Ultrasound Interpretation Research Articles

The Current Progress of Artificial Intelligence in Approach to Thyroid Nodules: A Narrative Review

Background: Artificial intelligence (AI) can play a significant role in the future of thyroidology. Thyroid nodules are common conditions that may benefit from AI through more accurate and efficient diagnosis, risk stratification, and medical or surgical management. Objective: This paper aims to review the latest developments in AI applications for diagnosing and managing thyroid nodules and cancers. Methods: English full-text articles published in the PubMed and Google Scholar databases from January 2014 to March 2024 were collected and reviewed to provide a comprehensive understanding of the topic. A total of 45 studies were selected based on relevance, robust methodology, statistical significance, and broader topic coverage. Results: Artificial intelligence has emerged as a powerful tool for managing thyroid nodules. First, several studies have demonstrated how AI-powered ultrasound interpretation enhances the diagnosis and classification of nodules while reducing the need for invasive fine-needle aspiration (FNA) biopsies. Second, AI significantly improves the cytopathological differentiation between benign and malignant thyroid nodules by minimizing reliance on pathologists' expertise and implementing standardized diagnostic criteria. When cytopathology is inconclusive, AI also aids in identifying molecular markers from omics data, distinguishing between normal and cancerous cells. Moreover, AI tools have been developed for prognosis assessment, predicting distant metastasis, recurrence, and surveillance by integrating medical imaging features with molecular and clinical factors. Additionally, some AI tools are designed for intraoperative evaluation, improving surgical techniques and reducing complications during thyroidectomy. In non-surgical treatments, several models have been developed to optimize therapeutic doses of radioactive iodine (RAI) and predict the outcomes of new drug formulations. Conclusions: Artificial intelligence has the potential to assist physicians in accurate thyroid nodule diagnosis, classification, decision-making, optimizing treatment strategies, and improving patient outcomes. However, there are still limitations to this technology. Artificial intelligence-driven tools require further advancements before they can be fully integrated into clinical practice and replace specialists.

Directed image review technique (DIRT): A framework for ultrasound image assessment and interpretation.

Use of point-of-care ultrasound (POCUS) is integral to the practice of emergency medicine, and POCUS education is a required component of emergency medicine training. Developing POCUS skills requires iterative deliberate practice of image acquisition and interpretation. Providing feedback to learners regarding ultrasound image interpretation can be challenging for emergency medicine clinician educators. We present a framework called the directed image review technique. This framework guides learner ultrasound image interpretation and provides educators with a similar structured approach to evaluate a learner's ultrasound competency and provide targeted feedback regarding image acquisition and interpretation.

Advances in AI-based combination therapies versus standard treatments for heart failure in patients with advanced kidney injury

Background: Recent advancements in AI and Machine Learning (ML) can help manage kidney disease and heart failure by providing predictive analytics and personalized treatment plans, improving diagnostic accuracy, and assisting clinicians in controlling chronic disease symptoms like acute kidney injury (AKI) and Managing Heart Failure (HF). We evaluated AI and ML role in predicting AKI and managing HF patients and it involved analyzing various predictive models and technologies to improve early detection provide personalized treatment, and enhance overall patient outcomes in complex renal and cardiac conditions. Methodology: We conducted our search on databases Scopus, PubMed, and Web of Science. Empirical evidence and state of the art of cutting-edge literature and real-time field research was analyzed. Results: AI advancements in HF management for advanced kidney disease AKI include unsupervised machine learning for risk stratification, reinforcement learning for predictive modeling and dynamic management, and LLMs and chatbots for diagnostic support and patient education. New developments in AI and medical technology are predictive analytics for AKI, automated ultrasound interpretation, AI-enhanced dialysis monitoring, HF risk prediction, remote monitoring, and telehealth integration, and making personal treatment strategies according to patient needs. Innovations like wearable dialysis devices, bioengineered kidney tissues, ECMO, LVADs, TAVR, SGLT2 inhibitors, CRT, and nephroprotective drugs have also improved patient outcomes as these have enabled personalized care and early intervention strategies. Conclusion: It is possible to conclude that AI has revolutionized AKI and HF management. Novel technologies offer precise and adaptive care that strictly addresses individual patient needs.

