settings and improve the quality of obstetrical care. Specifically, the evaluation and management of fetal anomalies require perinatal subspecialists, rendering prenatal diagnosis essential, and may benefit from telemedicine platforms to improve access to care. This study aimed to evaluate the impact of a maternal-fetal medicine telemedicine ultrasound program on the diagnostic accuracy of fetal anomalies when used within practices where ultrasounds are interpreted by general obstetricians or family medicine physicians. This was a cross-sectional study of all patients receiving care at 11 private obstetrical practices and imaging centers who had obstetrical ultrasounds performed from January 1, 2020, to July 6, 2020. All ultrasounds were performed by sonographers remotely trained under a standardized protocol and interpreted by maternal-fetal medicine physicians via telemedicine. Ultrasound characteristics and interpretation were extracted from ultrasound reports. Before the introduction of maternal-fetal medicine telemedicine, all ultrasound interpretations were reviewed by general obstetricians and family medicine physicians with reliance predominantly on the sonographer's impression. The primary outcome was potential missed diagnosis of a fetal anomaly, defined as an ultrasound designated as normal by a sonographer but diagnosed with an anomaly by a maternal-fetal medicine physician via telemedicine. This outcome serves as a proxy measure for anomaly diagnoses that would likely be missed without the supervision of a maternal-fetal medicine physician. The characteristics of the potential missed diagnoses were compared by type of scan and fetal organ system in univariable analysis. Moreover, a survey was conducted for sonographers and obstetrical providers to assess their perceptions of ultrasound interpretation via telemedicine. Overall, 6403 ultrasound examinations were evaluated, 310 of which had a diagnosis of fetal anomaly by a maternal-fetal medicine physician (4.8%). Of the fetal anomalies, 43 were diagnosed on an anatomic survey (13.9%), and 89 were diagnosed as cardiac anomalies (28.7%). The overall rate of the potential missed diagnoses was 34.5% and varied significantly by type of ultrasound (anatomy scans vs other first-, second-, and third-trimester ultrasounds) (P<.01). Moreover, there were significant differences in the rate of the potential missed diagnoses by organ system, with the highest rate for cardiac anomalies (P<.01). Expertise in maternal-fetal medicine telemedicine improves the diagnostic performance of antenatal ultrasound throughout pregnancy. However, there are implications for improving the quality of antenatal care, such as ensuring appropriate referrals and site of delivery, particularly for cardiac anomalies.

DIAGNOSTIC PERFORMANCE OF ULTRASONOGRAPHY FOR DETECTION OF ABRUPTION AND ITS CLINICAL CORRELATION AND MATERNAL AND FETAL OUTCOME

Placental abruption complicates about 1% of singleton pregnancies and is an important cause of perinatal mortality and morbidity. Though sensitivity and reliability of ultrasound are poor for detecting or excluding placental abruption, because of the advances in ultrasound resolution, imaging and interpretation, sensitivity of ultrasound is better than what was reported previously. To determine the diagnostic performance of Aim: Ultrasonography (USG) for the detection of placental abruption and whether sonographic results correlate with maternal and foetal management and outcome Sixty patients with clinical diagnosis of placental abruption we Materials and Methods: re studied in the Obstetrics and Gynaecology Department of Gujarat Adani Institute of Medical Sciences, Bhuj over a period of 6 months. These patients underwent ultrasonography for conrmation. Obstetric and neonatal outcome and sonographic results were compared and reviewed. Sonographic sensitivity and specicity and positive and negative predictive values were calculated. Incidence of abruption in present study was 3.05% (56 Results: patients out of 1834 total deliveries). Sensitivity of ultrasonography in the diagnosis of abruption was 57% while its specicity was 100% with a positive predictive value of 100% and a 14% negative predictive value. An 87.5% of patients(28 out of 32) with a positive USG nding of abruption had Intrauterine foetal Death (IUD)/still birth while 91.6% of patients (22 out of 24) with negative USG ndings of abruption gave birth to babies who required NICU admission. Sonography has a poor sensitivity for diagnosing placental abrupt Conclusion: ion, even though it has a high specicity and PPV. In a positive sonographic result, maternal morbidity and perinatal mortality are high which needs aggressive obstetric management as compared to the normal sonography. In case of a negative sonographic nding but a strong clinical suspicion of abruption if Obstetric intervention is made in due time, foetal as well as maternal outcome are better

Influence of clinical experience on accuracy and safety of obliquus capitus inferior dry needling in unembalmed cadavers

