Environmental Sustainability and MRI: Challenges, Opportunities, and a Call for Action.

The environmental impact of magnetic resonance imaging (MRI) has recently come into focus. This includes its enormous demand for electricity compared to other imaging modalities and contamination of water bodies with anthropogenic gadolinium related to contrast administration. Given the pressing threat of climate change, addressing these challenges to improve the environmental sustainability of MRI is imperative. The purpose of this review is to discuss the challenges, opportunities, and the need for action to reduce the environmental impact of MRI and prepare for the effects of climate change. The approaches outlined are categorized as strategies to reduce greenhouse gas (GHG) emissions from MRI during production and use phases, approaches to reduce the environmental impact of MRI including the preservation of finite resources, and development of adaption plans to prepare for the impact of climate change. Co-benefits of these strategies are emphasized including lower GHG emission and reduced cost along with improved heath and patient satisfaction. Although MRI is energy-intensive, there are many steps that can be taken now to improve the environmental sustainability of MRI and prepare for the effects of climate change. On-going research, technical development, and collaboration with industry partners are needed to achieve further reductions in MRI-related GHG emissions and to decrease the reliance on finite resources. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.

Can incorrect artificial intelligence (AI) results impact radiologists, and if so, what can we do about it? A multi-reader pilot study of lung cancer detection with chest radiography.

OBJECTIVE: To examine whether incorrect AI results impact radiologist performance, and if so, whether human factors can be optimized to reduce error. METHODS: Multi-reader design, 6 radiologists interpreted 90 identical chest radiographs (follow-up CT needed: yes/no) on four occasions (09/20-01/22). No AI result was provided for session 1. Sham AI results were provided for sessions 2-4, and AI for 12 cases were manipulated to be incorrect (8 false positives (FP), 4 false negatives (FN)) (0.87 ROC-AUC). In the Delete AI (No Box) condition, radiologists were told AI results would not be saved for the evaluation. In Keep AI (No Box) and Keep AI (Box), radiologists were told results would be saved. In Keep AI (Box), the ostensible AI program visually outlined the region of suspicion. AI results were constant between conditions. RESULTS: Relative to the No AI condition (FN = 2.7%, FP = 51.4%), FN and FPs were higher in the Keep AI (No Box) (FN = 33.0%, FP = 86.0%), Delete AI (No Box) (FN = 26.7%, FP = 80.5%), and Keep AI (Box) (FN = to 20.7%, FP = 80.5%) conditions (all ps < 0.05). FNs were higher in the Keep AI (No Box) condition (33.0%) than in the Keep AI (Box) condition (20.7%) (p = 0.04). FPs were higher in the Keep AI (No Box) (86.0%) condition than in the Delete AI (No Box) condition (80.5%) (p = 0.03). CONCLUSION: Incorrect AI causes radiologists to make incorrect follow-up decisions when they were correct without AI. This effect is mitigated when radiologists believe AI will be deleted from the patient's file or a box is provided around the region of interest. CLINICAL RELEVANCE STATEMENT: When AI is wrong, radiologists make more errors than they would have without AI. Based on human factors psychology, our manuscript provides evidence for two AI implementation strategies that reduce the deleterious effects of incorrect AI. KEY POINTS: • When AI provided incorrect results, false negative and false positive rates among the radiologists increased. • False positives decreased when AI results were deleted, versus kept, in the patient's record. • False negatives and false positives decreased when AI visually outlined the region of suspicion.

Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data.

OBJECTIVES: Early recognition of coronavirus disease 2019 (COVID-19) severity can guide patient management. However, it is challenging to predict when COVID-19 patients will progress to critical illness. This study aimed to develop an artificial intelligence system to predict future deterioration to critical illness in COVID-19 patients. METHODS: An artificial intelligence (AI) system in a time-to-event analysis framework was developed to integrate chest CT and clinical data for risk prediction of future deterioration to critical illness in patients with COVID-19. RESULTS: A multi-institutional international cohort of 1,051 patients with RT-PCR confirmed COVID-19 and chest CT was included in this study. Of them, 282 patients developed critical illness, which was defined as requiring ICU admission and/or mechanical ventilation and/or reaching death during their hospital stay. The AI system achieved a C-index of 0.80 for predicting individual COVID-19 patients' to critical illness. The AI system successfully stratified the patients into high-risk and low-risk groups with distinct progression risks (p < 0.0001). CONCLUSIONS: Using CT imaging and clinical data, the AI system successfully predicted time to critical illness for individual patients and identified patients with high risk. AI has the potential to accurately triage patients and facilitate personalized treatment. KEY POINT: • AI system can predict time to critical illness for patients with COVID-19 by using CT imaging and clinical data.

