Computed Tomography Coronary Angiography on a Detector-Based Spectral Computed Tomography Platform: Evaluation of Patients With Coronary Artery Disease Reporting and Data System Score of 3 and Higher.

PURPOSE: Computed tomography (CT) coronary angiography performed on a detector-based spectral scanner helps more closely approximate severity of stenosis with nuclear medicine and cardiac catheterization tests compared with single-energy CT (SECT) in patients with an original CAD-RADS score of 3 and higher. METHODS: This retrospective trial was conducted between January 2017 and December 2019 and included 52 patients with a CAD-RADS score of 3 and higher. Two reading sessions were performed 6 weeks apart. The first reading session was performed using only conventional images and the second reading session was performed using spectral results. Detector-based spectral CT CAD-RADS scores were compared with cardiac stress test and/or cardiac catheterization results for final characterization of stenosis in 41 segments from 32 patients. The mean CAD-RADS score was calculated for both the conventional images and spectral images. RESULTS: The CAD-RADS score for SECT and the score for spectral CT for the 41 segments were compared. Available associated stress test and/or cardiac catheterization results were also compared with CAD-RADS scores. In 51% (21/41), a diagnosis concordant with best practices results was achieved with the help of spectral CT results. A mean CAD-RADS score of 3.56 was obtained using spectral results, compared with 3.93 using conventional images. A 2-tailed paired t test determined the difference to be significant with a P value of 0.007. CONCLUSIONS: Computed tomography coronary angiography is feasible on a detector-based spectral CT scanner and can improve diagnostic confidence over SECT angiography in patients with an original CAD-RADS score of 3 and higher.

Radiomics in Abdominopelvic Solid-Organ Oncologic Imaging: Current Status.

Radiomics is the process of extraction of high-throughput quantitative imaging features from medical images. These features represent noninvasive quantitative biomarkers that go beyond the traditional imaging features visible to the human eye. This article first reviews the steps of the radiomics pipeline, including image acquisition, ROI selection and image segmentation, image preprocessing, feature extraction, feature selection, and model development and application. Current evidence for the application of radiomics in abdominopelvic solid-organ cancers is then reviewed. Applications including diagnosis, subtype determination, treatment response assessment, and outcome prediction are explored within the context of hepatobiliary and pancreatic cancer, renal cell carcinoma, prostate cancer, gynecologic cancer, and adrenal masses. This literature review focuses on the strongest available evidence, including systematic reviews, meta-analyses, and large multicenter studies. Limitations of the available literature are highlighted, including marked heterogeneity in radiomics methodology, frequent use of small sample sizes with high risk of overfitting, and lack of prospective design, external validation, and standardized radiomics workflow. Thus, although studies have laid a foundation that supports continued investigation into radiomics models, stronger evidence is needed before clinical adoption.

Influences of the Social Media Continuum Model in Radiology: Theory and Reality.

Social media utilization has been growing exponentially worldwide and has created a thriving venue for radiologists and the profession of radiology to engage in on both the academic and social levels. The aim of this article is to conduct updated literature review and address a gap in the literature by introducing a simple classification for social media utilization and a new theoretical model to outline the role and potential value of social media in the realm of radiology. We propose classifying social media through usage-driven and access-driven indices. Furthermore, we discuss the interdependency of radiologists, other physicians and non-physician stakeholders, scientific journals, conferences/meetings and the general public in an integrated social media continuum model. With the ongoing sub-specialization of radiology, social media helps mitigate the physical barriers of making connections with peers and audiences which would have otherwise been unfeasible. The constant evolution and diversification of social media platforms necessitates a novel approach to better understand its role through a radiological lens. With the looming fear of 'ancillary service' labelling, social media could be the golden plate to halt the path towards commoditization of radiology.

Can Radiographic Tumor Volume of Oral Squamous Cell Carcinoma Help Predict Clinical and Pathological Tumor Features?

