Interpretation Of Radiographs Research Articles

Paradigm Shift in Respiratory Diagnosis: Current Status and Future Prospects of Dynamic Chest Radiography

Dynamic chest radiography (DCR) is a flat-panel detector (FPD) -based functional X-ray imaging, which is performed as an additional examination in chest radiography. The large field of view of FPDs permits real-time observation of motion/kinetic findings on the entire lungs, right and left diaphragm, ribs, and chest wall; heart wall motions; respiratory changes in lung density; and diameter of the intrathoracic trachea. Since the dynamic FPDs had been developed in the early 2000s, we focused on the potential of dynamic FPDs for functional X-ray imaging and have launched a research project for the development of an imaging protocol and digital image-processing techniques for the DCR. The quantitative analysis of motion/kinetic findings is helpful for a better understanding of pulmonary function, because the interpretation of dynamic chest radiographs is challenging and time-consuming for radiologists, pulmonologists, and surgeons. Recent clinical studies have demonstrated the usefulness of DCR combined with the digital image processing techniques for the evaluation of pulmonary function and circulation. Especially, there is a major concern in color-mapping images based on dynamic changes in radiographic lung density, where pulmonary impairments can be detected as color defects, even without the use of contrast media or radioactive medicine. Dynamic chest radiography is now commercially available for the use in general X-ray room and therefore can be deployed as a simple and rapid means of functional imaging in both routine and emergency medicine. This review article describes the current status and future prospects of DCR, which might bring a paradigm shift in respiratory diagnosis.

Impact of viewing conditions on the performance assessment of different computer monitors used for dental diagnostics.

PurposeThis study aimed to assess the computer monitors used for analysis and interpretation of digital radiographs within the clinics of the Oral Health Centre of Western Australia.Materials and MethodsIn total, 135 computer monitors (3 brands, 6 models) were assessed by analysing the same radiographic image of a combined 13-step aluminium step wedge and the Artinis CDDent 1.0® (Artinis Medical Systems B.V.®, Elst, the Netherlands) test object. The number of steps and cylindrical objects observed on each monitor was recorded along with the monitor's make, model, position relative to the researcher's eye level, and proximity to the nearest window. The number of window panels blocked by blinds, the outside weather conditions, and the number of ceiling lights over the surgical suite/cubicle were also recorded. MedCalc® version 19.2.1 (MedCalc Software Ltd®, Ostend, Belgium, https://www.medcalc.org; 2020) was used for statistical analyses (Kruskal-Wallis test and stepwise regression analysis). The level of significance was set at P<0.05.ResultsStepwise regression analysis showed that only the monitor brand and proximity of the monitor to a window had a significant impact on the monitor's performance (P<0.05). The Kruskal-Wallis test showed significant differences (P<0.05) in monitor performance for all variables investigated, except for the weather and the clinic in which the monitors were placed.ConclusionThe vast performance variation present between computer monitors implies the need for a review of monitor selection, calibration, and viewing conditions.

Mandibular First Premolar with Three Canals and Periodontalendodontic Lesion: Case Report

This clinical report presents and describes both the endodontic and periodontal treatment of a mandibular first premolar exhibiting three root canals presented with perio-endo infection. Mandibular first premolars usually have a single root and a single root canal. The incidence of three root canals in this tooth is quite rare. Knowledge of root canal morphology, proper clinical examination, correct radiographic interpretation, using dental operating microscope, and careful tactile examination of the root canals are important in detecting the presence of the multiple canals and in treating the endodontic and periodontal lesions.

