Implementation of a Survey Spine Magnetic Resonance Imaging Protocol for Cord Compression in the Emergency Department: Experience at a Level-1 Trauma Center.

BACKGROUND AND PURPOSE: Imaging stewardship in the emergency department (ED) is vital in ensuring patients receive optimized care. While suspected cord compression (CC) is a frequent indication for total spine MRI in the ED, the incidence of CC is low. Recently, our level-I trauma center introduced a survey spine MRI protocol to evaluate for suspected CC while reducing exam time to avoid imaging overutilization. This study aims to evaluate the time savings, frequency of ordering patterns of the survey, and the symptoms and outcomes of patients undergoing the survey. MATERIALS AND METHODS: This retrospective study examined patients who received a survey spine MRI in the ED at our institution between 2018 and 2022. All exams were performed on a 1.5T GE scanner using our institutional CC survey protocol, which includes sagittal T2 and STIR sequences through the cervical, thoracic, and lumbar spine. Exams were read by a blinded, board-certified neuroradiologist. RESULTS: A total of 2,002 patients received a survey spine MRI protocol during the study period. Of these patients, 845 (42.2%, mean age 57 ± 19 years, 45% female) received survey spine MRI exams for the suspicion of CC, and 120 patients (14.2% positivity rate) had radiographic CC. The survey spine MRI averaged 5 minutes and 50 seconds (79% faster than routine MRI). On multivariate analysis, trauma, back pain, lower extremity weakness, urinary or bowel incontinence, numbness, ataxia, and hyperreflexia were each independently associated with CC. Of the 120 patients with CC, 71 underwent emergent surgery, 20 underwent non-emergent surgery, and 29 were managed medically. CONCLUSIONS: The survey spine protocol was positive for CC in 14% of patients in our cohort and acquired at a 79% faster rate compared to routine total spine. Understanding the positivity rate of CC, the clinical symptoms that are most associated with CC, and the subsequent care management for patients presenting with suspected cord compression who received the survey spine MRI may better inform the broad adoption and subsequent utilization of survey imaging protocols in emergency settings to increase throughput, improve allocation of resources, and provide efficient care for patients with suspected CC.ABBREVIATIONS: CC, cord compression; ED, emergency department; MRI, magnetic resonance imaging; T2; T2-weighted imaging sequence; STIR, short TI inversion recovery.

Effects of Low-Level Light Therapy on Resting-State Connectivity Following Moderate Traumatic Brain Injury: Secondary Analyses of a Double-blinded Placebo-controlled Study.

Background Low-level light therapy (LLLT) has been shown to modulate recovery in patients with traumatic brain injury (TBI). However, the impact of LLLT on the functional connectivity of the brain when at rest has not been well studied. Purpose To use functional MRI to assess the effect of LLLT on whole-brain resting-state functional connectivity (RSFC) in patients with moderate TBI at acute (within 1 week), subacute (2-3 weeks), and late-subacute (3 months) recovery phases. Materials and Methods This is a secondary analysis of a prospective single-site double-blinded sham-controlled study conducted in patients presenting to the emergency department with moderate TBI from November 2015 to July 2019. Participants were randomized for LLLT and sham treatment. The primary outcome of the study was to assess structural connectivity, and RSFC was collected as the secondary outcome. MRI was used to measure RSFC in 82 brain regions in participants during the three recovery phases. Healthy individuals who did not receive treatment were imaged at a single time point to provide control values. The Pearson correlation coefficient was estimated to assess the connectivity strength for each brain region pair, and estimates of the differences in Fisher z-transformed correlation coefficients (hereafter, z differences) were compared between recovery phases and treatment groups using a linear mixed-effects regression model. These analyses were repeated for all brain region pairs. False discovery rate (FDR)-adjusted P values were computed to account for multiple comparisons. Quantile mixed-effects models were constructed to quantify the association between the Rivermead Postconcussion Symptoms Questionnaire (RPQ) score, recovery phase, and treatment group. Results RSFC was evaluated in 17 LLLT-treated participants (median age, 50 years [IQR, 25-67 years]; nine female), 21 sham-treated participants (median age, 50 years [IQR, 43-59 years]; 11 female), and 23 healthy control participants (median age, 42 years [IQR, 32-54 years]; 13 male). Seven brain region pairs exhibited a greater change in connectivity in LLLT-treated participants than in sham-treated participants between the acute and subacute phases (range of z differences, 0.37 [95% CI: 0.20, 0.53] to 0.45 [95% CI: 0.24, 0.67]; FDR-adjusted P value range, .010-.047). Thirteen different brain region pairs showed an increase in connectivity in sham-treated participants between the subacute and late-subacute phases (range of z differences, 0.17 [95% CI: 0.09, 0.25] to 0.26 [95% CI: 0.14, 0.39]; FDR-adjusted P value range, .020-.047). There was no evidence of a difference in clinical outcomes between LLLT-treated and sham-treated participants (range of differences in medians, -3.54 [95% CI: -12.65, 5.57] to -0.59 [95% CI: -7.31, 8.49]; P value range, .44-.99), as measured according to RPQ scores. Conclusion Despite the small sample size, the change in RSFC from the acute to subacute phases of recovery was greater in LLLT-treated than sham-treated participants, suggesting that acute-phase LLLT may have an impact on resting-state neuronal circuits in the early recovery phase of moderate TBI. ClinicalTrials.gov Identifier: NCT02233413 © RSNA, 2024 Supplemental material is available for this article.