ABSTRACT Background Suboccipital myofascial trigger points are common in tension-type headaches. Objectives Compare the influence of clinical experience on the accuracy and safety of dry needle placement on the C2 laminar arch using a cranial-medial and caudal-medial technique to target obliquus capitus inferior in unembalmed cadavers. Methods Three physical therapists inserted three 50 mm dry needles, per technique, individually toward the C2 laminar arch targeting the obliquus capitus inferior. Ultrasound video of each trial was recorded, and an investigator trained in ultrasound interpretation and blinded to experience level recorded needling accuracy. Results The novice, experienced and expert clinicians were accurate on 73.8%, 59.5% and 71.4% of caudal-medial trials, and 14.3%, 16.7% and 66.7% of cranial-medial trials, respectively, with each clinician striking the spinal cord at least once. The expert clinician was 10 times more likely to accurately reach the C2 laminar arch using the cranial-medial direction than the experienced and novice clinicians. Conclusion Increased clinical experience improved accuracy reaching the C2 laminar arch, with all investigators being more accurate with the caudal-medial technique. Greater experience did not eliminate risk as all investigators recorded at least one incident of striking the spinal cord. Fewer spinal cord strikes occurred with the cranial-medial than the caudal-medial technique.

A regional multicentric survey on variability and accuracy in lung ultrasound interpretation during the COVID-19 pandemic.

A regional multicentric survey on variability and accuracy in lung ultrasound interpretation during the COVID-19 pandemic.

627 Examining ultrasound diagnostic performance improvement when utilizing maternal-fetal medicine interpretation

Telemedicine can extend essential health services to under-resourced settings and improve level and quality of care. Fetal anomalies often require subspecialty perinatal care, rendering prenatal diagnosis essential. This study examines the impact of a maternal-fetal medicine (MFM) tele-ultrasound program on diagnostic accuracy of fetal anomalies when in-person MFM is unavailable. This is a cross-sectional study of all patients receiving care at one of eleven private obstetric practices and imaging centers who had an obstetric ultrasound from January 1 - July 6, 2020. All ultrasounds were performed by sonographers remotely trained under a standardized protocol and interpreted by MFM physicians via telemedicine. Ultrasound characteristics and interpretation were extracted from ultrasound reports. Prior to introduction of tele-MFM, all ultrasounds were reviewed by general OB/GYN and family practitioners with reliance predominantly on the sonographer’s impression. The primary outcome was potential missed diagnosis of a fetal anomaly, defined as an ultrasound designated normal by the sonographer but diagnosed with an anomaly by tele-MFM. These serve as a measure for anomaly diagnoses that would be missed without MFM supervision. Characteristics of potential missed diagnoses were compared by type of scan and fetal organ system in univariable analysis. 6,403 ultrasounds were evaluated, 310 of which had a diagnosis of a fetal anomaly (4.8%) with 89 cardiac anomalies. 43 of the anomalies were diagnosed on anatomic survey (13.9%) (Table 1). The overall rate of potential missed diagnoses was 34.5% and varied significantly by type of ultrasound (p < 0.01). There were significant differences in the rate of potential missed diagnoses by organ system, with the highest rate for cardiac anomalies (p< 0.01) (Table 2). MFM expertise improves diagnostic performance of antenatal ultrasound throughout pregnancy. This has implications for improving quality of antenatal care by ensuring appropriate referrals and site of delivery, particularly for cardiac anomalies.View Large Image Figure ViewerDownload Hi-res image Download (PPT)

Integrating Focused Cardiac Ultrasound Into Pediatric Septic Shock Assessment.