Student Response to a Blended Radiology Course: A Multi-Year Study in Dental Education

Universities around the world are increasingly moving towards blended learning models to engage their 21st century learners (Alammary et al., 2014; Brenard et al., 2014; Tandoh et al., 2014). However, students’ engagement and satisfaction with blended learning in dental education remain understudied. To address this gap, this study examines the effects of a blended learning approach on students’ satisfaction and engagement within dental hygiene and dentistry oral radiology courses. Thirty-five students participated in a survey designed to measure two main constructs: student engagement (per Fredericks et al., 2005) and student satisfaction (per Owston et al., 2013) with the addition of one student providing interview data on each of these constructs. It was found that students were generally satisfied (67%) with the blended learning course format with 65% of students expressing a preference for the blended format. This finding was complemented by students’ also expressing that they were emotionally engaged (70% engagement score), cognitively engaged (69% engagement score), and behaviourally engaged (61% engagement score). These findings suggest that blended learning may be of benefit to the engagement and satisfaction of dental students’ learning the interpretation of dental radiographs.

Artificial Intelligence-Based Triaging of Normal Chest Radiographs: Results of a Retrospective Simulation Study in a Multi-Center Health Screening Cohort

Background: Interpretation of normal chest radiographs causes significant burden for the radiologists interpreting screening chest radiographs. This study aimed to simulate a workflow that uses artificial intelligence (AI) algorithm to triage normal screening chest radiographs, improving efficiency of radiologists. Methods: This retrospective simulation study was conducted using chest radiographs of 5887 individuals (whole dataset) undergoing medical checkup in three institutions in South Korea. An image was considered positive for visible findings and clearly visible findings if at least one of the three, and at least two of the three thoracic radiologists marked the image as positive for referable thoracic abnormality, respectively. In the whole dataset, percentages of normal images that can be filtered out as well as abnormal images that were skipped as a result of AI triaging were analyzed. 480 chest radiographs randomly sampled from the whole dataset were used in the reader study to evaluate the change in the performance of physician, general radiologist, and thoracic radiologist reader groups in the new AI-based triaging workflow. Findings: Of 5887 images included in the whole dataset, 405 images (6·9%) and 227 images (3·9%) contained visible and clearly visible abnormalities, respectively. With AI-based triaging workflow, 42·9% (95% CI 41·6-44·3) (2354 of 5482) of normal images were removed at the cost of removing 3·5% (95% CI 1·7-5·2) (14 of 405) and 1·8% (95% CI 0·1-3·5) (4 of 227) of images with visible and clearly visible findings, respectively. In the reader study, 41·6% (95% CI 37·0-46·1) (188 of 452) of normal images were removed from the worklist without any additionally missed visible abnormalities, increasing specificity without decreasing sensitivity in all reader groups. Interpretation: Although readers should be cautious of the additionally missed abnormalities, AI-based triaging can reduce total radiologist workload and lead to dramatic increase in efficiency. Funding Statement: Korea Health Industry Development Institute. Declaration of Interests: HY is employee of Lunit Inc. KNJ received a research fund from Lunit. Other authors have neither financial interests nor conflicts of interest. Ethics Approval Statement: This retrospective study was approved by ethics review and institutional review board from participating institutions, and the requirement for informed consent was waived. Under this approval, all chest radiographs were de-identified and collected according to the Health Insurance Portability and Accountability Act Safe Harbor standard.

Derivation With Internal Validation of a Multivariable Predictive Model to Predict COVID-19 Test Results in Emergency Department Patients.