Trends in non-focal neurological chief complaints and CT angiography utilization among adults in the emergency department.

Prudent imaging use is essential for cost reduction and efficient patient triage. Recent efforts have focused on head and neck CTA in patients with emergent concerns for non-focal neurological complaints, but have failed to demonstrate whether increases in utilization have resulted in better care. The objective of this study was to examine trends in head and neck CTA ordering and determine whether a correlation exists between imaging utilization and positivity rates. This is a single-center retrospective observational study at a quaternary referral center. This study includes patients presenting with headache and/or dizziness to the emergency department between January 2017 and December 2021. Patients who received a head and neck CTA were compared to those who did not. The main outcomes included annual head and neck CTA utilization and positivity rates, defined as the percent of scans with attributable acute pathologies. Among 24,892 emergency department visits, 2264 (9.1%) underwent head and neck CTA imaging. The percentage of patients who received a scan over the study period increased from 7.89% (422/5351) in 2017 to 13.24% (662/5001) in 2021, representing a 67.4% increase from baseline (OR, 1.14; 95% CI 1.11-1.18; P < .001). The positivity rate, or the percentage of scans ordered that revealed attributable acute pathology, dropped from 16.8% (71/422) in 2017 to 10.4% (69/662) in 2021 (OR, 0.86; 95% CI 0.79-0.94; P = .001), a 38% reduction in positive examinations. Throughout the study period, there was a 67.4% increase in head and neck CTA ordering with a concomitant 38.1% decrease in positivity rate.

Clinical Evaluation of a 2-Minute Ultrafast Brain MR Protocol for Evaluation of Acute Pathology in the Emergency and Inpatient Settings.

BACKGROUND AND PURPOSE: The use of MR imaging in emergency settings has been limited by availability, long scan times, and sensitivity to motion. This study assessed the diagnostic performance of an ultrafast brain MR imaging protocol for evaluation of acute intracranial pathology in the emergency department and inpatient settings. MATERIALS AND METHODS: Sixty-six adult patients who underwent brain MR imaging in the emergency department and inpatient settings were included in the study. All patients underwent both the reference and the ultrafast brain MR protocols. Both brain MR imaging protocols consisted of T1-weighted, T2/T2*-weighted, FLAIR, and DWI sequences. The ultrafast MR images were reconstructed by using a machine-learning assisted framework. All images were reviewed by 2 blinded neuroradiologists. RESULTS: The average acquisition time was 2.1 minutes for the ultrafast brain MR protocol and 10 minutes for the reference brain MR protocol. There was 98.5% agreement on the main clinical diagnosis between the 2 protocols. In head-to-head comparison, the reference protocol was preferred in terms of image noise and geometric distortion (P < .05 for both). The ultrafast ms-EPI protocol was preferred over the reference protocol in terms of reduced motion artifacts (P < .01). Overall diagnostic quality was not significantly different between the 2 protocols (P > .05). CONCLUSIONS: The ultrafast brain MR imaging protocol provides high accuracy for evaluating acute pathology while only requiring a fraction of the scan time. Although there was greater image noise and geometric distortion on the ultrafast brain MR protocol images, there was significant reduction in motion artifacts with similar overall diagnostic quality between the 2 protocols.

Empathy and Equity: Key Considerations for Large Language Model Adoption in Health Care.