Prognostic significance of T1 mapping parameters in heart failure with preserved ejection fraction: a systematic review.

Heart failure with preserved ejection fraction (HFpEF) accounts for almost one-half of all heart failure (HF) patients and continues to increase in prevalence. While mortality with heart failure with reduced ejection fraction (HFrEF) has decreased over the past few decades with use of evidence-based HFrEF therapy, mortality related to heart failure with HFpEF has not changed significantly over the same time period. The combination of poor prognosis and lack of effective treatment options creates a pressing need for novel strategies for better patient characterization. We conducted a systematic review to evaluate the prognostic value of cardiac magnetic resonance (CMR)-derived T1 relaxation time and extracellular volume fraction (ECV) in HFpEF patients. PubMed, Embase, and Cochrane Central were searched for relevant studies. The primary outcomes of interest were hospitalization for HF and all-cause mortality. Five studies with 2741 patients were included. Four studies reported correlation of outcomes with ECV, 2 studies reported correlation of outcomes with native T1 time, and 1 study reported correlation of outcomes with post-contrast T1 time. All five studies showed significant correlation of CMR-derived parameters with adverse outcomes including event-free survival to cardiac event, all cause, and cardiac mortality. CMR-determined ECV is strongly correlated with adverse outcomes in HFpEF cohorts.

Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT.

Background Coronavirus disease 2019 (COVID-19) and pneumonia of other diseases share similar CT characteristics, which contributes to the challenges in differentiating them with high accuracy. Purpose To establish and evaluate an artificial intelligence (AI) system for differentiating COVID-19 and other pneumonia at chest CT and assessing radiologist performance without and with AI assistance. Materials and Methods A total of 521 patients with positive reverse transcription polymerase chain reaction results for COVID-19 and abnormal chest CT findings were retrospectively identified from 10 hospitals from January 2020 to April 2020. A total of 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia at chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by a two-layer fully connected neural network to pool slices together. The final cohort of 1186 patients (132 583 CT slices) was divided into training, validation, and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance in separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance. Results The final model achieved a test accuracy of 96% (95% confidence interval [CI]: 90%, 98%), a sensitivity of 95% (95% CI: 83%, 100%), and a specificity of 96% (95% CI: 88%, 99%) with area under the receiver operating characteristic curve of 0.95 and area under the precision-recall curve of 0.90. On independent testing, this model achieved an accuracy of 87% (95% CI: 82%, 90%), a sensitivity of 89% (95% CI: 81%, 94%), and a specificity of 86% (95% CI: 80%, 90%) with area under the receiver operating characteristic curve of 0.90 and area under the precision-recall curve of 0.87. Assisted by the probabilities of the model, the radiologists achieved a higher average test accuracy (90% vs 85%, Δ = 5, P < .001), sensitivity (88% vs 79%, Δ = 9, P < .001), and specificity (91% vs 88%, Δ = 3, P = .001). Conclusion Artificial intelligence assistance improved radiologists' performance in distinguishing coronavirus disease 2019 pneumonia from non-coronavirus disease 2019 pneumonia at chest CT. © RSNA, 2020 Online supplemental material is available for this article.

Performance of Radiologists in Differentiating COVID-19 from Non-COVID-19 Viral Pneumonia at Chest CT.