ObjectivesThe COVID‐19 pandemic has placed acute care providers in demanding situations in predicting disease given the clinical variability, desire to cohort patients, and high variance in testing availability. An approach to stratifying patients by likelihood of disease based on rapidly available emergency department (ED) clinical data would offer significant operational and clinical value. The purpose of this study was to develop and internally validate a predictive model to aid in the discrimination of patients undergoing investigation for COVID‐19.MethodsAll patients greater than 18 years presenting to a single academic ED who were tested for COVID‐19 during this index ED evaluation were included. Outcome was defined as the result of COVID‐19 polymerase chain reaction (PCR) testing during the index visit or any positive result within the following 7 days. Variables included chest radiograph interpretation, disease‐specific screening questions, and laboratory data. Three models were developed with a split‐sample approach to predict outcome of the PCR test utilizing logistic regression, random forest, and gradient‐boosted decision tree methods. Model discrimination was evaluated comparing area under the receiver operator curve (AUC) and point statistics at a predefined threshold.ResultsA total of 1,026 patients were included in the study collected between March and April 2020. Overall, there was disease prevalence of 9.6% in the population under study during this time frame. The logistic regression model was found to have an AUC of 0.89 (95% confidence interval [CI] = 0.84 to 0.94) when including four features: exposure history, temperature, white blood cell count (WBC), and chest radiograph result. Random forest method resulted in AUC of 0.86 (95% CI = 0.79 to 0.92) and gradient boosting had an AUC of 0.85 (95% CI = 0.79 to 0.91). With a consistently held negative predictive value, the logistic regression model had a positive predictive value of 0.29 (0.2–0.39) compared to 0.2 (0.14–0.28) for random forest and 0.22 (0.15–0.3) for the gradient‐boosted method.ConclusionThe derived predictive models offer good discriminating capacity for COVID‐19 disease and provide interpretable and usable methods for those providers caring for these patients at the important crossroads of the community and the health system. We found utilization of the logistic regression model utilizing exposure history, temperature, WBC, and chest X‐ray result had the greatest discriminatory capacity with the most interpretable model. Integrating a predictive model‐based approach to COVID‐19 testing decisions and patient care pathways and locations could add efficiency and accuracy to decrease uncertainty.

Endodontic Enigma: A case report series of mandibular premolars with two root canals

Endodontic treatment success depends on biomechanical preparation and 3-D obturation. Mandibular premolars have been reported with aberrant anatomy. The endodontic treatment of mandibular premolars may have major failure due to unrecognized or untreated multiple canals when they are present. Hence a thorough knowledge of the root canal morphology, careful radiographic interpretation and access cavity modifications are essentials for enhancing endodontic procedures. Keywords: Mandibular premolars, multiple canals, root canal treatment.

A histological evaluation of facial suture lines in six horses aged 1 day to 9 years

SummaryCraniofacial sutures are fibrous connections between the flat bones in the skull, allowing a small amount of movement to absorb strain and load as long as they are patent. In the present study, we examined the histological appearance of facial suture lines in horses of different ages. The internasal, nasofrontal and maxillolacrimal sutures were macroscopically identified and extracted from the skulls of six horses aged 1 day (two horses), 5 days, 2, 6 and 9 years and prepared into histological samples. The suture lines were then examined for width, form, cell density and morphology, vascularisation and morphology of the surrounding tissue and compared based on the age of the horse. Although macroscopically the sutures became difficult to identify in the 6‐ and 9‐year‐old horses, histologically they were clearly visible in all samples, indicating that the sutures were patent and consisted of connective tissue in all analysed horses. The sutures became subjectively narrower with lower cell density in older horses as compared to young horses, and there was a noticeable maturation from woven to cancellous bone surrounding the sutures. Vascular structures were present in all sutures regardless of age or location. In conclusion, this study raises awareness of the histological suture conformation in neonatal and adult horses and their persistence into adulthood. A better understanding of the histological structure of facial sutures and their continued patency into adulthood can aide in the interpretation of radiographs and computed tomography images of the head and in improving treatment methods and outcomes for horses affected with suture exostosis. In addition, if biopsies are taken, clinicians will have a basis on which to determine which cells are related to the disease process and which are normally occurring.

