RESUMEN
Self-monitoring is essential for effectively regulating learning, but difficult in visual diagnostic tasks such as radiograph interpretation. Eye-tracking technology can visualize viewing behavior in gaze displays, thereby providing information about visual search and decision-making. We hypothesized that individually adaptive gaze-display feedback improves posttest performance and self-monitoring of medical students who learn to detect nodules in radiographs. We investigated the effects of: (1) Search displays, showing which part of the image was searched by the participant; and (2) Decision displays, showing which parts of the image received prolonged attention in 78 medical students. After a pretest and instruction, participants practiced identifying nodules in 16 cases under search-display, decision-display, or no feedback conditions (n = 26 per condition). A 10-case posttest, without feedback, was administered to assess learning outcomes. After each case, participants provided self-monitoring and confidence judgments. Afterward, participants reported on self-efficacy, perceived competence, feedback use, and perceived usefulness of the feedback. Bayesian analyses showed no benefits of gaze displays for post-test performance, monitoring accuracy (absolute difference between participants' estimated and their actual test performance), completeness of viewing behavior, self-efficacy, and perceived competence. Participants receiving search-displays reported greater feedback utilization than participants receiving decision-displays, and also found the feedback more useful when the gaze data displayed was precise and accurate. As the completeness of search was not related to posttest performance, search displays might not have been sufficiently informative to improve self-monitoring. Information from decision displays was rarely used to inform self-monitoring. Further research should address if and when gaze displays can support learning.
RESUMEN
While radiological imaging is presented as two-dimensional images either on radiography or cross-sectional imaging, it is important for interpreters to understand three-dimensional anatomy and pathology. We hypothesized that virtual reality (VR) may serve as an engaging and effective way for trainees to learn to extrapolate from two-dimensional images to an understanding of these three-dimensional structures. We created a Google Cardboard Virtual Reality application that depicts intracranial vasculature and aneurysms. We then recruited 12 medical students to voluntarily participate in our study. The performance of the students in identifying intracranial aneurysms before and after the virtual reality training was evaluated and compared to a control group. While the experimental group's performance in correctly identifying aneurysms after virtual reality educational intervention was better than the control's (experimental increased by 5.3%, control decreased by 2.1%), the difference was not statistically significant (p-value of 0.06). Significantly, survey data from the medical students was very positive with students noting they preferred the immersive virtual reality training over conventional education and believed that VR would be a helpful educational tool for them in the future. We believe virtual reality can serve as an important tool to help radiology trainees better understand three-dimensional anatomy and pathology.
Asunto(s)
Aneurisma Intracraneal , Estudiantes de Medicina , Realidad Virtual , Humanos , Aprendizaje , Aneurisma Intracraneal/diagnóstico por imagen , Tomografía Computarizada por Rayos XRESUMEN
PURPOSE: This retrospective review examines the incidence of pulmonary embolism (PE) during computed tomography pulmonary angiography (CTPA) exams performed in the emergency room setting of a tertiary care center over dominant periods of the ancestral, Delta, and Omicron variants of COVID-19. MATERIALS/METHODS: Demographic information, patient comorbidities and risk factors, vaccination status, and COVID-19 infection status were collected from patient's charts. Incidence of PE in COVID positive patients was compared between variant waves. Subgroup analysis of vaccination effect was performed. RESULTS: CTPA was ordered in 18.3% of COVID-19 positive patients during the ancestral variant period, 18.3% during the Delta period and 17.3% during the Omicron wave. PE was seen in 15.0% of the ancestral COVID-19 variant cohort, 10.6% in the Delta COVID cohort and 9.23% of the Omicron cohort, reflecting a 41% and 60% increased risk of PE with ancestral variants compared to Delta and Omicron periods respectively. The study however was underpowered and the difference in rate of PE did not reach statistically significance (p = 0.43 and p = 0.22). Unvaccinated patients had an 2.75-fold increased risk of COVID-associated PE during the Delta and Omicron periods (p = .02) compared to vaccinated or recovered patients. CONCLUSION: Vaccination reduces the risk of COVID-19 associated PE. Patients infected with the Delta and Omicron COVID-19 variants may have a lower incidence of pulmonary embolism, though a larger or multi-institution study is needed to prove definitively.