PURPOSE: Radiographic tumor volume (RTV) of oral squamous cell carcinoma (SCC) is seldom measured in practice. Aims of the study are to estimate RTV of SCC and to investigate its relationship with clinical and pathological stage, tumor margin status, recurrence, and need for chemo/radiation. METHODS: The design is a retrospective cohort study. The predictor variable is SCC RTV. The primary outcome variables are clinical and pathological tumor size. The secondary outcomes are margin status and postoperative chemo/radiation. Tumor dimensions were measured on preoperative maxillofacial or neck computer tomography images with contrast. Information on patient and tumor characteristics was obtained. Pearson correlation, t test, ANOVA and log rank test were used for statistical analysis. The significance level was set at .05. RESULTS: Thirty-six subjects aged 36 to 86 were included in the study. Positive association was found between clinical T stage and RTV (P = .0003) and between pathologic T stage and RTV (P = .002). Mean value of RTV was significantly higher in the group with positive margins (P = .0004). RTV was significantly higher in cancers requiring adjuvant chemo/radiation (P = .033). Mean RTV for patients with recurrence was 1.86 cm3 as compared to 1.29 cm3 for patients with no recurrence. Higher tumor volumes were more likely to be associated with recurrence. CONCLUSIONS: RTV is a variable that is readily available to head and neck surgeons. RTV is associated with clinical and pathological tumor sizes, margin status, need for adjuvant chemo/radiation and tumor recurrence.

Diagnosis in a snap: a pilot study using Snapchat in radiologic didactics.

PURPOSE: To evaluate Snapchat, an image-based social media platform, as a tool for emergency radiologic didactics comparing image interpretation on mobile devices with conventional analysis on a classroom screen. MATERIALS AND METHODS: Seven radiology residents (4 juniors, 3 seniors;4 males, 3 females; 28.4 years old, ± 1.7 years) were shown 5 emergent radiologic cases using Snapchat and 5 cases of similar content and duration on a classroom projector over 4 weeks. All images depicted diagnoses requiring immediate communication to ordering physicians. Performance was scored 0-2 (0 = complete miss, 1 = major finding, but missed the diagnosis, 2 = correct diagnosis) by two attending radiologists in consensus. RESULTS: All residents performed better on Snapchat each week. In weeks 1-4, juniors scored 21/40 (52.5%), 23/40 (57.5%), 19/40 (47.5%), and 18/40 (45%) points using Snapchat compared with 13/40 (32.5%), 23/40 (57.5%), 14/40 (35%), and 13/40 (32.5%), respectively, each week by projector, while seniors scored 19/30 (63.3%), 21/30 (70%), 27/30 (90%), and 21/30 (70%) on Snapchat versus 16/30 (53.3%), 19/30 (63.3%), 20/30 (66.7%), and 20/30 (66.7%) on projector. Four-week totals showed juniors scoring 81/160 (50.6%) on Snapchat and 63/160 (39.4%) by projector compared with seniors scoring 88/120 (73.3%) and 75/120 (62.5%), respectively. Performance on Snapchat was statistically, significantly better than via projector during weeks 1 and 3 (p values 0.0019 and 0.0031). CONCLUSION: Radiology residents interpreting emergency cases via Snapchat showed higher accuracy compared with using a traditional classroom screen. This pilot study suggests that Snapchat may have a role in the digital radiologic classroom's evolution.

Analysis of Potential for User Errors in Mobile Deployment of Radiology Deep Learning for Cardiac Rhythm Device Detection.