Artificial intelligence: contemporary applications and future compass

The clinical use of information technology in the dental profession has increased substantially in the past 10 to 20 years. In most developing countries an insufficiency of medical and dental specialists has increased the mortality of patients suffering from various diseases. Employing technology, especially artificial intelligence technology, in medical and dental application could reduce cost, time, human expertise and medical error. This approach has the potential to revolutionise the dental public health scenario in developing countries. Clinical decision support systems (CDSS) are computer programs that are designed to provide expert support for health professionals. The applications in dental sciences vary from dental emergencies to differential diagnosis of orofacial pain, radiographic interpretations, analysis of facial growth in orthodontia to prosthetic dentistry. However, despite the recognised need for CDSS, the implementation of these systems has been limited and slow. This can be attributed to lack of formal evaluation of the systems, challenges in developing standard representations, cost and practitioner scepticism about the value and feasibility of CDSS. Increasing public awareness of safety and quality has accelerated the adoption of generic knowledge based CDSS. Information technology applications for dental practice continue to develop rapidly and will hopefully contribute to reduce the morbidity and mortality of oral and maxillofacial diseases and in turn impact patient care.

The Utility of the Energy Subtraction Method for Thoracic Spine Radiography in Clinical Practice: An Analysis of 25 Patients With Multiple Myeloma.

Interpretation of thoracic spine radiographs is difficult because they cannot clearly depict the vertebrae due to overlap with soft tissues. This study aimed to evaluate whether thoracic spine radiographs obtained using the energy subtraction method could improve the accuracy of a diagnosis of thoracic osteolytic lesions. The authors analyzed 300 thoracic vertebrae from 25 patients with multiple myeloma who underwent thoracic spine radiography. All patients underwent thoracic spine radiography with 2 views. Two sets of images were prepared: computed radiography images (CR images) acquired using conventional processing parameters; and processed images for specifically visualizing bone, using the energy subtraction method (ES images). The CR images (CR group) and paired CR and ES images (CR+ES group) were interpreted in parallel by 5 orthopedic surgeons. The presence of osteolytic lesions was evaluated for each of the 12 thoracic vertebrae, and the sensitivity and specificity of the method were compared with computed tomography (CT), which is considered the gold standard. Subgroup analysis was also performed based on location. Osteolytic lesions were found on CT in 28 (9.3%) vertebrae of 12 patients. The overall sensitivities and specificities of the CR and CR+ES groups were 17.2% and 54.3%, respectively, and 95.6% and 98.0%, respectively, with statistically significant differences. Subgroup analysis showed particular improvement in the sensitivity for the CR+ES group in the middle thoracic spine compared with that at other locations. Thoracic spine radiographs generated using this method may improve the accuracy of diagnosis of thoracic osteolytic lesions. [Orthopedics. 2021;44(1):e31-e35.].

How massed practice improves visual expertise in reading panoramic radiographs in dental students: An eye tracking study.

The interpretation of medical images is an error-prone process that may yield severe consequences for patients. In dental medicine panoramic radiography (OPT) is a frequently used diagnostic procedure. OPTs typically contain multiple, diverse anomalies within one image making the diagnostic process very demanding, rendering students' development of visual expertise a complex task. Radiograph interpretation is typically taught through massed practice; however, it is not known how effective this approach is nor how it changes students' visual inspection of radiographs. Therefore, this study investigated how massed practice-an instructional method that entails massed learning of one type of material-affects processing of OPTs and the development of diagnostic performance. From 2017 to 2018, 47 dental students in their first clinical semester diagnosed 10 OPTs before and after their regular massed practice training, which is embedded in their curriculum. The OPTs contained between 3 to 26 to-be-identified anomalies. During massed practice they diagnosed 100 dental radiographs without receiving corrective feedback. The authors recorded students' eye movements and assessed the number of correctly identified and falsely marked low- and high prevalence anomalies before and after massed practice. Massed practice had a positive effect on detecting anomalies especially with low prevalence (p < .001). After massed practice students covered a larger proportion of the OPTs (p < .001), which was positively related to the detection of low-prevalence anomalies (p = .04). Students also focused longer, more frequently, and earlier on low-prevalence anomalies after massed practice (ps < .001). While massed practice improved visual expertise in dental students with limited prior knowledge, there is still substantial room for improvement. The results suggest integrating massed practice with more deliberate practice, where, for example, corrective feedback is provided, and support is adapted to students' needs.