Role of teleradiology in the interpretation of ultrasound images acquired in the emergency setting

BACKGROUND: Teleradiology has become an important tool in emergency medicine, particularly in the interpretation of emergency ultrasonography. In emergency situations, where time is essential, rapid diagnosis and treatment can mean the difference between life and death. Teleradiology is an innovative alternative to augment the staffing and fill the gaps of onsite radiology personnel in emergency departments or during off-hours. AIM: To assess the effectiveness/impact of teleradiology in emergency ultrasound interpretation. MATERIALS AND METHODS: A retrospective study was performed in a cohort of 33,616 patients from 86 hospitals across the USA between January and December 2022. The study involved radiological interpretations of 37,253 ultrasound images acquired in the emergency setting by American Board Certified Radiologists empaneled by a teleradiology service provider, headquartered in Bangalore, India. RESULTS: The proposed telehealth model provided timely and quality reporting of 37,253 scans of patients with a mean turnaround time of 35.71 min (95% confidence interval 35.50–35.91). CONCLUSION: This study demonstrates that a structured telesonography program with defined protocols for image capture, transmission, and clinical communication can allow for successful immediate reporting of ultrasound data in the emergency care setting.

Can incorporating image resolution into neural networks improve kidney tumor classification performance in ultrasound images?

Deep learning has been widely used in ultrasound image analysis, and it also benefits kidney ultrasound interpretation and diagnosis. However, the importance of ultrasound image resolution often goes overlooked within deep learning methodologies. In this study, we integrate the ultrasound image resolution into a convolutional neural network and explore the effect of the resolution on diagnosis of kidney tumors. In the process of integrating the image resolution information, we propose two different approaches to narrow the semantic gap between the features extracted by the neural network and the resolution features. In the first approach, the resolution is directly concatenated with the features extracted by the neural network. In the second approach, the features extracted by the neural network are first dimensionally reduced and then combined with the resolution features to form new composite features. We compare these two approaches incorporating the resolution with the method without incorporating the resolution on a kidney tumor dataset of 926 images consisting of 211 images of benign kidney tumors and 715 images of malignant kidney tumors. The area under the receiver operating characteristic curve (AUC) of the method without incorporating the resolution is 0.8665, and the AUCs of the two approaches incorporating the resolution are 0.8926 (P < 0.0001) and 0.9135 (P < 0.0001) respectively. This study has established end-to-end kidney tumor classification systems and has demonstrated the benefits of integrating image resolution, showing that incorporating image resolution into neural networks can more accurately distinguish between malignant and benign kidney tumors in ultrasound images.

Improved prenatal assessment of kidney disease using multiple ultrasound features.

Congenital anomalies of the kidney and the urinary tract (CAKUT), often discovered in utero, cover a wide spectrum of outcomes ranging from normal postnatal kidney function to fetal death. The current ultrasound workup does not allow for an accurate assessment of the outcome. The present study aimed to significantly improve the ultrasound-based prediction of postnatal kidney survival in CAKUT. Histological analysis of kidneys of 15 CAKUT fetuses was performed to better standardize the ultrasound interpretation of dysplasia and cysts. Ultrasound images of 140 CAKUT fetuses with 2-year postnatal follow-up were annotated for amniotic fluid volume and kidney number, size, dysplasia and/or cysts using standardized ultrasound readout. Association of ultrasound features and clinical data (sex and age at diagnosis) with postnatal kidney function was studied using logistic regression. Amniotic fluid proteome associated to kidney dysplasia or cysts was characterized by mass spectrometry. Histologically, poor ultrasound corticomedullary differentiation was associated to dysplastic lesions and ultrasound hyperechogenicity was associated to the presence of microcysts. Of all ultrasound and clinical parameters, reduced amniotic volume, dysplasia and cysts were the best predictors of poor outcome (Odd ratio = 57 [95%CI: 11-481], 20 [3-225] and 7 [1-100], respectively). Their combination into an algorithm improved prediction of postnatal kidney function compared to amniotic volume alone (area under the ROC curve = 0.92 [0.86-0.98] in a 10-fold cross validation). Dysplasia and cysts were correlated (Cramer's V coefficient = 0.44, p<0.0001), but amniotic fluid proteome analysis revealed that they had distinct molecular origin (extracellular matrix and cell contacts versus cellular death, respectively), probably explaining the additivity of their predictive performances. Antenatal clinical advice for CAKUT pregnancies can be improved by a more standardized and combined interpretation of ultrasound data.