We examine how convolutional neural networks (CNNs) for cardiac rhythm device detection can exhibit failures in performance under suboptimal deployment scenarios and examine how medically adversarial image presentation can further impair neural network performance. We validated the publicly available Pacemaker-ID web server and mobile app on 43 local hospital emergency department (ED) cases of patients presenting with a cardiac rhythm device on anterior-posterior (AP) chest radiograph and assessed performance using Cohen's kappa coefficient for inter-rater reliability. To illustrate adversarial performance concerns, we then produced example CNN models using the 65,379 patient MIMIC-CXR chest radiograph retrospective database and evaluated performance with area under the receiver operating characteristic (AUROC). In retrospective review of 43 patients with cardiac rhythm devices on AP chest radiographs during our study period (January 1, 2020 to March 1, 2020), 74.4% (32/43) had device manufacturer information readily available within the electronic medical record. A total of 25.6% of patients (11/43) did not have this information documented in the patient chart and could ostensibly benefit from CNN-based identification of device manufacturer. For patients with known device manufacturer, the Pacemaker-ID prediction was accurate in 87.5% of cases (28/32). Mobile app accuracy varied from 62.5 to 93.75% depending on image capture settings and presentation. Cohen's kappa coefficient varied from 0.448 to 0.897 depending on mobile image capture conditions. For our additional analysis of medically adversarial performance failures with a DenseNet121 trained on MIMIC-CXR images, we showed that an AUROC of 0.9807 ± 0.0051 could be achieved on an example testing dataset while masking a 30% false positive rate in identification of cardiac rhythm devices versus clinically distinct entities such as vagal nerve stimulators. Despite the promise of CNN approaches for cardiac rhythm device analysis on chest radiographs, further study is warranted to assess potential for errors driven by user misuse when deploying these models to mobile devices as well as for cases when performance can be impaired by the presence of other support apparatuses.

Estimation of age in unidentified patients via chest radiography using convolutional neural network regression.

PURPOSE: Patient age has important clinical utility for refining a differential diagnosis in radiology. Here, we evaluate the potential for convolutional neural network models to predict patient age based on anterior-posterior chest radiographs for instances where patients may present for emergency services without the ability to provide this identifying information. METHODS: We used the CheXpert dataset of 224,316 chest radiographs from 65,240 patients to train CNN regression models with ResNet50 and DenseNet121 architectures for prediction of patient age based on anterior-posterior (AP) view chest radiographs. We evaluate these models on both the CheXpert validation dataset and a local hospital case in which a patient initially presented for emergency services intubated and without identification. RESULTS: Mean absolute error (MAE) for our ResNet50 model on the CheXpert dataset is 4.94 years for predicting patient age based on AP chest radiographs. MAE for our DenseNet121 model is 4.69 years. Both models have a correlation coefficient between true patient ages and predicted ages of 0.944. Wilcoxon rank-sum comparison between the two model architectures shows no significant difference (p = 0.33), but both show improvement over a baseline demographic-driven estimation (p < 0.001). CONCLUSIONS: For circumstances in which patients present for healthcare services without readily accessible identification such as in the setting trauma or altered mental status, CNN regression models for age prediction have potential clinical utility for refining estimates related to this missing patient information.

Text Report Analysis to Identify Opportunities for Optimizing Target Selection for Chest Radiograph Artificial Intelligence Models.

Our goal was to analyze radiology report text for chest radiographs (CXRs) to identify imaging findings that have the most impact on report length and complexity. Identifying these imaging findings can highlight opportunities for designing CXR AI systems which increase radiologist efficiency. We retrospectively analyzed text from 210,025 MIMIC-CXR reports and 168,949 reports from our local institution collected from 2019 to 2022. Fifty-nine categories of imaging finding keywords were extracted from reports using natural language processing (NLP), and their impact on report length was assessed using linear regression with and without LASSO regularization. Regression was also used to assess the impact of additional factors contributing to report length, such as the signing radiologist and use of terms of perception. For modeling CXR report word counts with regression, mean coefficient of determination, R2, was 0.469 ± 0.001 for local reports and 0.354 ± 0.002 for MIMIC-CXR when considering only imaging finding keyword features. Mean R2 was significantly less at 0.067 ± 0.001 for local reports and 0.086 ± 0.002 for MIMIC-CXR, when only considering use of terms of perception. For a combined model for the local report data accounting for the signing radiologist, imaging finding keywords, and terms of perception, the mean R2 was 0.570 ± 0.002. With LASSO, highest value coefficients pertained to endotracheal tubes and pleural drains for local data and masses, nodules, and cavitary and cystic lesions for MIMIC-CXR. Natural language processing and regression analysis of radiology report textual data can highlight imaging targets for AI models which offer opportunities to bolster radiologist efficiency.

