Head CTs Research Articles

Leveraging an EHR tool to improve provider adherence to the modified brain injury guidelines

IntroductionThe aim was to leverage electronic health record (EHR) smartphrases to improve compliance with the modified Brain Injury Guidelines (mBIG). MethodsSmartphrases were developed for the trauma team and radiology and implemented December 2022. Traumatic brain injury (TBI) patients meeting mBIG inclusion from 03/2021- 07/2023 were reviewed. Smartphrase usage and clinical compliance with mBIG (measured by percent reduction of repeat head imaging, ICU admissions, and neurosurgery consults) were compared pre- and post-intervention. Results268 cases were examined. Post-intervention, mBIG1 patients had significantly fewer neurosurgery consults (82.4 ​% vs. 50.0 ​%, OR ​= ​0.21, p ​= ​0.03), while mBIG2 patients had significantly fewer repeat head CTs (91.0 ​% vs. 66.7 ​%, OR ​= ​0.2, p ​= ​0.01), ICU admissions (66.7 ​% vs. 38.5 ​%, OR ​= ​0.31, p ​= ​0.02) and neurosurgery consults (93.9 ​% vs. 56.4 ​%, OR ​= ​0.08, p ​< ​0.01). ConclusionStandardized smartphrases can streamline workflow and significantly improve trauma team compliance with best practice guidelines for TBI and reduce unnecessary imaging, consults, and costly ICU admissions.

Artificial Intelligence Efficacy as a Function of Trainee Interpreter Proficiency: Lessons from a Randomized Controlled Trial.

Recently, artificial intelligence tools have been deployed with increasing speed in educational and clinical settings. However, the use of artificial intelligence by trainees across different levels of experience has not been well-studied. This study investigates the impact of artificial intelligence assistance on the diagnostic accuracy for intracranial hemorrhage and large-vessel occlusion by medical students and resident trainees. This prospective study was conducted between March 2023 and October 2023. Medical students and resident trainees were asked to identify intracranial hemorrhage and large-vessel occlusion in 100 noncontrast head CTs and 100 head CTAs, respectively. One group received diagnostic aid simulating artificial intelligence for intracranial hemorrhage only (n = 26); the other, for large-vessel occlusion only (n = 28). Primary outcomes included accuracy, sensitivity, and specificity for intracranial hemorrhage/large-vessel occlusion detection without and with aid. Study interpretation time was a secondary outcome. Individual responses were pooled and analyzed with the t test; differences in continuous variables were assessed with ANOVA. Forty-eight participants completed the study, generating 10,779 intracranial hemorrhage or large-vessel occlusion interpretations. With diagnostic aid, medical student accuracy improved 11.0 points (P < .001) and resident trainee accuracy showed no significant change. Intracranial hemorrhage interpretation time increased with diagnostic aid for both groups (P < .001), while large-vessel occlusion interpretation time decreased for medical students (P < .001). Despite worse performance in the detection of the smallest-versus-largest hemorrhages at baseline, medical students were not more likely to accept a true-positive artificial intelligence result for these more difficult tasks. Both groups were considerably less accurate when disagreeing with the artificial intelligence or when supplied with an incorrect artificial intelligence result. This study demonstrated greater improvement in diagnostic accuracy with artificial intelligence for medical students compared with resident trainees. However, medical students were less likely than resident trainees to overrule incorrect artificial intelligence interpretations and were less accurate, even with diagnostic aid, than the artificial intelligence was by itself.

The association between slow-wave sleep and choroid plexus calcifications in older adults. Results from the sleep disorders substudy of the Atahualpa Project cohort.

ObjectiveIt has been suggested that choroid plexus calcifications (CPC) may be associated with glymphatic system dysfunction and with disturbed slow-wave (N3) sleep. If this is the case, volumetric analysis of CPC could be used to estimate the functional ability of the glymphatic system. However, data on this association is limited. This study aims to assess the association between percentages of N3 sleep – used as a putative marker of glymphatic system activity – and the volume of CPC in older adults. Patients and methodsCommunity-dwelling individuals aged ≥60 years enrolled in the Atahualpa Project Cohort received head CTs (for automated determinations of CPC volume) and a single-night polysomnography (PSG) for quantification of N3 sleep percentages. Multivariate linear regression and non-parametric models were fitted to assess the association between these variables. ResultsA total of 125 older adults (median age: 65 years; 32 % males) were included. The mean percentage of N3 sleep was 12.4±9.1 %, and the mean volume of CPC was 655±345.3 µL. Non-parametric locally weighted scatterplot smoothing showed that the volume of CPC increased as the percentage of N3 sleep increased, but only when N3 sleep is reduced (up to 12 % of total sleep time). The significance disappeared when PSG parameters were included in the model as well as in participants with normal N3 sleep percentages. ConclusionsStudy results suggest that in the presence of severe reductions in N3 sleep, increased CPC volume may be a manifestation of choroid plexus compensation or adaptation, and not necessarily dysfunction.

Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time.

The diagnostic performance of an artificial intelligence (AI) clinical decision support solution for acute intracranial hemorrhage (ICH) detection was assessed in a large teleradiology practice. The impact on radiologist read times and system efficiency was also quantified. A total of 61 704 consecutive noncontrast head CT examinations were retrospectively evaluated. System performance was calculated along with mean and median read times for CT studies obtained before (baseline, pre-AI period; August 2021 to May 2022) and after (post-AI period; January 2023 to February 2024) AI implementation. The AI solution had a sensitivity of 75.6%, specificity of 92.1%, accuracy of 91.7%, prevalence of 2.70%, and positive predictive value of 21.1%. Of the 56 745 post-AI CT scans with no bleed identified by a radiologist, examinations falsely flagged as suspected ICH by the AI solution (n = 4464) took an average of 9 minutes 40 seconds (median, 8 minutes 7 seconds) to interpret as compared with 8 minutes 25 seconds (median, 6 minutes 48 seconds) for unremarkable CT scans before AI (n = 49 007) (P < .001) and 8 minutes 38 seconds (median, 6 minutes 53 seconds) after AI when ICH was not suspected by the AI solution (n = 52 281) (P < .001). CT scans with no bleed identified by the AI but reported as positive for ICH by the radiologist (n = 384) took an average of 14 minutes 23 seconds (median, 13 minutes 35 seconds) to interpret as compared with 13 minutes 34 seconds (median, 12 minutes 30 seconds) for CT scans correctly reported as a bleed by the AI (n = 1192) (P = .04). With lengthened read times for falsely flagged examinations, system inefficiencies may outweigh the potential benefits of using the tool in a high volume, low prevalence environment. Keywords: Artificial Intelligence, Intracranial Hemorrhage, Read Time, Report Turnaround Time, System Efficiency Supplemental material is available for this article. © RSNA, 2024.

Establishment of diagnostic reference level for routine CT scan examination in Sokoto state, Nigeria

Diagnostic Reference Levels (DRLs) are embedded into the optimization procedure to regulate CT dose and diagnostic quality. The purpose of this research was to establish the local DRLs and radiation dose exposure for CT scans at the Sokoto State Advanced Medical Diagnostic Center, Nigeria. 190 patients who had CT head, chest, and abdomen-pelvis scans were collected and evaluated for this study. It was established that the DRLs for CTDIvol for the head, thorax, and abdomen-pelvis were 48.2, 9.44, and 8.02, respectively with DLP DRLs in mGy.cm were 1044, 372, and 646. When comparing head CTs, our CTDIvol DRL is lower than many international standards, yet our DLP DRL is also below those of other nations. The chest CT DRL from Sokoto state is comparable to the DLP standards of some nations, although its CTDIvol is higher. The abdomen-pelvis CTDIvol DRLs are lower than those of the UK and US, thus necessitating the implementation of a controlled and optimized protocol in order to guarantee patient safety while maintaining image quality.

A Pediatric Brain Injury Guideline Allows Safe Management of Traumatic Brain Injuries by Trauma Surgeons

