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.

Active Learning in Brain Tumor Segmentation with Uncertainty Sampling and Annotation Redundancy Restriction.

Deep learning models have demonstrated great potential in medical imaging but are limited by the expensive, large volume of annotations required. To address this, we compared different active learning strategies by training models on subsets of the most informative images using real-world clinical datasets for brain tumor segmentation and proposing a framework that minimizes the data needed while maintaining performance. Then, 638 multi-institutional brain tumor magnetic resonance imaging scans were used to train three-dimensional U-net models and compare active learning strategies. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotating similar images were also considered. We determined the minimum data necessary to achieve performance equivalent to the model trained on the full dataset (α = 0.05). Bayesian approximation with dropout at training and testing showed results equivalent to that of the full data model (target) with around 30% of the training data needed by random query to achieve target performance (p = 0.018). Annotation redundancy restriction techniques can reduce the training data needed by random query to achieve target performance by 20%. We investigated various active learning strategies to minimize the annotation burden for three-dimensional brain tumor segmentation. Dropout uncertainty estimation achieved target performance with the least annotated data.

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.

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.

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.

COVID-19 mortality prediction in the intensive care unit with deep learning based on longitudinal chest X-rays and clinical data.

OBJECTIVES: We aimed to develop deep learning models using longitudinal chest X-rays (CXRs) and clinical data to predict in-hospital mortality of COVID-19 patients in the intensive care unit (ICU). METHODS: Six hundred fifty-four patients (212 deceased, 442 alive, 5645 total CXRs) were identified across two institutions. Imaging and clinical data from one institution were used to train five longitudinal transformer-based networks applying five-fold cross-validation. The models were tested on data from the other institution, and pairwise comparisons were used to determine the best-performing models. RESULTS: A higher proportion of deceased patients had elevated white blood cell count, decreased absolute lymphocyte count, elevated creatine concentration, and incidence of cardiovascular and chronic kidney disease. A model based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, and a model based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657. A model based on all longitudinal CXRs (both pre-ICU and ICU) achieved an AUC of 0.702 and an accuracy of 0.694. A model based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data in a combined model significantly improved performance, reaching an AUC of 0.727 (p = 0.039) and an accuracy of 0.732. CONCLUSIONS: The addition of longitudinal CXRs to clinical data significantly improves mortality prediction with deep learning for COVID-19 patients in the ICU. KEY POINTS: • Deep learning was used to predict mortality in COVID-19 ICU patients. • Serial radiographs and clinical data were used. • The models could inform clinical decision-making and resource allocation.

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.

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.

Cardiovascular magnetic resonance findings in young adult patients with acute myocarditis following mRNA COVID-19 vaccination: a case series.

BACKGROUND: Messenger RNA (mRNA) coronavirus disease of 2019 (COVID-19) vaccine are known to cause minor side effects at the injection site and mild global systemic symptoms in first 24-48 h. Recently published case series have reported a possible association between acute myocarditis and COVID-19 vaccination, predominantly in young males. METHODS: We report a case series of 5 young male patients with cardiovascular magnetic resonance (CMR)-confirmed acute myocarditis within 72 h after receiving a dose of an mRNA-based COVID-19 vaccine. RESULTS: Our case series suggests that myocarditis in this setting is characterized by myocardial edema and late gadolinium enhancement in the lateral wall of the left ventricular (LV) myocardium, reduced global LV longitudinal strain, and preserved LV ejection fraction. All patients in our series remained clinically stable during a relatively short inpatient hospital stay. CONCLUSIONS: In conjunction with other recently published case series and national vaccine safety surveillance data, this case series suggests a possible association between acute myocarditis and COVID-19 vaccination in young males and highlights a potential pattern in accompanying CMR abnormalities.

Aorta-cameral fistulas: Spectrum of CT findings and review.

Aorto-cameral fistula (ACF) is an uncommon entity, defined as an abnormal communication between the aorta and a cardiac chamber. The most common causes include ruptured sinus of Valsalva aneurysm, infective endocarditis, traumatic injury, aortic dissection, or rarely can be iatrogenic in nature. While smaller communications may initially be asymptomatic, the natural course of these connections is generally refractory heart failure as they do not spontaneously heal. Larger fistulas can be life threatening with high mortality rates, and therefore once recognized, surgery is generally considered the treatment of choice. Diagnosis, however, can be challenging, and various imaging modalities are often used for diagnosis. This review highlights common underlying etiologies, clinical manifestations, and radiologic imaging appearances of ACF to each of the cardiac chambers of this uncommon, but clinically important entity, with emphasis on CT.