Medical Malpractice and Diagnostic Radiology: Challenges and Opportunities.

Medicolegal challenges in radiology are broad and impact both radiologists and patients. Radiologists may be affected directly by malpractice litigation or indirectly due to defensive imaging ordering practices. Patients also could be harmed physically, emotionally, or financially by unnecessary tests or procedures. As technology advances, the incorporation of artificial intelligence into medicine will bring with it new medicolegal challenges and opportunities. This article reviews the current and emerging direct and indirect effects of medical malpractice on radiologists and summarizes evidence-based solutions.

A Problem of Gender Representation: Adapting the Bechdel Test to Evaluate the Social Media Presence of Radiology Residency Programs.

RATIONALE AND OBJECTIVES: Social media serves as recruitment tools for residency programs, allowing programs to "brand" themselves in an era of virtual interviews. For female applicants, viewing their gender represented on Instagram may influence their pursuit of a program. Our study's goal is to quantify how female-presenting professionals are represented on radiology residency (RR) Instagram pages, as these are increasingly important platforms for resident recruitment. MATERIALS AND METHODS: The Bechdel test is a well-known measure of the representation of women in fiction that requires at least 2 women speak to each other about a topic other than a man. We modified this test to evaluate the portrayal of female-presenting professionals on public Instagram galleries of RR programs. For a photo to pass our test, female-presenting persons are shown physically together, without male-presenting professionals, and in a professional setting. To compare gender depiction, a Male Bechdel Test was also used. RR Instagram pages were identified using the Fellowship and Residency Electronic Interactive Database Access (n = 87) and examined with an adapted framework approach to count female and male-presenting individuals in 1044 images. Results were assessed using paired t-tests and a chi-square with McNemar's test. RESULTS: Approximately 50% of the RR Instagrams passed the Male Bechdel Test while only 21.3% passed the Female Bechdel Test, a significant difference in gender representation (χ2(1) = 13.255, P = 0.022). Paired sample t-tests revealed that RR Instagram pages are significantly more likely to feature male-presenting professionals in a professional setting (P < 0.0001), feature them with other male-presenting professionals (P = 0.001), and feature them without female-presenting professionals (P = 0.003). CONCLUSION: Our results suggest female-presenting radiologists are under-represented on the Instagram profiles of RR programs. While this reflects the dearth of females in this field, programs may improve gender inclusion by more prominently displaying females on social media. This may assist in recruiting minority applicants.

Continuing to Thrive in Academic Radiology Despite Decreasing Reimbursement.

Decreasing radiology reimbursement is a major challenge faced by academic radiology practices in the United States. The consequent increased workload from reading more radiological studies can lead to job dissatisfaction, burnout and adverse impact on research, innovation, and education. Thriving successfully in an academic practice despite low reimbursement requires modification of radiology business models and culture of the practice. In this article, we review the financial and operational strategies to mitigate low reimbursement and strategies for thriving in academic radiology without burnout.

Perspectives on lung visualization: Three-dimensional anatomical modeling of computed and micro-computed tomographic data in comparative evolutionary morphology and medicine with applications for COVID-19.

The vertebrate respiratory system is challenging to study. The complex relationship between the lungs and adjacent tissues, the vast structural diversity of the respiratory system both within individuals and between taxa, its mobility (or immobility) and distensibility, and the difficulty of quantifying and visualizing functionally important internal negative spaces have all impeded descriptive, functional, and comparative research. As a result, there is a relative paucity of three-dimensional anatomical information on this organ system in all vertebrate groups (including humans) relative to other regions of the body. We present some of the challenges associated with evaluating and visualizing the vertebrate respiratory system using computed and micro-computed tomography and its subsequent digital segmentation. We discuss common mistakes to avoid when imaging deceased and live specimens and various methods for merging manual and threshold-based segmentation approaches to visualize pulmonary tissues across a broad range of vertebrate taxa, with a particular focus on sauropsids (reptiles and birds). We also address some of the recent work in comparative evolutionary morphology and medicine that have used these techniques to visualize respiratory tissues. Finally, we provide a clinical study on COVID-19 in humans in which we apply modeling methods to visualize and quantify pulmonary infection in the lungs of human patients.