Background Despite its high sensitivity in diagnosing coronavirus disease 2019 (COVID-19) in a screening population, the chest CT appearance of COVID-19 pneumonia is thought to be nonspecific. Purpose To assess the performance of radiologists in the United States and China in differentiating COVID-19 from viral pneumonia at chest CT. Materials and Methods In this study, 219 patients with positive COVID-19, as determined with reverse-transcription polymerase chain reaction (RT-PCR) and abnormal chest CT findings, were retrospectively identified from seven Chinese hospitals in Hunan Province, China, from January 6 to February 20, 2020. Two hundred five patients with positive respiratory pathogen panel results for viral pneumonia and CT findings consistent with or highly suspicious for pneumonia, according to original radiologic interpretation within 7 days of each other, were identified from Rhode Island Hospital in Providence, RI. Three radiologists from China reviewed all chest CT scans (n = 424) blinded to RT-PCR findings to differentiate COVID-19 from viral pneumonia. A sample of 58 age-matched patients was randomly selected and evaluated by four radiologists from the United States in a similar fashion. Different CT features were recorded and compared between the two groups. Results For all chest CT scans (n = 424), the accuracy of the three radiologists from China in differentiating COVID-19 from non-COVID-19 viral pneumonia was 83% (350 of 424), 80% (338 of 424), and 60% (255 of 424). In the randomly selected sample (n = 58), the sensitivities of three radiologists from China and four radiologists from the United States were 80%, 67%, 97%, 93%, 83%, 73%, and 70%, respectively. The corresponding specificities of the same readers were 100%, 93%, 7%, 100%, 93%, 93%, and 100%, respectively. Compared with non-COVID-19 pneumonia, COVID-19 pneumonia was more likely to have a peripheral distribution (80% vs 57%, P < .001), ground-glass opacity (91% vs 68%, P < .001), fine reticular opacity (56% vs 22%, P < .001), and vascular thickening (59% vs 22%, P < .001), but it was less likely to have a central and peripheral distribution (14% vs 35%, P < .001), pleural effusion (4% vs 39%, P < .001), or lymphadenopathy (3% vs 10%, P = .002). Conclusion Radiologists in China and in the United States distinguished coronavirus disease 2019 from viral pneumonia at chest CT with moderate to high accuracy. © RSNA, 2020 Online supplemental material is available for this article. A translation of this abstract in Farsi is available in the supplement. ترجمه چکیده این مقاله به فارسی، در ضمیمه موجود است.

Detection of emergent large vessel occlusion stroke with CT angiography is high across all levels of radiology training and grayscale viewing methods.

OBJECTIVES: CT angiography (CTA) is essential in acute stroke to detect emergent large vessel occlusions (ELVO) and must be interpreted by radiologists with and without subspecialized training. Additionally, grayscale inversion has been suggested to improve diagnostic accuracy in other radiology applications. This study examines diagnostic performance in ELVO detection between neuroradiologists, non-neuroradiologists, and radiology residents using standard and grayscale inversion viewing methods. METHODS: A random, counterbalanced experimental design was used, where 18 radiologists with varying experiences interpreted the same patient images with and without grayscale inversion. Confirmed positive and negative ELVO cases were randomly ordered using a balanced design. Sensitivity, specificity, positive and negative predictive values as well as confidence, subjective assessment of image quality, time to ELVO detection, and overall interpretation time were examined between grayscale inversion (on/off) by experience level using generalized mixed modeling assuming a binary, negative binomial, and binomial distributions, respectively. RESULTS: All groups of radiologists had high sensitivity and specificity for ELVO detection (all > .94). Neuroradiologists were faster than non-neuroradiologists and residents in interpretation time, with a mean of 47 s to detect ELVO, as compared with 59 and 74 s, respectively. Residents were subjectively less confident than attending physicians. With respect to grayscale inversion, no differences were observed between groups with grayscale inversion vs. standard viewing for diagnostic performance (p = 0.30), detection time (p = .45), overall interpretation time (p = .97), and confidence (p = .20). CONCLUSIONS: Diagnostic performance in ELVO detection with CTA was high across all levels of radiologist training level. Grayscale inversion offered no significant detection advantage. KEY POINTS: • Stroke is an acute vascular syndrome that requires acute vascular imaging. • Proximal large vessel occlusions can be identified quickly and accurately by radiologists across all training levels. • Grayscale inversion demonstrated minimal detectable benefit in the detection of proximal large vessel occlusions.