Pneumonia Detection Using Deep Learning Architectures

Pneumonia is an infection caused by bacteria and viruses. It can shift from mellow to serious cases. This disease causes severe damages to the lungs since they fill with fluids. This situation causes difficulty in breathing. It further prevents oxygen to reach the blood. Pneumonia is diagnosed with the help of a chest X-rays, which can also use in the diagnosis of diseases like emphysema, lung cancer, and tuberculosis. According to WHO (World Health Organization (WHO). 2001. Standardization of Interpretation of Chest Radiographs for the Diagnosis of Pneumonia in Children. p.4.), Chest X-rays, at present, is the best available method for detecting pneumonia. Feature extraction methods like DiscreteWavelet Transform (DWT),Wavelet Frame Transform (WFT), andWavelet Packet Transform (WPT) can be used followed by any classification algorithm. In this paper, models like Squeezenet, DenseNet, and Resnet34 have been used for image recognition. In our system, the medical images were taken from Kaggle database and were recorded using a suitable imaging system. The images retrieved were then considered for input for the system where the images go through the various phases of image processing like pre-processing, edge detection and feature extraction. Later, a variety of training models are applied to know which model offers the highest accuracy.

The role of radiography in the study of spinal disorders.

Despite the growing use of computed tomography (CT) and magnetic resonance imaging (MRI) in the study of spinal disorders, radiography still plays an important role in many conditions affecting the spine. However, the study and interpretation of spine radiograph is receiving less attention and radiologists are increasingly unfamiliar with the typical findings in normal and pathologic conditions of the spine. The aim of this article is to review the radiologic indications of radiograph in different pathologic conditions that affect the spine, including congenital, traumatic, degenerative, inflammatory, infectious and tumour disorders, as well as their main radiographic manifestations.

An unusual case of unilateral hyperlucent lung

Differential diagnoses of unilateral hyperlucent lung are expansive, ranging from soft tissue to pulmonary parenchyma. A systematic approach to interpretation of radiography guides us in quick localisation of the anatomical site of involvement. https://bit.ly/3fNy4vT

An abnormal course of the interazygos vein: a case report

BackgroundThe azygos venous system in the posterior mediastinum has a complex developmental pattern.Case presentationDuring the dissection of this region, we encountered a variation in this system. In this case, we observed that the accessory hemiazygos and hemiazygos veins in the left side passed anterior to the aorta and drained to the azygos vein located on the left side of the vertebral column. Other structures were normal in this area.ConclusionsThis variation is important in mediastinal surgery and radiographic interpretation.

A Radiographic Assessment of Dental Morbidity in Patients with Multiple Myeloma Undergoing Autologous Stem Cell Transplant: A Retrospective Study

Aim: To assess the dental and oral morbidity in multiple myeloma patients as expressed in dental radiographs before autologous stem cell transplant. Materials and Methods: A retrospective study involving 79 multiple myeloma patients was designed to collect data prior to their autologous stem cell transplant. Patients were seen at the oral medicine clinic at the University of Florida College of Dentistry during the years 2010–2013. Through available patient data and interpretation of radiographs, the following variables were recorded: age, gender, carious lesions, periodontal disease, and periapical radiolucency. In addition, the incidence of root fragment retention and the presence of punched-out osteolytic lesions were recorded. Cochran–Mantel–Haenszel (CMH) tests and logistic regression were performed for descriptive analysis and presentation of the data. Results: Seventy-nine multiple myeloma patients were recruited for this study. Ages ranged from 28 to 79 years (mean = 61, SD = 9.6), including 41 (51.9%) females and 38 (48.1%) males. The results demonstrated dental decay in 64.56% of patients, periodontal disease in 62.03%, apical rarefying osteitis in 13.92% of patients, and punched-out lesions in 24.05% of patients. Conclusion: Our study indicates high dental morbidity in multiple myeloma patients prior to autologous stem cell transplant. The elimination of foci of infection is highly recommended prior to autologous stem cell transplant for this high-risk population because of the potential risk of bacteremia/septicemia from oral bacteria associated with dental morbidity.