Point-of-Care Kidney and Genitourinary Ultrasound in Adults: Image Acquisition.

A range of conditions involving the kidneys and urinary bladder can cause organ-threatening complications that are preventable if diagnosed promptly with diagnostic imaging. Common imaging modalities include either computed tomography or diagnostic ultrasound. Traditionally, ultrasound of the kidney-genitourinary system has required consultative teams consisting of a sonographer performing image acquisition and a radiologist performing image interpretation. However, diagnostic point-of-care ultrasound (POCUS) has recently emerged as a useful tool to troubleshoot acute kidney injury at the bedside. Studies have shown that non-radiologists can be trained to perform diagnostic POCUS of the kidneys and bladder with high accuracy for a set number of important conditions. Currently, diagnostic POCUS of the kidney-genitourinary system remains underused in actual clinical practice. This is likely because image acquisition for this organ system is unfamiliar to most clinicians in specialties that encounter acute kidney injury, including primary care, emergency medicine, intensive care, anesthesiology, nephrology, and urology. To address this multi-specialty educational gap, this narrative review was developed by a multi-disciplinary group to provide a specialty-agnostic framework for kidney-genitourinary POCUS image acquisition: indications/contraindications, patient positioning, transducer selection, acquisition sequence, and exam limitations. Finally, we describe foundational concepts in kidney-genitourinary ultrasound image interpretation, including key abnormal findings that every bedside clinician performing this modality should know.

Accuracy of focused cardiac ultrasound interpretation among emergency and critical care medicine residents in Ethiopia: A multi-center cross-sectional study

IntroductionFocused cardiac ultrasound (FoCUS) has emerged as a valuable tool in emergency and critical care medicine, allowing for rapid assessment of cardiac function and structure at the bedside. This rapid diagnostic technique holds particular promise in resource-limited settings like Ethiopia, where access to standard echocardiography may be limited and delayed. However, the accuracy of FoCUS interpretation is highly dependent on the operator's skills and expertise. To inform the design of effective interventions, the study aimed to assess the accuracy of FoCUS interpretation and associated factors among senior Emergency Medicine residents at two large referral teaching hospitals in Ethiopia. MethodsA cross-sectional study was conducted from October to December 2023 among 80 residents at Tikur Anbessa Specialized Hospital and St. Paul's Hospital Millennium Medical College. To assess diagnostic accuracy, 15 pre-selected cardiac ultrasound videos (normal and pathological cases) were selected from American College of Emergency Physicians website and the PoCUS Atlas, and accurate interpretation was defined as correctly answering at least 12 out of 15 readings. A binary logistic regression model was fitted to identify significant factors at the 5% level of significance, where significant results were interpreted using adjusted odds ratio (AOR) with 95% confidence interval (CI). ResultThe overall accuracy in interpreting FoCUS findings was 47.5% (95% CI: 38.8–60.0%), with highest for collapsing Inferior Vena Cava (91.3%) and standstill (90.0%), and lowest for Regional Wall Motion Abnormality of Left Ventricle (46.3%). Residents who received training (AOR=4.14, 95%CI:1.32–13.04, p = 0.015), perceived themselves as skilled (AOR=4.81, 95%CI=1.06–21.82, p = 0.042), and felt confident in acquiring and interpretation (AOR=3.16, 95%CI=1.01–9.82, p = 0.047) demonstrated significantly higher accuracy. ConclusionThe study identified a low overall accuracy in FoCUS interpretation, with accuracy improving with training and better perceived skill and confidence. Training programs with simulation, continuous education, and mentorship are crucial to enhance these critical skills.