Asunto(s)
COVID-19 , Embolia Pulmonar , Vacunas , Humanos , Incidencia , Embolia Pulmonar/diagnóstico por imagen , Embolia Pulmonar/epidemiología , SARS-CoV-2RESUMEN
Recent studies have demonstrated the effectiveness of simulation in radiology perceptual education. While current software exists for perceptual research, these software packages are not optimized for inclusion of educational materials and do not have full integration for presentation of educational materials. To address this need, we created a user-friendly software application, RadSimPE. RadSimPE simulates a radiology workstation, displays radiology cases for quantitative assessment, and incorporates educational materials in one seamless software package. RadSimPE provides simple customizability for a variety of educational scenarios and saves results to quantitatively document changes in performance. We performed two perceptual education studies involving evaluation of central venous catheters: one using RadSimPE and the second using conventional software. Subjects in each study were divided into control and experimental groups. Performance before and after perceptual education was compared. Improved ability to classify a catheter as adequately positioned was demonstrated only in the RadSimPE experimental group. Additional quantitative performance metrics were similar for both the group using conventional software and the group using RadSimPE. The study proctors felt that it was qualitatively easier to run the RadSimPE session due to integration of educational material into the simulation software. In summary, we created a user-friendly and customizable simulated radiology workstation software package for perceptual education. Our pilot test using the software for central venous catheter assessment was a success and demonstrated effectiveness of our software in improving trainee performance.
Asunto(s)
Competencia Clínica , Radiología , Simulación por Computador , Evaluación Educacional , Humanos , Radiología/educación , Programas InformáticosRESUMEN
OBJECTIVE. The goal of this article is to examine some of the current cardiothoracic radiology applications of artificial intelligence in general and deep learning in particular. CONCLUSION. Artificial intelligence has been used for the analysis of medical images for decades. Recent advances in computer algorithms and hardware, coupled with the availability of larger labeled datasets, have brought about rapid advances in this field. Many of the more notable recent advances have been in the artificial intelligence subfield of deep learning.
RESUMEN
OBJECTIVE: Contagious infectious diseases add a new dimension to radiology and pose many unanswered questions. In particular, what is the safest way to image patients with contagious and potentially lethal infectious diseases? Here, we describe protocols used by Emory University to successfully acquire chest radiographs of patients with Ebola virus disease. CONCLUSION: Radiology departments need to develop new protocols for various modalities used in imaging patients with contagious and potentially lethal infectious diseases.
Asunto(s)
Infección Hospitalaria/prevención & control , Fiebre Hemorrágica Ebola/diagnóstico por imagen , Fiebre Hemorrágica Ebola/prevención & control , Seguridad del Paciente/normas , Guías de Práctica Clínica como Asunto , Radiografía Torácica/normas , Administración de la Seguridad/normas , Infección Hospitalaria/diagnóstico por imagen , Georgia , HumanosRESUMEN
Pleural effusions are categorized as transudative or exudative, with transudative effusions usually reflecting the sequala of a systemic etiology and exudative effusions usually resulting from a process localized to the pleura. Common causes of transudative pleural effusions include congestive heart failure, cirrhosis, and renal failure, whereas exudative effusions are typically due to infection, malignancy, or autoimmune disorders. This document summarizes appropriateness guidelines for imaging in four common clinical scenarios in patients with known or suspected pleural effusion or pleural disease. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.
Asunto(s)
Medicina Basada en la Evidencia , Derrame Pleural , Sociedades Médicas , Humanos , Derrame Pleural/diagnóstico por imagen , Estados Unidos , Enfermedades Pleurales/diagnóstico por imagen , Diagnóstico por Imagen/métodos , Diagnóstico por Imagen/normas , Diagnóstico DiferencialRESUMEN
Purpose: Perceptual errors account for a significant percent of errors in radiology. Reasons for failure to identify significant lesions are partially due to suboptimal differences in image contrast. The goal of this study is to determine if teaching trainees how to adjust image contrast, window, and level helps trainees identify pulmonary nodules on chest radiographs (CXRs). Approach: Fourteen medical students voluntarily participated. Subjects were asked to identify pulmonary nodules on CXRs before and after being taught how to adjust image contrast, window, and level. At the end of the study, subjects were given a survey assessing their perceptions about their training. Results: The experimental group was more confident in their ability to localize nodules relative to the control group ( P -value = 0.003). Subjects demonstrated statistically significant improvement in their ability to identify and localize nodules, with the experimental group performing better than the control group, though there was no statistically significant difference between groups. Participant survey indicated that they felt this training was beneficial, P -values for all survey responses were significant ( P -values all < 0.02 ). Conclusions: Teaching subjects how to window and level medical images may be a useful adjunct to current training for medical image interpretation.