BackgroundWe implemented a pediatric Brain Injury Guideline (pBIG) to stratify traumatic brain injuries (TBI) and allow management of less severe cases without repeat CT imaging or neurosurgical consultation. Injuries were classified as mild (pBIG1), moderate (pBIG2), severe (pBIG3) or isolated skull fracture (ISF) based on neurologic status, size and number of bleeds. We hypothesize that pediatric TBIs can be safely managed with this guideline. MethodsIsolated TBIs (<18 years) were queried from the Pediatric Trauma Registry after pBIG implementation from July 2021–March 2023. Datasets included age, injury specifics, repeat head CTs, neurosurgical consultations and interventions. Analysis was performed with Stata, with significance set at p < 0.05. ResultsA total of 139 children with a median age of 2.8 years were included. Skull fractures (113, 81%) and subdural hematomas (54, 39%) were the most common injuries. Repeat head CTs were obtained in 44 (32%) and neurosurgical consultation in 89 (64%). Overall guideline compliance was 83.5%, with best performance in the pBIG3 category (96%). One pBIG1 patient had increasing symptoms requiring upgrade, neurosurgical consultation and repeat head CT, but no intervention. Five children (3.6%; 4 isolated skull fracture, 1 pBIG3) had post-discharge ED visits and 1 (0.7%, ISF) had a post-discharge CT. Three (2.2%) children, all in the pBIG3 group, died from their TBIs. ConclusionsAdherence to the algorithm was 83.5%, with the lowest compliance in the moderate TBI (pBIG2) category. This group had a high rate of neurosurgical consultation suggesting uneasiness with independent management of moderate injuries when compared to minor TBIs or isolated skull fracture. Outcomes with the use of the pBIG algorithm were otherwise acceptable. Level of EvidenceLevel IV, Therapeutic/Care Management.

Choroid plexus calcifications are not associated with putative markers of glymphatic dysfunction: A population study in middle-aged and older adults.

Recent studies have suggested an association between dysfunction of the choroid plexus and the glymphatic system. However, information is inconclusive. Following a population-based study design, we aimed to assess the association between choroid plexus calcifications (CPCs)-as a surrogate of choroid plexus dysfunction-and severity and progression of putative markers of glymphatic dysfunction, including white matter hyperintensities (WMH) of presumed vascular origin and abnormally enlarged basal ganglia perivascular spaces (BG-PVS). This study recruited community-dwellers aged ≥40years living in neighboring Ecuadorian villages. Participants who had baseline head CTs and brain MRIs were included in cross-sectional analyses and those who additional had follow-up MRIs (after a mean of 6.4 ± 1.5years) were included in longitudinal analyses. Logistic and Poisson regression models, adjusted for demographics and cardiovascular risk factors, were fitted to assess associations between CPCs and WMH and enlarged BG-PVS severity and progression. A total of 590 individuals were included in the cross-sectional component of the study, and 215 in the longitudinal component. At baseline, 25% of participants had moderate-to-severe WMH and 27% had abnormally enlarged BG-PVS. At follow-up, 36% and 20% of participants had WMH and enlarged BG-PVS progression, respectively. Logistic regression models showed no significant differences between CPCs volumes stratified in quartiles and severity of WMH and enlarged BG-PVS. Poisson regression models showed no association between the exposure and WMH and enlarged BG-PVS progression. Baseline age remained significant in these models. Choroid plexus calcifications are not associated with putative markers of glymphatic system dysfunction.

Risk of hematologic malignant neoplasms from head CT radiation in children and adolescents presenting with minor head trauma: a nationwide population-based cohort study.

The carcinogenic risks of CT radiation in children and adolescents remain debated. We aimed to assess the carcinogenic risk of CTs performed in children and adolescents with minor head trauma. In this nationwide population-based cohort study, we included 2,411,715 patients of age 0-19 with minor head trauma from 2009 to 2017. We excluded patients with elevated cancer risks or substantial past medical radiation exposure. Patients were categorized into CT-exposed or CT-unexposed group according to claim codes for head CT. The primary outcome was development of hematologic malignant neoplasms. Secondary outcomes included development of malignant solid neoplasms and benign neoplasms in the brain. We measured the incidence rate ratio (IRR) and incidence rate difference (IRD) using G-computation with Poisson regression adjusting for age, sex, hospital setting, and the type of head trauma. Hematologic malignant neoplasms developed in 100 of 216,826 patients during 1,303,680 person-years in the CT-exposed group and in 808 of 2,194,889 patients during 13,501,227 person-years in the CT-unexposed group. For hematologic malignant neoplasms, the IRR was 1.29 (95% CI, 1.03-1.60) and the IRD was 1.71 (95% CI, 0.04-3.37) per 100,000 person-years at risk. The majority of excess hematologic malignant neoplasms were leukemia (IRR, 1.40 [98.3% CI, 1.05-1.87]; IRD, 1.59 [98.3% CI, 0.02-3.16] per 100,000 person-years at risk). There were no between-group differences for secondary outcomes. Radiation exposure from head CTs in children and adolescents with minor head trauma was associated with an increased incidence of hematologic malignant neoplasms. Our study provides a quantitative grasp of the risk conferred by CT examinations in children and adolescents, thereby providing the basis for cost-benefit analyses and evidence-driven guidelines for patient triaging in head trauma. • This nationwide population-based cohort study showed that radiation exposure from head CTs in children and adolescents was associated with a higher incidence of hematologic malignant neoplasms. • The incidence rate of hematologic malignant neoplasms in the CT-exposed group was 29% higher than that in the CT-unexposed group (IRR, 1.29 [95% CI, 1.03-1.60]), and there were approximately 1.7 excess neoplasms per 100,000 person-years at risk in the CT-exposed group (IRD, 1.71 [0.04-3.37]). • Our study provides a quantified grasp of the risk conferred by CT examinations in children and adolescents, while controlling for biases observed in previous studies via specifying CT indication and excluding patients with predisposing conditions for cancer development.