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens with known, unchangeable defect properties, which are usually complicated to fabricate. It consist of a shape memory polymer foil with temperature-dependent Young’s modulus and ultrasound attenuation. This open a possibility to generate a reconfigurable defect by projecting a heating laser in the form of a short line on the specimen surface. Ultrasound is generated by a laser pulse at one fixed position and detected by a laser vibrometer at another fixed position for 64 different defect positions and 3 different configurations of the specimen. The obtained diversified datasets are used to optimize the neural network architecture for the interpretation of ultrasound signals. We study the performance of the model in cases of reduced and dissimilar training datasets. In our first study, we classify the specimen configurations with the defect position being the disturbing parameter. The model shows high performance on a dataset of signals obtained at all the defect positions, even if trained on a completely different dataset containing signals obtained at only few defect positions. In our second study, we perform precise defect localization. The model becomes robust to the changes in the specimen configuration when a reduced dataset, containing signals obtained at two different specimen configurations, is used for the training process. This work highlights the potential of the demonstrated machine learning algorithm for industrial quality control. High-volume products (simulated by a reconfigurable specimen in our work) can be rapidly tested on the production line using this single-point and contact-free laser ultrasonic method.

Implementing Prehospital Ultrasound at the Saudi Red Crescent Authority: Perceived Barriers and Training Needs.

This study examines the inherent barriers to implementing prehospital ultrasound within the Saudi Red Crescent Authority (SRCA) in Saudi Arabia. A qualitative study was conducted to explore the perceived barriers, mode of transportation, ultrasound familiarity, and self-efficacy level of relevant stakeholders in implementing the prehospital ultrasound in SRCA. Data was collected via surveys and interviews with 24 SRCA paramedics/EMTs, 4 SRCA station administrators, and two hospital physicians to further examine the inherent barriers of implementing the prehospital ultrasound. Thematic analysis revealed the main barriers were costs of ultrasound equipment, environmental factors affecting image capture, and lack of training in ultrasound skills and interpretation. Administrators and physicians also noted concerns about machine portability and technical maintenance. Stakeholders agreed ultrasound could improve trauma diagnosis if barriers were addressed through extensive training and protocols. In prehospital care setting, the two main modes of transportation are "stay and play", involving on-scene interventions before transport, and "load and go", prioritizing rapid transport to the hospital, with the choice depending on various factors. An overwhelming 96% of paramedics/EMTs preferred a 'stay and play' approach to stabilize patients before transport, while 75% of administrators preferred 'load and go' for rapid transport to hospitals. 62.5% of paramedics were familiar with ultrasound, but only 20.8% had previously used it. This study provides important insights into stakeholder perspectives on the implementation of prehospital ultrasound within the Saudi Red Crescent Authority. The findings can guide efforts to implement appropriate ultrasound use through tailored training programs and enhanced coordination across groups, aimed at improving trauma outcomes.

Competencies for proficiency in basic point-of-care ultrasound in anesthesiology: national expert recommendations using Delphi methodology.