Practical Tips and a Template for Developing Your Curriculum Vitae.

The Alliance of Leaders in Academic Affairs in Radiology (ALAAR) advocates for a Universal Curriculum Vitae for all medical institutions and to that end, we have developed a template that can be downloaded on the AUR website (ALAAR CV template) that includes all of the elements required by many academic institutions. Members of ALAAR represent multiple academic institutions and have spent many hours reviewing and providing input on radiologists' curricula vitae. The purpose of this review is to help academic radiologists accurately maintain and optimize their CVs with minimal effort and to clarify common questions that arise at many different institutions in the process of constructing a CV.

High-grade bladder cancer: association of the apparent diffusion coefficient with metastatic disease: preliminary results.

PURPOSE: To assess the utility of apparent diffusion coefficient (ADC) values obtained from diffusion-weighted imaging (DWI) in distinguishing high-grade bladder cancer with and without metastatic disease. MATERIALS AND METHODS: Seventeen patients with histologically confirmed high-grade bladder cancer who underwent pelvic magnetic resonance imaging (MRI) at 1.5T including DWI using b-values of 0, 400, and 800 sec/mm(2) were assessed. Histologic findings and follow-up imaging were used to establish the reference standard in terms of metastatic disease. Two radiologists independently recorded ADC of all lesions following a training session, with their results averaged. Mann-Whitney U-test, receiver operating characteristic (ROC) curve analysis and intraclass correlation coefficient (ICC) were used for data analysis. RESULTS: Metastatic disease was characterized as present or absent in eight and nine patients, respectively. ADC was significantly lower among cases with metastatic disease than among cases without metastatic disease, both within the entire cohort (1.07 ± 0.18 × 10(-3) mm(2)/s vs. 1.45 ± 0.22 × 10(-3) mm(2)/s; P = 0.002) and within the subset of patients with muscle-invasive tumor (1.06 ± 0.19 × 10(-3) mm(2)/s vs. 1.45 ± 0.23 × 10(-3) mm(2)/s; P = 0.017). Area under the ROC curve for identifying metastatic disease using ADC was 0.944, with optimal threshold of 1.21 × 10(-3) mm(2)/s, which was associated with a sensitivity of 87.5%, specificity of 100%, positive predictive value of 100%, and negative predictive value of 90.0%. Interreader agreement for ADC was excellent (ICC = 0.91). CONCLUSION: In this preliminary study, ADC was significantly different between cases of high-grade urothelial carcinoma of the bladder with and without metastatic disease. These results may have value in assessing the metastatic potential of patients with localized high-grade tumors of the bladder.

Utility of MRI features for differentiation of retroperitoneal fibrosis and lymphoma.

