RESUMO
The adage "a picture is worth a thousand words" holds true in medicine, especially so in radiology. Although the images radiologists interpret are highly detailed, there often is no substitute for a concise diagrammatic illustration. Medical illustrations can help to clarify anatomy, pathology, and procedures-relaying complex information in a simple and easily understandable format. Medical illustrations have become ubiquitous in medical education and sought after for publications. Unfortunately, existing best-fit illustrations are not always available to complement discussion points. Thus, academicians are well served by the ability to produce their own illustrations. Although creating medical illustrations may seem unachievable to amateur artists, this is not necessarily the case. Digital illustration does not require the typical artistic skills needed for drawing with pen and paper or painting on a canvas. Radiologists of all skill levels, including those who do not view themselves as artistically inclined, can create their own high-quality original diagrams. Whether drawn freehand with a stylus or traced with a mouse, simple and complex digital works are within reach. However, the utility of illustration programs for radiologists is not inherently obvious, and discussion of useful features in the radiology literature is lacking. Digital illustration programs are accessible to most radiologists, and the process can be simplified to an easily approachable level, with illustration complexity left to the artist's discretion. Online supplemental material is available for this article. ©RSNA, 2018.
Assuntos
Gráficos por Computador , Diagnóstico por Imagem , Ilustração Médica , Radiologistas , Software , HumanosRESUMO
The field of Radiology is continually changing, requiring corresponding evolution in both medical student and resident training to adequately prepare the next generation of radiologists. With advancements in adult education theory and a deeper understanding of perception in imaging interpretation, expert educators are reshaping the training landscape by introducing innovative teaching methods to align with increased workload demands and emerging technologies. These include the use of peer and interdisciplinary teaching, gamification, case repositories, flipped-classroom models, social media, and drawing and comics. This publication aims to investigate these novel approaches and offer persuasive evidence supporting their incorporation into the updated Radiology curriculum.
Assuntos
Currículo , Radiologistas , Radiologia , Humanos , Radiologistas/educação , Radiologia/educaçãoRESUMO
In this study, we present a method based on Monte Carlo Dropout (MCD) as Bayesian neural network (BNN) approximation for confidence-aware severity classification of lung diseases in COVID-19 patients using chest X-rays (CXRs). Trained and tested on 1208 CXRs from Hospital 1 in the USA, the model categorizes severity into four levels (i.e., normal, mild, moderate, and severe) based on lung consolidation and opacity. Severity labels, determined by the median consensus of five radiologists, serve as the reference standard. The model's performance is internally validated against evaluations from an additional radiologist and two residents that were excluded from the median. The performance of the model is further evaluated on additional internal and external datasets comprising 2200 CXRs from the same hospital and 1300 CXRs from Hospital 2 in South Korea. The model achieves an average area under the curve (AUC) of 0.94 ± 0.01 across all classes in the primary dataset, surpassing human readers in each severity class and achieves a higher Kendall correlation coefficient (KCC) of 0.80 ± 0.03. The performance of the model is consistent across varied datasets, highlighting its generalization. A key aspect of the model is its predictive uncertainty (PU), which is inversely related to the level of agreement among radiologists, particularly in mild and moderate cases. The study concludes that the model outperforms human readers in severity assessment and maintains consistent accuracy across diverse datasets. Its ability to provide confidence measures in predictions is pivotal for potential clinical use, underscoring the BNN's role in enhancing diagnostic precision in lung disease analysis through CXR.