Point-of-care ultrasound (POCUS) allows for rapid bedside assessment and guidance of patient care. Recently, POCUS was included as a mandatory component of Canadian anesthesiology training; however, there is no national consensus regarding the competencies to guide curriculum development. We therefore aimed to define national residency competencies for basic perioperative POCUS proficiency. We adopted a Delphi process to delineate relevant POCUS competencies whereby we circulated an online survey to academic anesthesiologists identified as POCUS leads/experts (n = 25) at all 17 Canadian anesthesiology residency programs. After reviewing a list of competencies derived from the Royal College of Physicians and Surgeons of Canada's National Curriculum, we asked participants to accept, refine, delete, or add competencies. Three rounds were completed between 2022 and 2023. We discarded items with < 50% agreement, revised those with 50-79% agreement based upon feedback provided, and maintained unrevised those items with ≥ 80% agreement. We initially identified and circulated (Round 1) 74 competencies across 19 clinical domains (e.g., basics of ultrasound [equipment, nomenclature, clinical governance, physics]; cardiac [left ventricle, right ventricle, valve assessment, pericardial effusion, intravascular volume status] and lung ultrasound anatomy, image acquisition, and image interpretation; and clinical applications [monitoring and serial assessments, persistent hypotension, respiratory distress, cardiac arrest]). After three Delphi rounds (and 100% response rate maintained), panellists ultimately agreed upon 75 competencies. Through national expert consensus, this study identified POCUS competencies suitable for curriculum development and assessment in perioperative anesthesiology. Next steps include designing and piloting a POCUS curriculum and assessment tool(s) based upon these nationally defined competencies.

A narrative review on the application of artificial intelligence in renal ultrasound.

Kidney disease is a serious public health problem and various kidney diseases could progress to end-stage renal disease. The many complications of end-stage renal disease. have a significant impact on the physical and mental health of patients. Ultrasound can be the test of choice for evaluating the kidney and perirenal tissue as it is real-time, available and non-radioactive. To overcome substantial interobserver variability in renal ultrasound interpretation, artificial intelligence (AI) has the potential to be a new method to help radiologists make clinical decisions. This review introduces the applications of AI in renal ultrasound, including automatic segmentation of the kidney, measurement of the renal volume, prediction of the kidney function, diagnosis of the kidney diseases. The advantages and disadvantages of the applications will also be presented clinicians to conduct research. Additionally, the challenges and future perspectives of AI are discussed.

URI-CADS: A Fully Automated Computer-Aided Diagnosis System for Ultrasound Renal Imaging.

Ultrasound is a widespread imaging modality, with special application in medical fields such as nephrology. However, automated approaches for ultrasound renal interpretation still pose some challenges: (1) the need for manual supervision by experts at various stages of the system, which prevents its adoption in primary healthcare, and (2) their limited considered taxonomy (e.g., reduced number of pathologies), which makes them unsuitable for training practitioners and providing support to experts. This paper proposes a fully automated computer-aided diagnosis system for ultrasound renal imaging addressing both of these challenges. Our system is based in a multi-task architecture, which is implemented by a three-branched convolutional neural network and is capable of segmenting the kidney and detecting global and local pathologies with no need of human interaction during diagnosis. The integration of different image perspectives at distinct granularities enhanced the proposed diagnosis. We employ a large (1985 images) and demanding ultrasound renal imaging database, publicly released with the system and annotated on the basis of an exhaustive taxonomy of two global and nine local pathologies (including cysts, lithiasis, hydronephrosis, angiomyolipoma), establishing a benchmark for ultrasound renal interpretation. Experiments show that our proposed method outperforms several state-of-the-art methods in both segmentation and diagnosis tasks and leverages the combination of global and local image information to improve the diagnosis. Our results, with a 87.41% of AUC in healthy-pathological diagnosis and 81.90% in multi-pathological diagnosis, support the use of our system as a helpful tool in the healthcare system.

Ultrasound Evaluation of Interstitial Lung Disease in Rheumatoid Arthritis and Autoimmune Diseases.

The interpretation of lung ultrasound is the result of the analysis of artifacts rather than exact representations of anatomical structures, which appear when changes in the physical properties of the lung occur. Its application to the study of interstitial lung disease (ILD) associated with autoimmune diseases has aroused great interest in the last 10 years, as evidenced by a growing number of publications studying its usefulness in the diagnostic process, as a prognostic marker and as an aid in monitoring of patients. The main elements in lung ultrasound interpretation in ILD are the B lines and the changes in the pleural line. B lines are vertical artifacts that are generated when there is a partial decrease in the air content of the lung parenchyma and/or the volume of the interstitial area expands. Pleural line alterations that can be seen are irregularities, thickening, fragmentation, or subpleural nodules. Both the B lines and the changes in the pleural line have shown a significant positive correlation with the evidence on chest computed tomography [high resolution computed tomography (HRCT)] of ILD associated with autoimmune diseases, with sensitivity and negative predictive values of up to 100%. These results, together with the safety, accessibility, and low cost of lung ultrasound, support this imaging technique as a promising screening method for optimizing the indication for HRCT. The role of lung ultrasound regarding sensitivity to change needs further investigation with multicenter prospective studies.