Satisfaction of Search in Periapical Radiograph Interpretation

IntroductionSeveral studies in radiology and medicine have evaluated the satisfaction of search (SOS) error effect in chest radiography, abdominal radiography, osteoradiology, and patients with multiple trauma. No research to date has been published evaluating the possible existence of the SOS error phenomenon made during dental periapical radiograph interpretations. The purpose of the present pilot study was to determine if an SOS error effect exists when dental clinicians interpret periapical radiographs. The null hypothesis was that the detection accuracy will be the same or will improve for the detection of native lesions in the presence of an added abnormality. The alternative hypothesis is that there will be a decrease in detection accuracy for native lesions in the presence of an added abnormality. MethodsSix images were selected to be part of the present experiment. One of the 6 images served as the positive control, and another image served as the negative control. Four images, each including a single subtle carious lesion, were selected to represent the experimental images. The single subtle carious lesion present within the 4 experimental radiographs served as the native pathology, and an abnormality such as a periapical radiolucency, resorption, inadequate nonideal root canal obturation material, or recurrent carious lesion was artificially inserted into the image as the added pathology. Thus, the second set of images consisted of the same 4 images containing the native pathology including an added pathology that was inserted into the image using Adobe Photoshop CS6 (Adobe, Inc, San Jose, CA). Purposive sampling was obtained from 16 examiners including residents from endodontics and periodontics as well as alumni and faculty from the Saint Louis University Center for Advanced Dental Education, St Louis, MO. Each observer participated as a subject during 2 time-separated sessions. Each session was separated by a minimum period of 3 months' duration in order to prevent memory bias. Before starting each interpretation session, the participants were given verbal instructions. Subjects were instructed to provide a location (by tooth number), identify, and rate the presence of all suspected pathology using a Likert scale of 1–5 (1: definitely normal, 2: probably normal, 3: possibly abnormal, 4: probably abnormal, and 5: definitely abnormal). In the second session, the radiographs that were initially presented containing only the native lesion were presented again with the added abnormality, and vice versa. The observers' reports and confidence ratings were recorded and analyzed. Ratings of 3–5 were considered as being positive for the presence of pathology. ResultsA true SOS error occurs when the presence of the native lesion is reported correctly without an added abnormality but is not reported (missed) in the presence of an added abnormality. In our study, a true SOS error occurred in 13 of the 64 interpretation sets (20.31%). There was a total of 64 expected native lesions present within the 4 native images viewed by 16 observers. In the 4 added images, there was a total of 64 expected added findings. In the images containing only native lesions, the observers reported 30 of the 64 expected native lesions. In the images containing an artificially added abnormality, the observers reported 58 of the 64 expected added abnormalities and 25 of the 64 expected native lesions. Observers reported fewer native lesions in the presence of an added abnormality. ConclusionsThe current investigation demonstrated the existence of the SOS effect during periapical radiographic interpretations. In 20.31% of interpretations, a true SOS error occurred. This study is clinically relevant because it can help clinicians in reducing false-negative errors made during radiographic interpretation, thus preventing misdiagnosis.

Competency in Chest Radiography Interpretation by Junior Doctors and Final Year Medical Students at a Teaching Hospital.