OBJECTIVE: The objective of our study was to retrospectively compare the MRI features of retroperitoneal fibrosis (RPF) and lymphoma presenting as confluent retroperitoneal soft tissue. MATERIALS AND METHODS: MRI studies of 31 patients (18 men, 13 women; mean age, 58.4 ± 15.8 [SD] years; 22 with RPF and nine with lymphoma) were evaluated. Two radiologists independently and in consensus evaluated all cases for an array of subjective imaging features. A third radiologist measured the size (i.e., the greatest dimension in the transverse plane) and apparent diffusion coefficient (ADC) value of the tissue. Features of RPF and lymphoma were compared using the Fisher exact test, Mann-Whitney test, and receiver operating characteristic (ROC) curve analysis. Interreader concordance was also calculated. RESULTS: The mean age of patients with lymphoma was significantly greater than that in cases of RPF (72.4 ± 13.3 [SD] vs 52.7 ± 13.2 years, respectively; p = 0.003). The MRI features significantly more common in patients with RPF were pelvic extension (p = 0.004) and medial ureteral bowing (p < 0.001). The MRI features significantly more common in cases of lymphoma were predominantly suprarenal location, perirenal extension, anterior aortic displacement, heterogeneity, and the presence of additional nodes (p < 0.001-0.043). Size was significantly greater in patients with lymphoma than in those with RPF (mean ± SD, 33.9 ± 17.3 vs 11.0 ± 5.7 mm; p < 0.001) and had an area under the curve (AUC) of 0.960; a size larger than 15 mm had sensitivity of 100% and specificity of 86.4% for the diagnosis of lymphoma. The ADC was significantly lower in lymphoma than in RPF (mean ± SD, 0.92 ± 0.17 vs 1.40 ± 0.38 × 10(-3) mm(2)/s; p = 0.003) and had an AUC of 0.904. An ADC of 0.955 × 10(-3) mm(2)/s or less had sensitivity of 83.3% and specificity of 89.5% for the diagnosis of lymphoma. Interreader concordance for subjective features was very good to excellent (range, 80.6-100%). CONCLUSION: MRI features may be helpful in distinguishing between RPF and lymphoma.

Prostate cancer: multiparametric MRI for index lesion localization--a multiple-reader study.

OBJECTIVE: The purpose of this study was to evaluate the utility of multiparametric MRI in localization of the index lesion of prostate cancer. MATERIALS AND METHODS: Fifty-one patients who underwent 3-T MRI of the prostate with a pelvic phased-array coil that included T2-weighted, diffusion-weighted, and dynamic contrast-enhanced sequences before prostatectomy were included. Six radiologists assessed all images to identify the lesion most suspicious of being the index lesion, which was localized to one of 18 regions. A uropathologist using the same 18-region scheme reviewed the prostatectomy slides to localize the index lesion. MRI performance was assessed by requiring either an exact match or an approximate match (discrepancy of up to one region) between the MRI and pathologic findings in terms of assigned region. RESULTS: The pathologist identified an index lesion in 49 of 51 patients. In exact-match analysis, the average sensitivity was 60.2% (range, 51.0-63.3%), and the average positive predictive value (PPV) was 65.3% (range, 61.2-69.4%). In approximate-match analysis, the average sensitivity was 75.9% (range, 65.3-69.6%), and the average PPV was 82.6% (range, 79.2-91.4%). The sensitivity was higher for index lesions with a Gleason score greater than 6 in exact-match (74.8% vs 15.3%, p<0.001) and approximate-match (88.7% vs 36.1%, p=<0.001) analyses and for index lesions measuring at least 1 cm in approximate-match analysis (80.3% vs 58.3%, p=0.016). In exact-match analysis, 30.0%, 44.9%, and 79.1% of abnormalities found with one, two, and three MRI parameters represented the index lesion (p<0.001). CONCLUSION: The sensitivity and PPV of multiparametric MRI for index lesion localization were moderate, although they improved in the setting of more aggressive pathologic features and a greater number of abnormal MRI parameters, respectively.

Burnout: A Mindful Framework for the Radiologist.

Burnout, the outcome of prolonged stress or frustration, manifests as both mental and physical fatigue affecting over half of healthcare workers. This article will discuss the etiologies, problems, and potential solutions to burnout related issues that are impacting radiologists. Factors placing radiologists at risk for burnout as well the impact of burnout upon the radiologist, the department, staff, and patients they serve will also be discussed. An emphasis will also be placed upon recognition, solutions, and a collective response to burnout. Readers should be able to perform a self-assessment of their own risk for burnout and understand what can be done to dissolve and prevent burnout amongst their colleagues. In doing so, our hope is that radiologists will develop greater insight, awareness, and ultimately empathy for the unique challenges that others in the radiology community may face.