Reliability of assessing skeletal muscle architecture and tissue organization of the gastrocnemius medialis and vastus lateralis muscle using ultrasound and spatial frequency analysis.

The purpose of this study was to investigate inter- and intra-rater reliability as well as the inter-rater interpretation error of ultrasound measurements assessing skeletal muscle architecture and tissue organization of the gastrocnemius medialis (GM) and vastus lateralis (VL) muscle. The GM and VL of 13 healthy adults (22 ± 3 years) were examined thrice with sagittal B-mode ultrasound: intraday test-retest examination by one investigator (intra-rater) and separate examinations by two investigators (inter-rater). Additionally, images from one investigator were analysed by two interpretators (interpretation error). Muscle architecture was assessed by muscle thickness [MT], fascicle length [FL], as well as superior and inferior pennation angle [PA]. Muscle tissue organization was determined by spatial frequency analysis (SFA: peak spatial frequency radius, peak -6 dB width, PSFR/P6, normalized peak value of amplitude spectrum [Amax], power within peak [PWP], peak power percent). Reliability of ultrasound examination and image interpretation are presented as intraclass correlation coefficient (ICC), test-retest variability, standard error of measurement as well as bias and limits of agreement. GM and VL demonstrated excellent ICCs for inter- and intra-rater reliability, along with excellent ICCs for interpretation error of MT (0.91-0.99), showing minimal variability (<5%) and SEM% (<5%). Systematic bias for MT was less than 1 mm. For PA and FL poor to good ICCs for inter- and intra-rater reliability were revealed (0.41-0.90), with moderate variability (<12%), low SEM% (<10%) and systematic bias between 0.1-1.4°. Tissue organization analysis indicated moderate to good ICCs for inter- and intra-rater reliability. Notably, Amax and PWP consistently held the highest ICC values (0.77-0.87) across all analyses but with higher variability (<24%) and SEM% (<18%), compared to lower variability (<9%) and SEM% (<8%) in other tissue organization parameters. Interpretation error of all muscle tissue organization parameters showed excellent ICCs (0.96-0.999) with very low variability (≤1%) and SEM% (<2%), except Amax & PWP (TRV%: <6%; SEM%: <7%). Our findings demonstrated excellent inter- and intra-rater reliability for MT. However, agreement for PA, FL, and SFA parameters was not as strong. Additionally, MT and all SFA parameters exhibited excellent agreement for inter-rater interpretation error. Therefore, the SFA seems to offer the possibility of objectively and reliably evaluating ultrasound images.

One-week radiology boot camp for pre-clerkship medical students: A novel format improving image interpretation and confidence

Rationale and objectivesTo measure change in radiology knowledge, confidence in radiology skills, and perceptions pertaining to radiology following a one-week boot camp elective for undergraduate medical students. Materials and methodsA five-day comprehensive radiology boot camp was developed including sessions on image interpretation, procedural skills, and appropriate image ordering. A multiple-choice quiz was administered before and after the elective, utilizing radiology questions from the validated AMSER STARS database. Additionally, a pre- and post-elective survey was administered assessing radiology career interest, confidence in radiology-based skills, and the potential ability of radiology-based skills to increase confidence in specialties other than radiology. Responses from the assessments were analysed using paired t-tests. Results15 students enrolled in the course and 14 completed all assessments. The average score on the quiz increased from 50.1% to 66.0% (p<0.001). On the post-elective survey, the average student confidence score increased by more than one point on a six-point Likert scale in each of radiographic interpretation (p=0.004), ultrasound interpretation (p=0.0002), CT/MRI interpretation (p=0.02), general radiology knowledge including procedural skills (p=0.0001), and appropriate image ordering (p=0.004). Average student satisfaction with the elective was 8.1 out of 10. ConclusionA one-week radiology boot camp for pre-clerkship medical students improved radiology knowledge and confidence in radiology skills, showing potential for this format to meet the demand for increased radiology content in undergraduate training. Students indicated that confidence in radiology knowledge would increase confidence on non-radiology clerkship rotations, highlighting the importance of how a one-week radiology bootcamp can impact both future radiology and non-radiology clerkship experiences.