To assess focused cardiac ultrasound impact on clinician hemodynamic characterization of patients with suspected septic shock as well as expert-generated focused cardiac ultrasound algorithm performance. Retrospective, observational study. Single-center, noncardiac PICU. Less than 18 years old receiving focused cardiac ultrasound study within 72 hours of sepsis pathway initiation from January 2014 to December 2016. Hemodynamics of patients with suspected septic shock were characterized as fluid responsive, myocardial dysfunction, obstructive physiology, and/or reduced systemic vascular resistance by a bedside clinician before and immediately following focused cardiac ultrasound performance. The clinician's post-focused cardiac ultrasound hemodynamic assessments were compared with an expert-derived focused cardiac ultrasound algorithmic hemodynamic interpretation. Subsequent clinical management was assessed for alignment with focused cardiac ultrasound characterization and association with patient outcomes. Seventy-one patients with suspected septic shock (median, 4.7 yr; interquartile range, 1.6-8.1) received clinician performed focused cardiac ultrasound study within 72 hours of sepsis pathway initiation (median, 2.1 hr; interquartile range, -1.5 to 11.8 hr). Two patients did not have pre-focused cardiac ultrasound and 23 patients did not have post-focused cardiac ultrasound hemodynamic characterization by clinicians resulting in exclusion from related analyses. Post-focused cardiac ultrasound clinician hemodynamic characterization differed from pre-focused cardiac ultrasound characterization in 67% of patients (31/46). There was substantial concordance between clinician's post-focused cardiac ultrasound and algorithm hemodynamic characterization (33/48; κ = 0.66; CI, 0.51-0.80). Fluid responsive (κ = 0.62; CI, 0.40-0.84), obstructive physiology (к = 0.87; CI, 0.64-1.00), and myocardial dysfunction (1.00; CI, 1.00-1.00) demonstrated substantial to perfect concordance. Management within 4 hours of focused cardiac ultrasound aligned with algorithm characterization in 53 of 71 patients (75%). Patients with aligned management were less likely to have a complicated course (14/52, 27%) compared with misaligned management (8/19, 42%; p = 0.25). Incorporation of focused cardiac ultrasound in the evaluation of patients with suspected septic shock frequently changed a clinician's characterization of hemodynamics. An expert-developed algorithm had substantial concordance with a clinician's post-focused cardiac ultrasound hemodynamic characterization. Management aligned with algorithm characterization may improve outcomes in children with suspected septic shock.

Point-of-care lung ultrasound patterns in late third-trimester gravidas with and without preeclampsia

Transthoracic point-of-care ultrasonography of the lungs has become a standard technique in critical care medicine for the evaluation of patients with respiratory signs or symptoms but has not been well studied in pregnancy. To compare lung ultrasound patterns in third-trimester gravidas with and without preeclampsia and assess interobserver agreement between 3 obstetrical providers and a physician expert in critical care lung ultrasound. This is a prospective observational study of 262 women with singleton pregnancies between 32 0/7 and 41 6/7 weeks' gestation. Lung ultrasound examinations were performed and interpreted by a team of obstetrical care providers and then interpreted by an expert in point-of-care lung ultrasound. The number of B-lines in each of the 4 lung fields, indicating the accumulation of fluid in the interstitial space and the alveoli, was evaluated. The primary outcome was a positive study for pulmonary interstitial edema, defined as an ultrasound study with 3 or more B-lines in 2 or more bilateral lung fields. The secondary outcome was a lung ultrasound study with 1 or 2 B-lines in 1 or more lung fields or 3 B-lines in 1 lung field. Interobserver agreement in lung ultrasound interpretation between obstetrical care providers and an expert in critical care point-of-care ultrasonography of the lung was assessed. Among healthy gravidas, no subject had a lung ultrasound examination positive for pulmonary interstitial edema. Notably, 2 patients with preeclampsia had positive lung ultrasound studies, and both had respiratory symptoms or signs of pulmonary edema. One or 2 B-lines or 3 B-lines in 1 lung field were identified in 11.4% of healthy gravidas and 18.6% of patients with preeclampsia. There was no difference in lung ultrasound patterns between healthy gravidas and those with preeclampsia. The obstetrical care providers and the lung ultrasound expert had a high proportion of agreement regarding the interpretation of negative lung ultrasound examinations. The 2 patients with clinical signs of pulmonary edema were judged to have positive studies by both the obstetrical team and the expert; however, the obstetrical team classified more studies as positive. Lung ultrasound patterns in women with preeclampsia without respiratory symptoms or clinical signs of pulmonary edema are similar to the lung ultrasound patterns of healthy gravidas. Point-of-care lung ultrasound can be used to evaluate third-trimester gravidas with preeclampsia and respiratory complaints or signs concerning for pulmonary edema. Formal training is important before the widespread adoption of point-of-care lung ultrasound by obstetrical healthcare providers.

Artificial Intelligence and Robotics in Regional Anaesthesia: Do they have a role?

Artificial Intelligence and Robotics in Regional Anaesthesia: Do they have a role?

Implementation of Ultrasound in Anatomy Education.