RESUMO
PURPOSE: To evaluate relative detection of pulmonary embolism (PE) with standard bolus-triggered contrast-enhanced breath-hold magnetic resonance (MR) pulmonary angiography, contrast-enhanced recirculation-phase breath-hold low-flip angle three-dimensional (3D) gradient-echo (GRE), and nonenhanced free-induction cardiac- and respiratory-triggered true fast imaging with steady-state precession (FISP) MR sequences. MATERIALS AND METHODS: The study was HIPAA compliant and institutional review board approved. Twenty-two patients with a computed tomographic (CT) angiography diagnosis of PE underwent MR imaging within 48 hours of CT. MR included three complementary techniques: MR pulmonary angiography, 3D GRE, and triggered true FISP. Each sequence was analyzed separately by two independent reviewers who recorded presence of emboli in categorized pulmonary artery anatomic territories. CT angiography results were analyzed by a third independent reviewer, who retrospectively recorded presence of emboli using the same format; these results served as the reference standard. Sensitivity, specificity, and positive and negative predictive values for PE detection were calculated for each MR technique on a per-embolus basis, and 95% confidence intervals were calculated according to the efficient-score method. A two-sample t test was used to compare values among MR techniques. RESULTS: Sensitivities for PE detection were 55% for MR pulmonary angiography, 67% for triggered true FISP, and 73% for 3D GRE MR imaging. Combining all three MR sequences improved overall sensitivity to 84%. Specificity was 100% for all detection methods except for MR pulmonary angiography (one false-positive). Agreement between readers was high (κ = 0.87). Embolus detection rates were lowest in the lingula branch for all MR sequences compared with remainder of the vascular territories (P = .07). CONCLUSION: There are complementary benefits to combining standard MR pulmonary angiography, 3D GRE, and triggered true FISP MR examinations for evaluation of PE.
Assuntos
Angiografia/métodos , Imageamento Tridimensional , Imageamento por Ressonância Magnética/métodos , Embolia Pulmonar/diagnóstico , Idoso , Técnicas de Imagem de Sincronização Cardíaca , Meios de Contraste , Diagnóstico Diferencial , Feminino , Humanos , Interpretação de Imagem Assistida por Computador , Masculino , Pessoa de Meia-Idade , Valor Preditivo dos Testes , Técnicas de Imagem de Sincronização Respiratória , Estudos Retrospectivos , Sensibilidade e Especificidade , Tomografia Computadorizada por Raios XRESUMO
OBJECTIVE: The purpose was to evaluate reader variability between experienced and in-training radiologists of COVID-19 pneumonia severity on chest radiograph (CXR), and to create a multireader database suitable for AI development. METHODS: In this study, CXRs from polymerase chain reaction positive COVID-19 patients were reviewed. Six experienced cardiothoracic radiologists and two residents classified each CXR according to severity. One radiologist performed the classification twice to assess intraobserver variability. Severity classification was assessed using a 4-class system: normal (0), mild (1), moderate (2), and severe (3). A median severity score (Rad Med) for each CXR was determined for the six radiologists for development of a multireader database (XCOMS). Kendal Tau correlation and percentage of disagreement were calculated to assess variability. RESULTS: A total of 397 patients (1208 CXRs) were included (mean age, 60 years SD ± 1), 189 men). Interobserver variability between the radiologists ranges between 0.67 and 0.78. Compared to the Rad Med score, the radiologists show good correlation between 0.79-0.88. Residents show slightly lower interobserver agreement of 0.66 with each other and between 0.69 and 0.71 with experienced radiologists. Intraobserver agreement was high with a correlation coefficient of 0.77. In 220 (18%), 707 (59%), 259 (21%) and 22 (2%) CXRs there was a 0, 1, 2 or 3 class-difference. In 594 (50%) CXRs the median scores of the residents and the radiologists were similar, in 578 (48%) and 36 (3%) CXRs there was a 1 and 2 class-difference. CONCLUSION: Experienced and in-training radiologists demonstrate good inter- and intraobserver agreement in COVID-19 pneumonia severity classification. A higher percentage of disagreement was observed in moderate cases, which may affect training of AI algorithms. ADVANCES IN KNOWLEDGE: Most AI algorithms are trained on data labeled by a single expert. This study shows that for COVID-19 X-ray severity classification there is significant variability and disagreement between radiologist and between residents.
Assuntos
COVID-19 , Algoritmos , Inteligência Artificial , COVID-19/diagnóstico por imagem , Humanos , Masculino , Pessoa de Meia-Idade , Radiografia Torácica , Radiologistas , Estudos RetrospectivosRESUMO
Cardiac computed tomography (CT) scans can produce enormous datasets (>3,000 images), making traditional axial image interpretation un-workable. Previously existing and new techniques including multiplanar reformats, volume rendering, maximum intensity projections, curved multiplanar reformats, and "4D" (time-resolved) methods have all been used to increase diagnostic accuracy and reduce interpretation times. The methods and applications of these techniques to cardiac anatomy will be reviewed and discussed with an eye toward practical film interpretation.