A multitask approach for automated detection and segmentation of thyroid nodules in ultrasound images

An increase in the incidence and diagnosis of thyroid nodules and thyroid cancer underscores the need for a better approach to nodule detection and risk stratification in ultrasound (US) images that can reduce healthcare costs, patient discomfort, and unnecessary invasive procedures. However, variability in ultrasound technique and interpretation makes the diagnostic process partially subjective. Therefore, an automated approach that detects and segments nodules could improve performance on downstream tasks, such as risk stratification. Ultrasound studies were acquired from 280 patients at UCLA Health, totaling 9888 images, and annotated by collaborating radiologists. Current deep learning architectures for segmentation are typically semi-automated because they are evaluated solely on images known to have nodules and do not assess ability to identify suspicious images. However, the proposed multitask approach both detects suspicious images and segments potential nodules; this allows for a clinically translatable model that aptly parallels the workflow for thyroid nodule assessment. The multitask approach is centered on an anomaly detection (AD) module that can be integrated with any UNet architecture variant to improve image-level nodule detection. Of the evaluated multitask models, a UNet with a ImageNet pretrained encoder and AD achieved the highest F1 score of 0.839 and image-wide Dice similarity coefficient of 0.808 on the hold-out test set. Furthermore, models were evaluated on two external validations datasets to demonstrate generalizability and robustness to data variability. Ultimately, the proposed architecture is an automated multitask method that expands on previous methods by successfully both detecting and segmenting nodules in ultrasound.

E-FAST Ultrasound Training Curriculum for Prehospital Emergency Medical Service (EMS) Clinicians.

Audience and type of curriculum: This hybrid, asynchronous curriculum is designed for prehospital clinician colleagues, including but not limited to emergency medical technicians (EMT), advanced EMTs (AEMT), EMT-paramedics (EMT-P), critical care EMT-Ps (CCEMTP), critical care transport nurses (CCTN), and certified flight registered nurses (CFRN) to learn and practice ultrasound fundamentals in the setting of a standardized extended focused assessment with sonography in trauma (E-FAST) exam. Over a five-month curriculum, learners will perform a pre-test, review online module lectures, attend an ultrasound scanning workshop, and perform post-test examinations. The extended-focused assessment with sonography in trauma (E-FAST) exam can identify intrathoracic and intraabdominal free fluid, as well as pneumothoraces. The E-FAST ultrasound exam has previously been taught to clinicians of various backgrounds in healthcare including emergency medical service (EMS). However, an open-access, systemized curriculum for teaching E-FAST exams to EMS clinicians has not been published. By the end of these training activities, prehospital EMS learners will be able to demonstrate foundational ultrasound skills in scanning, interpretation, and artifact recognition by identifying pertinent organs and anatomically relevant structures for an E-FAST examination. Learners will differentiate between normal and pathologic E-FAST ultrasound images by identifying the presence of free fluid and lung sliding. Learners will also explain the clinical significance and application of detecting free fluid during an E-FAST scan. The educational strategies used in this curriculum include a hybrid, asynchronous curriculum encompassing 2.5 hours of lectures derived from online learning modules and in-person review. In addition, learners will attend 2 hours of hands-on proctored ultrasound scanning practicing E-FAST examinations. An online 13-question pre-test was administered prior to the study. An online post-test and in-person scanning OSCEs were administered at least eight weeks after their scheduled workshop consisting of an online 13-question multiple-choice post-test, a confidence survey, and a hands-on E-FAST Objectively Structured Clinical Exam (OSCE) session. A non-parametric Wilcoxon signed-rank test was performed between each pre-test and post-test metric to examine the statistical differences of paired data. Post-test scores demonstrated statistically significant improvement in both image interpretation exams and ultrasound self-efficacy from the pre-test. The mean pre-test and post-test scores were 55.46% (7.21 ± 1.99) and 84.23% (10.89 ± 1.59) correct out of 13 questions, respectively (p < 0.0001). Participants surveyed an increase in self-efficacy reflected by a Likert scale for ultrasound usage and image interpretation (p < 0.005). The average post-test OSCE E-FAST exam score was 37.89 ± 2.76 out of 42 points (90.21%). This 4.5-hour hybrid asynchronous model demonstrates an effective curriculum for teaching E-FAST ultrasound to prehospital clinicians. Ultrasound, sonography, prehospital clinicians, emergency medical services (EMS), paramedics, critical care transport, extended focused assessment with sonography in trauma (E-FAST), free fluid, sliding lung sign, elective, pain.