Abstract TMP80: Hematoma Radiomic Markers of Survival After Supratentorial Intracerebral Hemorrhage on Admission Non-Contrast Head CT

Background: Radiomic features provide quantitative information about lesions morphology and texture on medical images. Recent studies have shown that intracerebral hemorrhage (ICH) radiomics on admission non-contrast head CT are associated with severity of symptoms at baseline and clinical outcomes - providing prognostic information beyond hematoma volume. In this study, we determined hematoma radiomic markers of post-ICH survival on admission head CT. Methods: Using the ATACH-2 trial dataset, we manually segmented ICH on admission head CTs and extracted 1130 radiomic features. Univariate and multivariate survival analyses were performed using the Cox Proportional Hazards model, Kaplan Meier Analysis, and logistic regression. Results: We split our dataset (n=871) to training (n=580) and testing (n=291) cohorts. Increased “original first order Energy” radiomic feature was associated with a higher probability of death (Hazard Ratio=1.64, p &lt;0.0001). LASSO Cox Proportional Hazards modeling also identified “original first order Energy” alongside age, NIHSS, and baseline INR as significant predictors of death. The ROC analysis confirmed the prognostic capability of this feature at 7 days, 30 days, and 90 days post-ICH in training and test cohorts. Kaplan Meier analysis demonstrated that increased “original first order Energy” is associated with a higher probability of death (p &lt; 0.05 at all time points). Logistic regression also showed that this feature is an independent predictor of post-ICH mortality (Odds ratios=2.04, p &lt; 0.001). Conclusions: The “original first order Energy” radiomic feature of hematoma on admission non-contrast head CT scans is a main predictor of survival in supratentorial ICH. This radiomic feature represents the magnitude of voxel values confounded with lesion volume - i.e. brighter larger hematomas on head CT have higher " original first order Energy ", and are associated with higher mortality rates after supratentorial ICH.

Abstract TMP84: Multi-Institutional Validation of an Automated Segmentation Tool for Intracerebral Hemorrhage (ICH) and Peri-Hematomal Edema (PHE) on Head CT