The use of different ways to view the body has always been associated with anatomy. With advancing technology, the use of ultrasound has become more portable and accessible as a way for students to learn anatomy. Moreover, ultrasound's direct clinical context makes it an important skill that students need to acquire and be competent in, not only after graduation but on clinical placements as a student. There does appear to be a learned skill in being able to interpret ultrasound images and to be able to relate the anatomy seen to existing anatomical knowledge. In addition, there is a learned skill in being able to correctly hold the ultrasound probe and gain clear images. Because ultrasound use and interpretation is a skill it therefore needs to be taught as part of undergraduate medical and allied health care professional education. A key to successful training is regular teaching sessions distributed longitudinally throughout the curriculum with active, hands-on learning time being the focus of any teaching session.

Integration of Lung Point-of-care Ultrasound into Clinical Decision Making for Medical Students in Simulated Cases.

BackgroundPoint-of-care ultrasound (POCUS) has an emerging presence in medical student education; however, there is limited evidence that this translates into appropriate clinical care. We aimed to evaluate the ability of medical students to integrate newly obtained POCUS knowledge into simulated clinical cases.MethodsWe conducted an observational study of medical students participating in a mandatory rotation during their clinical years. Students in small groups underwent formalized lung POCUS lectures and hands-on training. Students participated in simulated “dyspnea” cases focused on either congestive heart failure (CHF) or chronic obstructive pulmonary disease (COPD). They were observed for critical actions including elements related to medical decision-making and ultrasound use and interpretation. Ultrasound-specific written knowledge was gauged with a short assessment after the first lecture and at week 4.ResultsA total of 62 students participated and were observed during simulations. All groups correctly identified and treated CHF in the simulated case. Most groups (7 out of 9) attempted to use ultrasound in the CHF case; five groups correctly recognized B-lines; and four groups correctly interpreted B-lines as pulmonary edema. No groups used ultrasound in the COPD case.ConclusionMost students attempted to use ultrasound during simulated CHF cases after a brief didactic intervention; however, many students struggled with clinical application. Interestingly, no students recognized the need to apply ultrasound for diagnosis and management of COPD. Future studies are needed to better understand how to optimize teaching for medical students to improve translation into POCUS skills and improved clinical practice.

Diagnostic Accuracy of Suspected Appendicitis: A Comparative Analysis of Misdiagnosed Appendicitis in Children.

When evaluating suspected appendicitis, limited data support quality benchmarks for negative appendectomy (NA); none exist for delayed diagnosis of appendicitis (DDA). The objectives of this study are the following: (1) to provide preliminary evidence supporting a quality benchmark for DDA and 2) to compare presenting features and diagnostic evaluations of children with NA and DDA with those with pathology-confirmed appendicitis (PCA) diagnosed during initial emergency department (ED) encounter. Secondary analysis of data from a QI project designed to reduce the use computed tomography when evaluating suspected appendicitis using a case-control design. Patients undergoing appendectomy in an academic tertiary care children's hospital system between January 1, 2015, and December 31, 2016 (n = 1,189) were eligible for inclusion in this case-control study. Negative appendectomy was defined as no pathologic change or findings consistent with a different diagnosis. Delayed diagnosis of appendicitis was defined as patients undergoing appendectomy within 7 days of a prior ED visit for a related complaint. Controls of PCA (n = 150) were randomly selected from all cases undergoing appendectomy. There were 42 NA (3.5%) and 31 DDA (2.6%). Cases of PCA and NA exhibited similar histories, examination findings, and underwent comparable diagnostic evaluations. Cases of PCA more frequently demonstrated a white blood cell count greater than 10 × 103/μL (85% vs 67%; P = 0.01), a left-shift (77% vs 45%; P < 0.001), and an ultrasound interpretation with high probability for appendicitis (73% vs 54%; P = 0.03). Numerous significant differences in history, examination findings, and diagnostic tests performed existed between cases of PCA and DDA. Children with PCA and NA present similarly and undergo comparable evaluations resulting in appendectomy. A 3% to 4% NA rate may be unavoidable given these similarities. Presenting features in DDA significantly differ from those of PCA. An irreducible proportion of appendicitis diagnoses may be delayed.