RESUMEN
Purpose: Gamification is used in several fields as an adjunct to standard educational methods but has found limited application in radiology to date. Gamification may be useful for teaching radiology skills typically acquired through experience, such as perceptual skills. The goal of our study is to use a gamified radiology workstation to teach skills related to identification of pulmonary nodules and evaluate for changes in trainee performance. Approach: We constructed a game called RADHunters to teach perceptual skills related to identification of pulmonary nodules on chest radiographs. Control and experimental groups were tasked with identifying nodules on chest radiographs on two sets of cases. The experimental group received gamified training for nodule identification using RADHunters between case sets, while the control group did not. Performance at nodule identification, localization, and confidence were compared. A poststudy survey was administered to assess for participants' thoughts about the gamified nodule detection training. Results: Survey responses were very positive with p -values for all survey responses < 0.001 , indicating subjects felt this training was beneficial. Experimental and control groups had a statistically significant improvement in their ability to identify and localize nodules with p -values < 0.05 . There was no significant difference between control and experimental groups. Neither group showed a statistically significant increase in their confidence in nodule localization. Conclusions: Perceptual training using gamification may be a useful adjunct to conventional methods of radiology education.
RESUMEN
Purpose: Diagnostic errors are common in radiology. The gestalt impression of an image refers to the rapid holistic understanding one formulates about an image and may facilitate improved diagnostic accuracy. The ability to generate a gestalt impression is typically acquired over time and is generally not explicitly taught. Our study aims to assess whether perceptual training using second look and minification technique (SLMT) can help image interpreters formulate a holistic understanding of an image and become more accurate at evaluating medical images. Approach: Fourteen healthcare trainees voluntarily participated in a perceptual training module, comparing the differences in detection of nodules and other actionable finding (OAF) on chest radiographs before and after perceptual training intervention. The experimental group received SLMT training, and the control group did not. Results: Survey results were positive for all items, with the p-values <0.01. There was improvement in the performance in detection of nodules and OAF in both groups. However, this change was statistically significant only for OAFs in the control group (p-value <0.05) but not the experimental group. Conclusions: SLMT training was viewed by participants as an extremely helpful educational tool. Survey results indicated that participants felt the SLMT was a beneficial educational intervention. The experimental group's detection of nodules and OAF improved after SLMT, though not statistically significantly so, which may be related to the small sample size or lack of training effect. Perceptual training using SLMT may help as a useful educational technique, help radiologists identify abnormalities, and improve workflow.
RESUMEN
Diffuse lung diseases are a heterogeneous group of disorders that can be difficult to differentiate by imaging using traditional methods of evaluation. The overlap between various disorders results in difficulty when medical professionals attempt to interpret images. Artificial intelligence offers new tools for the evaluation and quantification of imaging of patients with diffuse lung disease.
Asunto(s)
Inteligencia Artificial , Enfermedades Pulmonares , Diagnóstico por Imagen , Humanos , Enfermedades Pulmonares/diagnóstico por imagen , Redes Neurales de la ComputaciónRESUMEN
Deep learning has shown recent success in classifying anomalies in chest x-rays, but datasets are still small compared to natural image datasets. Supervision of abnormality localization has been shown to improve trained models, partially compensating for dataset sizes. However, explicitly labeling these anomalies requires an expert and is very time-consuming. We propose a potentially scalable method for collecting implicit localization data using an eye tracker to capture gaze locations and a microphone to capture a dictation of a report, imitating the setup of a reading room. The resulting REFLACX (Reports and Eye-Tracking Data for Localization of Abnormalities in Chest X-rays) dataset was labeled across five radiologists and contains 3,032 synchronized sets of eye-tracking data and timestamped report transcriptions for 2,616 chest x-rays from the MIMIC-CXR dataset. We also provide auxiliary annotations, including bounding boxes around lungs and heart and validation labels consisting of ellipses localizing abnormalities and image-level labels. Furthermore, a small subset of the data contains readings from all radiologists, allowing for the calculation of inter-rater scores.