Objective: In patients with acute intracerebral hemorrhage (ICH), the volume of hemorrhage, and perihematomal edema (PHE) are representative of primary, and secondary brain injury, respectively. Automated quantification of ICH and PHE volumes from admission non-contrast head CT can facilitate evaluation of large stroke datasets, and expedite treatment triage when volume cutoffs are applied. We aimed to train and externally validate an automated model for segmentation and quantification of ICH and PHE volumes on non-contrast head CT scans. Methods: For training of the model, we used the data from multicentric ATACH-2 clinical trial with head CTs from eleven medical institutes in six countries. The model was then exported and tested on two external datasets from Yale and University of Berlin. We designed an automated pipeline for extracting brain window from 3D non-contrast head CT, skull stripping, resampling to homogenous voxel size, and segmentation. For segmentation we applied a deep learning model based on 3D full resolution nnUNet. We used the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and Volume Similarity (VS) between automated segmentation and ground truth manual segmentation volumes to evaluate the models’ performance. Results: A total of 854 patients from the ATACH-2 trial (854 х2, baseline and follow-up CT scans) were used for training of the model in 5-fold cross-validation. In validation folds, the model achieved a mean DSC=0.90±0.10, HD =1.42±16.0mm, and VS=0.95±0.10 for ICH; and DSC=0.74±0.12, HD =3.0±16.5 mm, and VS=0.91±0.12 for PHE. In the externaltesting cohort from Yale (200 patients х2, baseline and follow-up CT scans), the model archieved median DSC=0.93, HD=0.98 mm, and VS=0.97 for ICH; and median DSC=0.69, HD=4.52 mm, and VS=0.84 for PHE. In the externaltesting cohort from Charité Hospital, University of Berlin (915 baseline CT scans), the model archived median DSC=0.87, HD=4 mm, and VS=0.90 for ICH; and median DSC=0.65, HD=5 mm, VS=0.85 for PHE. Conclusion: We trained, validated, and externally tested an end-to-end automated tool for segmentation of both ICH and PHE on non-contrast head CT. Such tool can facilitate treatment triage for trials when volume cutoffs are applied for enrollment.

Evaluation of Spectral X-Ray Imaging for Panoramic Dental Images Based on a Simulation Framework.

Modern photon counting detectors allow the calculation of virtual monoenergetic or material decomposed X-ray images but are not yet used for dental panoramic radiography systems. To assess the diagnostic potential and image quality of photon counting detectors in dental panoramic radiography, ethics approval from the local ethics committee was obtained for this retrospective study. Conventional CT scans of the head and neck region were segmented into bone and soft tissue. The resulting datasets were used to calculate panoramic equivalent thickness bone and soft tissue images by forward projection, using a geometry like that of conventional panoramic radiographic systems. The panoramic equivalent thickness images were utilized to generate synthetic conventional panoramic radiographs and panoramic virtual monoenergetic radiographs at various energies. The conventional, two virtual monoenergetic images at 40keV and 60keV, and material-separated bone and soft tissue panoramic equivalent thickness X-ray images simulated from 17 head CTs were evaluated in a reader study involving three experienced radiologists regarding their diagnostic value and image quality. Compared to conventional panoramic radiographs, the material-separated bone panoramic equivalent thickness image exhibits a higher image quality and diagnostic value in assessing the bone structure and details such as teeth or root canals . Panoramic virtual monoenergetic radiographs do not show a significant advantage over conventional panoramic radiographs. The conducted reader study shows the potential of spectral X-ray imaging for dental panoramic imaging to improve the diagnostic value and image quality.

Radiological Findings in Patients Presenting with Brief Resolved Unexplained Events (BRUEs)

Background/Hypothesis: Brief resolved unexplained events (BRUEs) are events in infants characterized by cyanosis, abnormal breathing, abnormal tone, and altered responsiveness. Practice guidelines define high-risk and low-risk BRUEs and do not recommend imaging in low-risk patients. We evaluated imaging in these patients and hypothesized that high-risk patients would have more imaging studies and abnormalities.&#x0D; Methods: Using the radiology information system, a retrospective review was performed between 2016-2022 for patients &lt;1 year presenting with BRUE. Defined search terms were used to identify imaging within one week of presentation. Patients were evaluated for clinical presentation, medical history, physical examination, imaging studies ordered, and final diagnoses.&#x0D; Results: 126 patients were identified. 113 patients (46 female; 93 high-risk), between 3 and 355 days old (average age 97 days), met inclusion criteria. Imaging included chest radiographs (99), head CTs (24), brain MRIs (19), skeletal surveys (16), and others (22). There was no difference in the number of imaging studies obtained between these groups (p=0.423, Mann-Whitney U test). However, a greater proportion of high-risk patients had imaging abnormalities (p=0.023, Fisher’s exact test). Only 1/20 (5%) low-risk patients had abnormal imaging (PCR proven viral bronchiolitis). 26/93 (28%) high-risk patients had abnormal findings, most commonly on chestradiographs (15), brain MRIs (9), head CTs (4), and skeletal surveys (3). 18/26 high-risk patients had imaging abnormalities leading to a diagnosis other than BRUE (viral bronchiolitis, bronchopulmonary dysplasia, nonaccidental trauma, perinatal HSV infection, ventricular septal defect, double aortic arch, intestinal malrotation, and neurofibromatosis). Overall, 7/93 (7.5%) high-risk BRUE patients had significant pathology.&#x0D; Conclusion: High-risk patients were more likely to have an imaging abnormality compared to low-risk patients, which is consistent with current imaging recommendations given only one low-risk imaging abnormality. Interestingly, 7.5% of the high-risk patients had significant pathology diagnosed by imaging.