Quantitative Assessment of Right Ventricular Volumes and Ejection Fraction in Patients with Left Ventricular Systolic Dysfunction by Real Time Three-Dimensional Echocardiography versus Cardiac Magnetic Resonance Imaging.

AIMS: The aim of this study was to assess the accuracy and reproducibility of real time three-dimensional echocardiographic (RT3DE) for the determination of right ventricular (RV) volumes and function in patients with left ventricular (LV) systolic dysfunction. METHODS AND RESULTS: Dedicated RT3DE was prospectively performed to assess RV volumes and EF in patients with LV systolic function identified on routine clinical cardiac magnetic resonance (CMR) imaging. RV end-diastolic volume (RV EDV), RV end-systolic volume (RV ESV), and RV EF were obtained using an offline analysis software (TomTec) by two observers blinded to CMR results. In this population of 27 patients with LV systolic dysfunction with a mean LV EF of 36 ± 12%, RV RT3DE dataset could be assessed in 27 of 30 patients (90%). High correlation was noted between RT3DE and CMR for RV EDV, ESV, and EF (r = 0.90, 0.89, and 0.77, respectively). RV EDV was lower by RT3DE as compared to CMR (129 ± 52 vs. 142 ± 53 mL, P = 0.005) while there was no significant difference in RV ESV and RV EF (71 ± 37 vs. 77 ± 45 mL, P = 0.146; 45 ± 11 vs. 48 ± 13%, P = 0.134, respectively). The intraclass correlation coefficient ranged from 0.94 to 0.94 between measurements and from 0.84 to 0.96 between observers. CONCLUSION: Overall, RV volumes and EF assessed by RT3DE correlate well with CMR measurements in patients with LV dysfunction. RT3DE may be used as a more widely available and versatile alternative to CMR for the quantitative assessment of RV size and function in patients with LV dysfunction.

Management of nodules with initially nondiagnostic results of thyroid fine-needle aspiration: can we avoid repeat biopsy?

PURPOSE: To identify demographic and ultrasonographic (US) features associated with malignancy after initially nondiagnostic results of fine-needle aspiration (FNA) to help clarify the role of repeat FNA, surgical excision, or serial US in these nodules. MATERIALS AND METHODS: This study was HIPAA compliant and institutional review board approved; informed consent was waived. Thyroid nodules (n = 5349) that underwent US-guided FNA in 2004-2012 were identified; 393 were single nodules with nondiagnostic FNA results but adequate cytologic, surgical, or US follow-up. Demographic information and diameters and volume at US at first biopsy were modeled with malignancy as outcome through medical record review. Exact logistic regression was used to model malignancy outcomes, demographic comparisons with age were made (Student t test, Satterthwaite test), and proportion confidence intervals (CIs) were estimated (Clopper-Pearson method). RESULTS: Of 393 nodules with initially nondiagnostic results, nine malignancies (2.3%) were subsequently diagnosed with repeat FNA (n = 2, 0.5%) or surgical pathologic examination (n = 7, 1.8%), 330 (84.0%) were benign, and 54 (13.7%) were stable or decreased in size at serial US (mean follow-up, 3.0 years; median, 2.5 years; range, 1.0-7.8 years). Patients with malignancies were significantly older (mean age, 62.7 years; median, 64 years; range, 47-77 years) than those without (mean age, 55.4 years; median, 57 years; range, 12-94 years; P = .0392). Odds of malignancy were 4.2 times higher for men versus women (P = .045) and increased significantly for each 1-cm increase in anteroposterior, minimum, and mean nodule diameter (1.78, 2.10, and 1.96, respectively). In 393 nodules, no malignancies were detected in cystic or spongiform nodules (both, n = 11, 2.8%; 95% CI: 1.4%, 5.0%), nodules with eggshell calcifications (n = 9, 2.3%; 95% CI: 1.1%, 4.3%), or indeterminate echogenic foci (n = 39, 9.9%; 95% CI: 7.2%, 13.3%). CONCLUSION: Very few malignancies were diagnosed with repeat FNA following nondiagnostic FNA results (two of 336, 0.6%); therefore, clinical and US follow-up may be more appropriate than repeat FNA following nondiagnostic biopsy results.