Asunto(s)
Tecnología de Seguimiento Ocular , Radiografía Torácica , Aprendizaje Profundo , Humanos , Radiografía , Rayos XRESUMEN
Purpose: Experienced radiologists have enhanced global processing ability relative to novices, allowing experts to rapidly detect medical abnormalities without performing an exhaustive search. However, evidence for global processing models is primarily limited to two-dimensional image interpretation, and it is unclear whether these findings generalize to volumetric images, which are widely used in clinical practice. We examined whether radiologists searching volumetric images use methods consistent with global processing models of expertise. In addition, we investigated whether search strategy (scanning/drilling) differs with experience level. Approach: Fifty radiologists with a wide range of experience evaluated chest computed-tomography scans for lung nodules while their eye movements and scrolling behaviors were tracked. Multiple linear regressions were used to determine: (1) how search behaviors differed with years of experience and the number of chest CTs evaluated per week and (2) which search behaviors predicted better performance. Results: Contrary to global processing models based on 2D images, experience was unrelated to measures of global processing (saccadic amplitude, coverage, time to first fixation, search time, and depth passes) in this task. Drilling behavior was associated with better accuracy than scanning behavior when controlling for observer experience. Greater image coverage was a strong predictor of task accuracy. Conclusions: Global processing ability may play a relatively small role in volumetric image interpretation, where global scene statistics are not available to radiologists in a single glance. Rather, in volumetric images, it may be more important to engage in search strategies that support a more thorough search of the image.
RESUMEN
Artificial intelligence (AI) systems play an increasingly important role in all parts of the imaging chain, from image creation to image interpretation to report generation. In order to responsibly manage radiology AI systems and make informed purchase decisions about them, radiologists must understand the underlying principles of AI. Our task force was formed by the Radiology Research Alliance (RRA) of the Association of University Radiologists to identify and summarize a curated list of current educational materials available for radiologists.
Asunto(s)
Inteligencia Artificial , Radiología , Humanos , Radiografía , RadiólogosRESUMEN
Guest editors provide an introduction to the Special Section on Medical Image Perception and Observer Performance.
RESUMEN
Prior research has demonstrated that perceptual training can improve the ability of healthcare trainees in identifying abnormalities on medical images, but it is unclear if the improved performance is due to learning or attentional shift-the diversion of perceptional resources away from other activities to a specified task. Our objective is to determine if research subject performance in perceiving the central venous catheter position on radiographs is improved after perceptional training and if improved performance is due to learning or an attentional shift. Forty-one physician assistant students were educated on the appropriate radiographic position of central venous catheters and then asked to evaluate the catheter position in two sets of radiographic cases. The experimental group was provided perceptional training between case sets one and two. The control group was not. Participants were asked to characterize central venous catheters for appropriate positioning (task of interest) and to assess radiographs for cardiomegaly (our marker for attentional shift). Our results demonstrated increased confidence in localization in the experimental group ( p -value < 0.001 ) but not in the control group ( p - value = 0.882 ). The ability of subjects to locate the catheter tip significantly improved in both control and experimental groups. Both the experimental ( p - value = 0.007 ) and control groups ( p - value = 0.001 ) demonstrated equivalent decreased performance in assessing cardiomegaly; the difference between groups was not significant ( p - value = 0.234 ). This suggests the performance improvement was secondary to learning not due to an attentional shift.
RESUMEN
A substantial number of medical errors in radiology are attributed to failures of perception or decision making, although it is believed that experience (or expertise) might buffer diagnosticians from some types of perceptual-cognitive bias. We examined how the quality of contextual information influences decision making and how underlying perceptual-cognitive processes change as a function of experience and diagnostic accuracy. Twenty-one radiologists dictated their findings on 16 deidentified musculoskeletal radiographic cases while wearing a mobile-eye tracking system. Patient histories were mismatched on a subset of cases to be miscued relative to the correct diagnosis. Experienced radiologists outperformed less-experienced participants, but no systematic differences in gaze behaviors emerged between groups. Miscued case notes increased perceptual-cognitive bias in both groups, resulting in an approximate 40% decrease in diagnostic accuracy. Most errors were judgment errors, meaning participants visually fixated on the abnormality for longer than a second yet still failed to make the correct diagnosis. Findings suggest a physician's confidence in their diagnosis might be misplaced after spending insufficient time extracting relevant information from key areas of the visual display, or when decisions are based primarily on a priori expectations derived from patient histories. (PsycInfo Database Record (c) 2020 APA, all rights reserved).
Asunto(s)
Cognición , Radiólogos , Radiología , Percepción Visual , Sesgo , HumanosRESUMEN
Interpretation of increasingly complex imaging studies involves multiple intricate tasks requiring visual evaluation, cognitive processing, and decision-making. At each stage of this process, there are opportunities for error due to human factors including perceptual and ergonomic conditions. Investigation into the root causes of interpretive error in radiology first began over a century ago. In more recent work, there has been increasing recognition of the limits of human image perception and other human factors and greater acknowledgement of the role of the radiologist's environment in increasing the risk of error. This article reviews the state of research on perceptual and interpretive error in radiology. This article focuses on avenues for further error examination, and strategies for mitigating these errors are discussed. The relationship between artificial intelligence and interpretive error is also considered.