A Framework for the Virtual Medical Interview Process: Considerations for the Applicant and the Interviewer.

Background: Videoconferencing platforms are being used for the purposes of interviewing in academic medicine because of the coronavirus disease 2019 pandemic. We present considerations applicable to interviewers and interviewees in the virtual space, with a focus on medical school and residency applicants. Methods: We reviewed the literature regarding the virtual interview process for medical school and residency by searching PubMed using the following keywords and terms: "interview," "academic medicine," "medical school application," "residency application," "virtual interviews," and "videoconferencing." Our search identified 701 results, from which we selected 36 articles for review. Results: The garnered information focuses on strategies for optimizing the virtual interview process from the standpoint of both the interviewer and the interviewee. We discuss the advantages and disadvantages of the virtual interview process and present recommendations. Conclusion: While the future of the interview process for medical school and residency is uncertain, virtual interviewing is a common and growing practice that will continue to be at least part of the medical interview process for years to come. Interviewers and interviewees should prepare to adapt to the evolving changes in the process.

Coronavirus Disease (COVID-19): The Value of Chest Radiography for Patients Greater Than Age 50 Years at an Earlier Timepoint of Symptoms Compared With Younger Patients.

Background: A relative paucity of data exists regarding chest radiography (CXR) in diagnosis of coronavirus disease (COVID-19) compared to computed tomography. We address the use of a strict pattern of CXR findings for COVID-19 diagnosis, specifically during early onset of symptoms with respect to patient age. Methods: We performed a retrospective study of patients under investigation for COVID-19 who presented to the emergency department during the COVID-19 outbreak of 2020 and had CXR within 1 week of symptoms. Only reverse transcription polymerase chain reaction (RT-PCR)-positive patients were included. Two board-certified radiologists, blinded to RT-PCR results, assessed 60 CXRs in consensus and assigned 1 of 3 patterns: characteristic, atypical, or negative. Atypical patterns were subdivided into more suspicious or less suspicious for COVID-19. Results: Sixty patients were included: 30 patients aged 52 to 88 years and 30 patients aged 19 to 48 years. Ninety-three percent of the older group demonstrated an abnormal CXR and were more likely to have characteristic and atypical-more suspicious findings in the first week after symptom onset than the younger group. The relationship between age and CXR findings was statistically significant (χ2 [2, n=60]=15.70; P=0.00039). The relationship between negative and characteristic COVID-19 CXR findings between the 2 age cohorts was statistically significant with Fisher exact test resulting in a P value of 0.001. Conclusion: COVID-19 positive patients >50 years show earlier, characteristic patterns of statistically significant CXR changes than younger patients, suggesting that CXR is useful in the early diagnosis of infection. CXR can be useful in early diagnosis of COVID-19 in patients older than 50 years.

Artificial Intelligence in Imaging of Chronic Liver Diseases: Current Update and Future Perspectives.

Here we review artificial intelligence (AI) models which aim to assess various aspects of chronic liver disease. Despite the clinical importance of hepatocellular carcinoma in the setting of chronic liver disease, we focus this review on AI models which are not lesion-specific and instead review models developed for liver parenchyma segmentation, evaluation of portal circulation, assessment of hepatic fibrosis, and identification of hepatic steatosis. Optimization of these models offers the opportunity to potentially reduce the need for invasive procedures such as catheterization to measure hepatic venous pressure gradient or biopsy to assess fibrosis and steatosis. We compare the performance of these AI models amongst themselves as well as to radiomics approaches and alternate modality assessments. We conclude that these models show promising performance and merit larger-scale evaluation. We review artificial intelligence models that aim to assess various aspects of chronic liver disease aside from hepatocellular carcinoma. We focus this review on models for liver parenchyma segmentation, evaluation of portal circulation, assessment of hepatic fibrosis, and identification of hepatic steatosis. We conclude that these models show promising performance and merit a larger scale evaluation.