Left Anterior Descending Coronary Artery Mimic: A Case of Coronary Artery to Pulmonary Artery Fistula.

Coronary artery fistulas (CAFs) are rare coronary anomalies involving the communication of an epicardial coronary artery and another cardiovascular structure. CAFs are usually easily distinguished from nearby coronary arteries. Here, we report a unique case of CAF that mimics the size, branching pattern, and appearance of a native epicardial left anterior descending artery.

De-Biased Disentanglement Learning for Pulmonary Embolism Survival Prediction on Multimodal Data.

Health disparities among marginalized populations with lower socioeconomic status significantly impact the fairness and effectiveness of healthcare delivery. The increasing integration of artificial intelligence (AI) into healthcare presents an opportunity to address these inequalities, provided that AI models are free from bias. This paper aims to address the bias challenges by population disparities within healthcare systems, existing in the presentation of and development of algorithms, leading to inequitable medical implementation for conditions such as pulmonary embolism (PE) prognosis. In this study, we explore the diverse bias in healthcare systems, which highlights the demand for a holistic framework to reducing bias by complementary aggregation. By leveraging de-biasing deep survival prediction models, we propose a framework that disentangles identifiable information from images, text reports, and clinical variables to mitigate potential biases within multimodal datasets. Our study offers several advantages over traditional clinical-based survival prediction methods, including richer survival-related characteristics and bias-complementary predicted results. By improving the robustness of survival analysis through this framework, we aim to benefit patients, clinicians, and researchers by enhancing fairness and accuracy in healthcare AI systems.

The Impact of Emerging Technologies on Residency Selection by Medical Students in 2017 and 2021, With a Focus on Diagnostic Radiology.

RATIONALE AND OBJECTIVES: We sought to determine the perceived impact of artificial intelligence (AI) and other emerging technologies (ET) on various specialties by medical students in both 2017 and 2021 and how this might affect their residency selections. MATERIALS AND METHODS: We conducted a brief, anonymous survey of all medical students at a single institution in 2017 and 2021. Survey questions evaluated (1) incentives motivating residency selection and career path, (2) degree of interest in each specialty, (3) perceived effect that ET will have on job prospects for each specialty, and (4) those specialties that students would not consider because of concerns regarding ET. RESULTS: A total of 72% (384/532) and 54% (321/598) of medical students participated in the survey in 2017 and 2021, respectively, and results were largely stable. Students perceived ET would reduce job prospects for pathology, diagnostic radiology, and anesthesiology, and enhance prospects for all other specialties (p < 0.01) except dermatology. For both surveys, 23% of students would NOT consider diagnostic radiology because ET would make it obsolete, higher than all other specialties (p < 0.01). Regarding the one student class that was surveyed twice, 50% felt ET would reduce job prospects for radiology in 2017, increasing to 71% in 2021 (p < 0.01), and similar percentages-20% in 2017 and 23% in 2021-said they explicitly would not consider radiology because of concerns levied by ET. CONCLUSIONS: Current perceptions of ET likely affect residency selection for a large proportion of medical students and may impact the future of various specialties, particularly diagnostic radiology.

Cardiac MRI Findings in Male Patients with Acute Myocarditis in the Presence or Absence of COVID-19 Vaccination.

By comparing phenotypic clinical characteristics and cardiovascular magnetic resonance (CMR) findings in 14 patients with COVID-19 mRNA vaccine-associated myocarditis to 14 patients with acute myocarditis from other causes, we found that patients with COVID-19 vaccination- associated acute myocarditis have higher left ventricular ejection fraction, higher left ventricular global circumferential and radial strain, and less involvement of late gadolinium enhancement in the septal segments with less involvement of midmyocardial pattern of late gadolinium enhancement, compared to patients with acute myocarditis from other causes.

An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data.

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital's image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.