Background Chest radiography (CXR) is a widely used imaging technique for assessing various chest conditions; however, little is known on the medical doctors' and medical students' level of skills to interpret the CXRs. This study assessed the residents, medical officers, house officers, and final year medical students' competency in CXRs interpretation and how the patient's clinical history influences the interpretation. Methods We conducted a cross-sectional study in the Cape Coast Teaching Hospital in the Central Region of Ghana among 99 nonradiologists, comprising 10 doctors in residency programmes, 18 medical officers, 33 house officers, and 38 final year medical students. The data collection was done with a semistructured questionnaire in two phases. In phase 1, ten CXRs were presented without patient's clinical history. Phase 2 involved the same ten CXRs presented in the same order alongside the patient's clinical history. Participants were given 3 minutes to interpret each image. Median and interquartile ranges were used to describe continuous variables, while frequencies and percentages were used to describe categorical variables. Test of significant difference and association was conducted using a Wilcoxon rank-sum test/Kruskal–Wallis test and chi-square (X2) test, respectively. Results The average score for interpreting CXRs was 7.0 (IQR = 5–8) and 4.0 (IQR = 3-4), when CXRs were, respectively, presented with and without clinical history. No significant difference was seen in average scores regarding the levels of formal training. Without clinical history, only 40.0% of residents, 22.2% of medical officers, 24.2% of house officers, and 13.2% of medical students correctly interpreted CXRs, while more than 75% each of all categories correctly interpreted CXRs when presented with clinical history. However, all participants had difficulties in identifying CXR with pneumothorax (27.3% vs. 30.3%), pneumomediastinum or left rib fracture (8.1% vs. 33.3%), and lung collapse (37.4% vs. 37.4%) in both situations, with and without patient clinical history. Conclusion The patient's clinical history was found to greatly influence doctors' competence in interpreting CXRs. We found a gap in doctors' and medical students' ability to interpret CXRs; hence, the development of this skill should be improved at all levels of medical training.

Deployment of artificial intelligence for radiographic diagnosis of COVID-19 pneumonia in the emergency department.

ObjectiveThe coronavirus disease 2019 pandemic has inspired new innovations in diagnosing, treating, and dispositioning patients during high census conditions with constrained resources. Our objective is to describe first experiences of physician interaction with a novel artificial intelligence (AI) algorithm designed to enhance physician abilities to identify ground‐glass opacities and consolidation on chest radiographs.MethodsDuring the first wave of the pandemic, we deployed a previously developed and validated deep‐learning AI algorithm for assisted interpretation of chest radiographs for use by physicians at an academic health system in Southern California. The algorithm overlays radiographs with “heat” maps that indicate pneumonia probability alongside standard chest radiographs at the point of care. Physicians were surveyed in real time regarding ease of use and impact on clinical decisionmaking.ResultsOf the 5125 total visits and 1960 chest radiographs obtained in the emergency department (ED) during the study period, 1855 were analyzed by the algorithm. Among these, emergency physicians were surveyed for their experiences on 202 radiographs. Overall, 86% either strongly agreed or somewhat agreed that the intervention was easy to use in their workflow. Of the respondents, 20% reported that the algorithm impacted clinical decisionmaking.ConclusionsTo our knowledge, this is the first published literature evaluating the impact of medical imaging AI on clinical decisionmaking in the emergency department setting. Urgent deployment of a previously validated AI algorithm clinically was easy to use and was found to have an impact on clinical decision making during the predicted surge period of a global pandemic.

Radiographic measurements of the normal distal radius: reliability of computer-aided CT versus physicians' radiograph interpretation.

We examined the reliability of a computer-aided cone-beam CT analysis of radiographic parameters of 50 normal distal radii and compared it with interobserver agreement of measurements made by three groups of physicians on two-dimensional plain radiographs. The intra-rater reliability of the computer-aided analysis was evaluated on 33 wrists imaged twice by cone-beam CT. The longitudinal axis, anterior tilt, radial inclination and ulnar variance were measured. The reliability of computer-aided analysis was excellent (intraclass correlation coefficient (ICC) 0.94-0.96) while the interobserver agreement of two-dimensional radiograph interpretation was good (ulnar variance, ICC 0.80-0.84) to poor (anterior tilt and radial inclination, ICC 0.20-0.42). We conclude that computer-aided cone-beam CT analysis was a reliable tool for radiographic parameter determination, whereas physicians demonstrated substantial variability especially in interpreting the angular parameters.