The growing presence of large language models (LLMs) in health care applications holds significant promise for innovative advancements in patient care. However, concerns about ethical implications and potential biases have been raised by various stakeholders. Here, we evaluate the ethics of LLMs in medicine along 2 key axes: empathy and equity. We outline the importance of these factors in novel models of care and develop frameworks for addressing these alongside LLM deployment.

Neuroradiology Applications of Dual and Multi-energy Computed Tomography.

Computed tomography (CT) imaging has become an essential diagnostic tool for most emergent clinical conditions, owing to its speed, accuracy, cost, and few contraindications, compared with MR imaging cross-sectional imaging. Spectral CT, which includes dual, multienergy, and photon-counting CT, is superior to conventional single-energy CT (SECT) in many respects. Spectral information enables differentiation between materials with similar Hounsfield Unit attenuations on SECT; examples include but are not limited to "virtual noncontrast," "virtual noncalcium," and most notably for neuro applications, "hemorrhage versus iodine." This article expands on the many possible benefits of spectral CT in neuroimaging.

Longitudinal Imaging in a Patient With Opioid-associated Amnestic Syndrome.

Since 2012, individuals with a history of opioid misuse have infrequently been observed to develop a sudden-onset amnestic syndrome associated with bilateral hippocampal-restricted diffusion on MRI. Follow-up imaging of this opioid-associated amnestic syndrome (OAS) has revealed persistent hippocampal abnormalities. Given these observations, as well as neuropathological studies demonstrating excessive tau deposition in the hippocampi and other brain regions of individuals with opioid misuse, we describe longitudinal imaging of a patient with a history of OAS from presentation through 53 months later, when tau positron emission tomography (PET) was performed. Our patient was a 21-year-old woman with a history of attention-deficit hyperactivity disorder and substance use disorder, including opioids (intravenous heroin), who was hospitalized for acute-onset, dense anterograde amnesia. Her urine toxicology screen was positive for opiates. On presentation, her brain MRI showed restricted diffusion as well as T2 and fluid-attenuated inversion recovery (FLAIR) hyperintensity of the hippocampi and globi pallidi. On day 3, magnetic resonance spectroscopy of a right hippocampal region of interest showed a mild reduction of N-acetyl aspartate/creatine, slight elevation of choline/creatine, and the appearance of lactate/lipid and glutamate/glutamine peaks. At 4.5 months, there was resolution of restricted diffusion on MRI, although a minimal anterior T2 and FLAIR hyperintense signal in the right hippocampus persisted. However, by 53 months, when mild memory loss was reported, the hippocampi appeared normal on MRI, and [ 18 F]T807 (tau) PET showed no uptake suggestive of tau deposition. This case report supports the investigation into the hypothesis that OAS may follow a trajectory of reversible metabolic injury.

Symmetric collateral pattern on CTA predicts favorable outcomes after endovascular thrombectomy for large vessel occlusion stroke.

Endovascular thrombectomy (EVT) has revolutionized large vessel occlusion (LVO) stroke management, but often requires advanced imaging. The collateral pattern on CT angiograms may be an alternative because a symmetric collateral pattern correlates with a slowly growing, small ischemic core. We tested the hypothesis that such patients will have favorable outcomes after EVT. Consecutive patients (n = 74) with anterior LVOs who underwent EVT were retrospectively analyzed. Inclusion criteria were available CTA and 90-day modified Rankin Scale (mRS). CTA collateral patterns were symmetric in 36%, malignant in 24%, or other in 39%. Median NIHSS was 11 for symmetric, 18 for malignant, and 19 for other (p = 0.02). Ninety-day mRS ≤2, indicating independent living, was achieved in 67% of symmetric, 17% of malignant, and 38% of other patterns (p = 0.003). A symmetric collateral pattern was a significant determinant of 90-day mRS ≤2 (aOR = 6.62, 95%CI = 2.24,19.53; p = 0.001) in a multivariable model that included age, NIHSS, baseline mRS, thrombolysis, LVO location, and successful reperfusion. We conclude that a symmetric collateral pattern predicts favorable outcomes after EVT for LVO stroke. Because the pattern also marks slow ischemic core growth, patients with symmetric collaterals may be suitable for transfer for thrombectomy. A malignant collateral pattern is associated with poor clinical outcomes.

Aluminum Thin Film Nanostructure Traces in Pediatric EEG Net for MRI and CT Artifact Reduction.