Inter- and intra-observer variability of radial-endobronchial ultrasound image interpretation for peripheral pulmonary lesions.

Radial probe endobronchial ultrasound (R-EBUS) is often utilized in guided bronchoscopy for the diagnosis of peripheral pulmonary lesions. R-EBUS probe positioning has been shown to correlate with diagnostic yield, but overall diagnostic yield with this technology has been inconsistent across the published literature. Currently there is no standardization for R-EBUS image interpretation, which may result in variability in grading concentricity of lesions and subsequently procedure performance. This was a survey-based study evaluating variability among practicing pulmonologists in R-EBUS image interpretation. R-EBUS images from peripheral bronchoscopy cases were sent to 10 practicing Interventional Pulmonologists at two different time points (baseline and 3 months). Participants were asked to grade the images as concentric, eccentric, or no image. Cohen's Kappa-coefficient was calculated for inter- and intra-observer variability. A total of 100 R-EBUS images were included in the survey. There was 100% participation with complete survey responses from all 10 participants. Overall kappa-statistic for inter-observer variability for Survey 1 and 2 was 0.496 and 0.477 respectively. Overall kappa-statistic for intra-observer variability between the two surveys was 0.803. There is significant variability between pulmonologists when characterizing R-EBUS images. However, there is strong intra-rater agreement from each participant between surveys. A standardized approach and grading system for radial EBUS patterns may improve inter-observer variability in order to optimize our clinical use and research efforts in the field.

Correlation of Non-Mass Breast Lesions on Ultrasound with Histopathology

Background and Aim: Breast cancer is the most common invasive cancer among women worldwide. In Iraq, the incidence of new breast cancer cases significantly increased from 52.00 per 100,000 in 2000 to 91.66 per 100,000 in 2019. The goal is to develop standardized reporting criteria for NMLs on ultrasound to improve patient management. Methods: A cross-sectional study at AL-Yarmouk Teaching Hospital in Baghdad included 55 female patients with NMLs. Participants underwent evaluations using ultrasound, with mammographic correlation when applicable. Lesion characteristics, such as size, location, echogenicity, and associated features, were documented according to BI-RADS lexicon. Tissue Core Biopsy (TCB) was performed to obtain samples for histopathological analysis. Ethical approval and informed consent were obtained, ensuring data confidentiality and participant privacy. Results: Among the 55 patients, 60% of NMLs were benign, 25.5% were malignant, and 14.5% had upgrade potential. Significant associations were found between ultrasound characteristics (e.g., distribution and echogenicity) and histopathological outcomes, with segmental distribution being more common in malignant lesions. Mammographic features such as calcifications and architectural distortion also strongly correlated with malignancy. Conclusion: The integration of advanced ultrasound technology has improved the detection of NMLs, crucial for early breast cancer detection. However, these lesions often mimic surrounding tissues, leading to potential false positives. Future research should focus on standardizing ultrasound interpretation of NMLs to enhance diagnostic accuracy and patient management.