Reliable Thyroid Carcinoma Detection with Real-Time Intelligent Analysis of Ultrasound Images

Thyroid carcinoma is one of the most common endocrine diseases globally, and the incidence has been on the rise in recent years. Ultrasound imaging is the primary clinical method for early thyroid nodule diagnosis. Regions of interest (ROIs) of nodules in ultrasound images are difficult to detect because of their irregular shape nand vague margins. Accurate real-time thyroid nodule detection can provide ROIs for subsequent nodule diagnosis automatically, avoid variabilities between the subjective interpretations and inter-observer effectively and alleviate the workloads of medical practitioners. The aim of this study was to present a reliable, real-time detection method based on the Faster R-CNN (region-based convolutional network) framework for accurate and fast detection of thyroid nodules in ultrasound images. Our study proposed a faster and more accurate thyroid nodule detection method based on the Faster R-CNN framework by adding three strategies: feature pyramid, spatial remapping and anchor-box redesign. Specifically, the network takes raw ultrasound images as inputs and generates boxes with positions and the possibilities that these boxes contain thyroid nodules. The proposed method could locate and detect target nodules accurately with a mean average precision of 92.79% with more than 9000 patient images. In addition, the detection rate has accelerated to >16 frames per second, four times faster than that of the initial network. Therefore, it can meet the requirements of clinical application. The performance of the fivefold cross-validation was also accurate and robust. The proposed automatic thyroid nodule detection method yields better performance in accuracy and detection speed, which indicates the potential value of our method in assisting clinical ultrasound image interpretation.

Integrating Basic and Clinical Sciences Using Point-of-Care Renal Ultrasound for Preclerkship Education.

IntroductionPoint-of-care ultrasound (POCUS) is a valuable asset in bedside clinical care. Undergraduate medical education is increasingly using POCUS as an adjunct tool for teaching anatomy, pathophysiology, and physical exam in an integrated manner. Many medical schools teach content in an organ systems–based format in the preclerkship years. POCUS teaching can be very effectively tailored to specific organ systems. Though pilot curricula for generalized ultrasound education exist, few teach organ systems–based content using POCUS. To address this gap, we designed and implemented an integrated POCUS module to supplement anatomy, pathophysiology, and physical exam teaching in the renal course.MethodsThe module consisted of (1) a 30-minute didactic lecture introducing students to renal ultrasound technique and image interpretation and (2) a practical hands-on skills session. Pre- and postmodule surveys assessed the efficacy and impact of the curriculum.ResultsA total of 31 first-year medical students completed the POCUS renal curriculum. A majority reported that the module positively affected their understanding of renal pathophysiology and the physical exam. They also reported increased confidence in using POCUS to detect renal pathology and make clinical decisions.DiscussionIt was feasible to implement a POCUS curriculum to supplement integrated teaching of renal system concepts in the first year of medical school, and students found POCUS teaching valuable. POCUS provides educators with another tool to integrate basic and clinical sciences with hands-on relevant clinical skills practice in early medical school years.

95 Evaluation of variation attributable to lab and technician for measurements of beef carcass traits made using ultrasound

Abstract Carcass data that is collected using ultrasound contributes to national genetic evaluation of beef cattle. Cattle are scanned by many technicians and the resulting images are processed by three laboratories providing data to breed associations. The Ultrasound Guidelines Council certifies technicians and laboratories as being proficient. However, there has been no comprehensive evaluation of non-genetic sources of variation that affect the data. The objective of this study was to partition the variance of ultrasound carcass measurements to animal genetic effects, ultrasound scanning technician and image interpretation laboratory. Ultrasound carcass data for longissimus muscle area, percent intramuscular fat, and subcutaneous fat depth were provided by the American Angus Association (n=65,971), American Hereford Association (n=43,380), and American Simmental Association (n=48,298). For each breed variance components were estimated for additive genetic effects of each animal, technician, contemporary group nested within technician and residual. Genetic correlations were estimated treating measurements from the different interpretation laboratories as separate traits. Across all three breeds, additive genetic effects explained between 15 and 30%, 11 and 25%, and 6 and 13% of the phenotypic variance for IMF, SQF, and LMA, respectively. Similarly, technician explained 12-27%, 4-28%, and 4-26% of the phenotypic variance; contemporary groups within technician accounted for 25-45%, 20-54%, and 43-73% of phenotypic variance. Among the image interpretation laboratories, the ratio of greatest to least residual variance was 3.96, 1.62, and 1.50 for IMF, SQF, and LMA, respectively. Genetic correlations between labs ranged from 0.79 to 0.95 for IMF, 0.64 to 0.94 for SQF and 0.78 to 0.98 for LMA. These results suggest the potential for the residual variances to be heterogeneous, particularly for IMF, depending on the image interpretation laboratory.