Magnetic resonance imaging (MRI) and continuous electroencephalogram (EEG) monitoring are essential in the clinical management of neonatal seizures. EEG electrodes, however, can significantly degrade the image quality of both MRI and CT due to substantial metallic artifacts and distortions. Thus, we developed a novel thin film trace EEG net ("NeoNet") for improved MRI and CT image quality without compromising the EEG signal quality. The aluminum thin film traces were fabricated with an ultra-high-aspect ratio (up to 17,000:1, with dimensions 30 nm × 50.8 cm × 100 µm), resulting in a low density for reducing CT artifacts and a low conductivity for reducing MRI artifacts. We also used numerical simulation to investigate the effects of EEG nets on the B1 transmit field distortion in 3 T MRI. Specifically, the simulations predicted a 65% and 138% B1 transmit field distortion higher for the commercially available copper-based EEG net ("CuNet", with and without current limiting resistors, respectively) than with NeoNet. Additionally, two board-certified neuroradiologists, blinded to the presence or absence of NeoNet, compared the image quality of MRI images obtained in an adult and two children with and without the NeoNet device and found no significant difference in the degree of artifact or image distortion. Additionally, the use of NeoNet did not cause either: (i) CT scan artifacts or (ii) impact the quality of EEG recording. Finally, MRI safety testing confirmed a maximum temperature rise associated with the NeoNet device in a child head-phantom to be 0.84 °C after 30 min of high-power scanning, which is within the acceptance criteria for the temperature for 1 h of normal operating mode scanning as per the FDA guidelines. Therefore, the proposed NeoNet device has the potential to allow for concurrent EEG acquisition and MRI or CT scanning without significant image artifacts, facilitating clinical care and EEG/fMRI pediatric research.

Assessing the Relationship Between Race, Language, and Surgical Admissions in the Emergency Department.

INTRODUCTION: English proficiency and race are both independently known to affect surgical access and quality, but relatively little is known about the impact of race and limited English proficiency (LEP) on admission for emergency surgery from the emergency department (ED). Our objective was to examine the influence of race and English proficiency on admission for emergency surgery from the ED. METHODS: We conducted a retrospective observational cohort study from January 1-December 31, 2019 at a large, quaternary-care urban, academic medical center with a 66-bed ED Level I trauma and burn center. We included ED patients of all self-reported races reporting a preferred language other than English and requiring an interpreter or declaring English as their preferred language (control group). A multivariable logistic regression was fit to assess the association of LEP status, race, age, gender, method of arrival to the ED, insurance status, and the interaction between LEP status and race with admission for surgery from the ED. RESULTS: A total of 85,899 patients (48.1% female) were included in this analysis, of whom 3,179 (3.7%) were admitted for emergent surgery. Regardless of LEP status, patients identifying as Black (odds ratio [OR] 0.456, 95% CI 0.388-0.533; P<0.005), Asian [OR 0.759, 95% CI 0.612-0.929]; P=0.009), or female [OR 0.926, 95% CI 0.862-0.996]; P=0.04) had significantly lower odds for admission for surgery from the ED compared to White patients. Compared to individuals on Medicare, those with private insurance [OR 1.25, 95% CI 1.13-1.39; P <0.005) were significantly more likely to be admitted for emergent surgery, whereas those without insurance [OR 0.581, 95% CI 0.323-0.958; P=0.05) were significantly less likely to be admitted for emergent surgery. There was no significant difference in odds of admission for surgery between LEP vs non-LEP patients. CONCLUSION: Individuals without health insurance and those identifying as female, Black, or Asian had significantly lower odds of admission for surgery from the ED compared to those with health insurance, males, and those self-identifying as White, respectively. Future studies should assess the reasons underpinning this finding to elucidate impact on patient outcomes.

Incorporating algorithmic uncertainty into a clinical machine deep learning algorithm for urgent head CTs.

Machine learning (ML) algorithms to detect critical findings on head CTs may expedite patient management. Most ML algorithms for diagnostic imaging analysis utilize dichotomous classifications to determine whether a specific abnormality is present. However, imaging findings may be indeterminate, and algorithmic inferences may have substantial uncertainty. We incorporated awareness of uncertainty into an ML algorithm that detects intracranial hemorrhage or other urgent intracranial abnormalities and evaluated prospectively identified, 1000 consecutive noncontrast head CTs assigned to Emergency Department Neuroradiology for interpretation. The algorithm classified the scans into high (IC+) and low (IC-) probabilities for intracranial hemorrhage or other urgent abnormalities. All other cases were designated as No Prediction (NP) by the algorithm. The positive predictive value for IC+ cases (N = 103) was 0.91 (CI: 0.84-0.96), and the negative predictive value for IC- cases (N = 729) was 0.94 (0.91-0.96). Admission, neurosurgical intervention, and 30-day mortality rates for IC+ was 75% (63-84), 35% (24-47), and 10% (4-20), compared to 43% (40-47), 4% (3-6), and 3% (2-5) for IC-. There were 168 NP cases, of which 32% had intracranial hemorrhage or other urgent abnormalities, 31% had artifacts and postoperative changes, and 29% had no abnormalities. An ML algorithm incorporating uncertainty classified most head CTs into clinically relevant groups with high predictive values and may help accelerate the management of patients with intracranial hemorrhage or other urgent intracranial abnormalities.

Advanced Imaging for Acute Stroke Treatment Selection: CT, CTA, CT Perfusion, and MR Imaging.

There is constant evolution in the diagnosis and treatment of acute ischemic stroke due to advances in treatments, imaging, and outreach. Two major revolutions were the advent of intravenous thrombolysis in the 1990s and endovascular thrombectomy in 2010s. Neuroimaging approaches have also evolved with key goals-detect hemorrhage, augment thrombolysis treatment selection, detect arterial occlusion, estimate infarct core, estimate viable penumbra, and augment thrombectomy treatment selection. The ideal approach to diagnosis and treatment may differ depending on the system of care and available resources. Future directions include expanding indications for these treatments, including a shift from time-based to tissue-based selection.

Trends in oncological imaging during the COVID-19 pandemic through the vaccination era.

BACKGROUND: This study examines the impact that the COVID-19 pandemic has had on computed tomography (CT)-based oncologic imaging utilization. METHODS: We retrospectively analyzed cancer-related CT scans during four time periods: pre-COVID (1/5/20-3/14/20), COVID peak (3/15/20-5/2/20), post-COVID peak (5/3/20-12/19/20), and vaccination period (12/20/20-10/30/21). We analyzed CTs by imaging indication, setting, and hospital type. Using percentage decrease computation and Student's t-test, we calculated the change in mean number of weekly cancer-related CTs for all periods compared to the baseline pre-COVID period. This study was performed at a single academic medical center and three affiliated hospitals. RESULTS: During the COVID peak, mean CTs decreased (-43.0%, p < 0.001), with CTs for (1) cancer screening, (2) initial workup, (3) cancer follow-up, and (4) scheduled surveillance of previously treated cancer dropping by 81.8%, 56.3%, 31.7%, and 45.8%, respectively (p < 0.001). During the post-COVID peak period, cancer screenings and initial workup CTs did not return to prepandemic imaging volumes (-11.4%, p = 0.028; -20.9%, p = 0.024). The ED saw increases in weekly CTs compared to prepandemic levels (+31.9%, p = 0.008), driven by increases in cancer follow-up CTs (+56.3%, p < 0.001). In the vaccination period, cancer screening CTs did not recover to baseline (-13.5%, p = 0.002) and initial cancer workup CTs doubled (+100.0%, p < 0.001). The ED experienced increased cancer-related CTs (+75.9%, p < 0.001), driven by cancer follow-up CTs (+143.2%, p < 0.001) and initial workups (+46.9%, p = 0.007). CONCLUSIONS AND RELEVANCE: The pandemic continues to impact cancer care. We observed significant declines in cancer screening CTs through the end of 2021. Concurrently, we observed a 2× increase in initial cancer workup CTs and a 2.4× increase in cancer follow-up CTs in the ED during the vaccination period, suggesting a boom of new cancers and more cancer examinations associated with emergency level acute care.

Percent Insular Ribbon Infarction for Predicting Infarct Growth Rate and 90-Day Outcomes in Large-Vessel Occlusive Stroke: Secondary Analysis of Prospective Clinical Trial Data.

BACKGROUND. Insight into the natural history of infarct growth could help identify patients with slowly progressing stroke who may benefit from delayed endovascular thrombectomy (EVT). OBJECTIVE. The purpose of this article is to evaluate associations of percent insular ribbon infarction (PIRI) with infarct growth rate (IGR) and 90-day outcomes in patients with large-vessel occlusive stroke. METHODS. This retrospective study was a secondary analysis of a prior clinical trial that enrolled patients with acute stroke not treated with reperfusion therapies from January 2007 to June 2009. The present analysis evaluated 31 trial patients (median age, 71 years; 12 women, 19 men) with anterior-circulation large-vessel occlusion who underwent serial MRI examinations. Two neuroradiologists independently scored PIRI on presentation MRI examinations on the basis of the ratio of the length of the portion of the insula showing restricted diffusion to the insula's total length using a previously described 0-4 scale; scores were categorized (mild [0-1], moderate [2], or severe [3-4]), and discrepancies were resolved by consensus. The 90-day modified Rankin Scale (mRS) was obtained. As part of earlier clinical trial analyses, collateral pattern on CTA was classified as symmetric, malignant, or other, and infarct volumes were measured on DWI during the initial 48 hours after presentation and on FLAIR at 90 days. RESULTS. Interrater agreement for PIRI category was strong (κ = 0.89). PIRI was mild in 10, moderate in four, and severe in 17 patients. For mild, moderate, and severe PIRI, median IGR from onset to presentation was 1.6 cm3/h, 8.5 cm3/h, and 17.5 cm3/h (p < .001); median IGR from presentation to 48 hours was 0.3 cm3/h, 0.2 cm3/h, and 1.2 cm3/h (p = .005); median 90-day infarct volume was 9.4 cm3, 39.8 cm3, and 108.6 cm3 (p = .01); and 90-day mRS of 2 or less occurred in 78%, 67%, and 6% of patients (p = .001). In multivariable models controlling for age, internal carotid artery occlusion, and collateral pattern, PIRI category independently predicted onset-to-presentation IGR (ß = 1.5), presentation-to-48-hour IGR (ß = 1.3), and 90-day mRS of 2 or less (OR = 0.2). For predicting 90-day mRS of 2 or less, mild-to-moderate PIRI had sensitivity of 90.0% and specificity of 84.2%; symmetric collateral pattern had sensitivity of 70.0% and specificity of 73.7%. CONCLUSION. PIRI was independently associated with IGR and 90-day outcome. CLINICAL IMPACT. PIRI may help identify patients who could benefit from late-window EVT when requiring transfer to EVT-capable centers.

Head CT deep learning model is highly accurate for early infarct estimation.

Non-contrast head CT (NCCT) is extremely insensitive for early (< 3-6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61-66% (specificity 90-92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r2 > 0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70 mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.

A high-resolution pediatric female whole-body numerical model with comparison to a male model.

Objective. Numerical models are central in designing and testing novel medical devices and in studying how different anatomical changes may affect physiology. Despite the numerous adult models available, there are only a few whole-body pediatric numerical models with significant limitations. In addition, there is a limited representation of both male and female biological sexes in the available pediatric models despite the fact that sex significantly affects body development, especially in a highly dynamic population. As a result, we developed Athena, a realistic female whole-body pediatric numerical model with high-resolution and anatomical detail.Approach. We segmented different body tissues through Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images of a healthy 3.5 year-old female child using 3D Slicer. We validated the high anatomical accuracy segmentation through two experienced sub-specialty-certified neuro-radiologists and the inter and intra-operator variability of the segmentation results comparing sex differences in organ metrics with physiologic values. Finally, we compared Athena with Martin, a similar male model, showing differences in anatomy, organ metrics, and MRI dosimetric exposure.Main results. We segmented 267 tissue compartments, which included 50 brain tissue labels. The tissue metrics of Athena displayed no deviation from the literature value of healthy children. We show the variability of brain metrics in the male and female models. Finally, we offer an example of computing Specific Absorption Rate and Joule heating in a toddler/preschooler at 7 T MRI.Significance. This study introduces a female realistic high-resolution numerical model using MRI and CT scans of a 3.5 year-old female child, the use of which includes but is not limited to radiofrequency safety studies for medical devices (e.g. an implantable medical device safety in MRI), neurostimulation studies, and radiation dosimetry studies. This model will be open source and available on the Athinoula A. Martinos Center for Biomedical Imaging website.

Tackling prediction uncertainty in machine learning for healthcare.

Predictive machine-learning systems often do not convey the degree of confidence in the correctness of their outputs. To prevent unsafe prediction failures from machine-learning models, the users of the systems should be aware of the general accuracy of the model and understand the degree of confidence in each individual prediction. In this Perspective, we convey the need of prediction-uncertainty metrics in healthcare applications, with a focus on radiology. We outline the sources of prediction uncertainty, discuss how to implement prediction-uncertainty metrics in applications that require zero tolerance to errors and in applications that are error-tolerant, and provide a concise framework for understanding prediction uncertainty in healthcare contexts. For machine-learning-enabled automation to substantially impact healthcare, machine-learning models with zero tolerance for false-positive or false-negative errors must be developed intentionally.