Follow-up ASPECTS improves prediction of potentially lethal malignant edema in patients with large middle cerebral artery stroke

BackgroundRecent studies have shown that follow-up head CT is a strong predictor of functional outcomes in patients with middle cerebral artery stroke and mechanical thrombectomy. We sought to determine whether...

Brain Reserve Score on Acute Trauma Head CT is Correlated with Pre‐TBI MCI/Dementia and is an Independent Predictor of Post‐TBI Cognitive Outcome

AbstractBackgroundPre‐injury brain reserve may contribute to the substantial heterogeneity observed in cognitive outcome after mild traumatic brain injury (mTBI), including risk for cognitive decline and dementia. However, no tools exist to quantify pre‐injury brain reserve in an acute trauma setting, thereby limiting research. We aimed to develop and validate a visually‐rated Brain Reserve Score (BRS) to quantify baseline brain reserve on head CTs obtained to rule out intracranial trauma in adults presenting acutely with mTBI.MethodsData are from the Transforming Research And Clinical Knowledge in Traumatic Brain Injury (TRACK‐TBI) and TRACK‐Geriatric TBI (TRACK‐GERI) studies, multi‐center prospective cohort studies of adults age 18+ presenting within 24 hours (TRACK‐TBI) or adults age 65y+ presenting within 72 hours (TRACK‐GERI) of TBI who received head CT and multi‐domain clinical follow‐up for one year. BRS was developed by adapting existing MRI visual rating scales of global cortical atrophy, hippocampal atrophy, and white matter change for use in trauma head CTs and then by refining the scoring guide to optimize rater reliability. To establish concurrent validity, we assessed correlation of BRS with pre‐injury cognitive status (measured in TRACK‐GERI using informant‐reported Clinical Dementia Rating interviews). To establish predictive validity, we assessed association of BRS with good versus poor 12‐month cognitive outcome in TRACK‐TBI using logistic regression adjusted for baseline demographics, medical/psychiatric comorbidities, injury characteristics, and trauma severity on CT.ResultsFinal BRS score ranged from 0‐10 (10 is highest burden of neuropathology); inter‐ and intra‐rater reliability were moderate‐substantial (weighted kappa 0.54‐0.80). Among N = 100 TRACK‐GERI participants BRS was significantly correlated with pre‐injury CDR (r = 0.37, p&lt;0.01). Among N = 656 TRACK‐TBI participants, BRS of 6+ was independently associated with poor 12‐month cognitive outcome (fully adjusted odds ratio 4.35, 95% confidence interval 1.35‐13.99, p = 0.01).ConclusionBRS is a reliable visually rated score of brain reserve on acute trauma head CT that correlates with pre‐injury cognitive status and independently predicts poor cognitive outcome one year post‐mTBI. BRS may be a useful tool to facilitate inclusion of older adults in acute TBI research thereby advancing clinical care and research on mechanisms of accelerated post‐TBI cognitive decline and dementia.

Study the variations in radiation doses in different multi-slice CT scan machines

Objectives: This study aimed to measure variations in dose output and patient’s effective dose across the different computed tomography scanners during standard CT examinations of head, chest and abdomen, so as to determine patient, and machine settings that contribute to variations in radiation dose to optimize patient effective dose. Methods: Retrospective, study performed in different hospitals, in Najran province (K.S.A) from October 2022 to June 2023. The study comprise 360 adults CT examinations. The mean values of CT dose index volume (CTDIvol) and dose length product (DLP) were measured. The patient effective dose (ED) were calculated for each protocol and compared among different CT scanners. Results: The mean values of CTDIvol , DLP, and ED, varied across the different CT scanners, Regarding abdomen CT, the CTDIvol mean values were (5.56 mGy to 18.655 mGy) , the DLP (289.78 to 968.241 mGy/cm), and mean effective doses were (4.34 to 14.5 mSv), in chest CTs the mean values of CTDIvol were (5.05 to 14.39mGy), the DLP were (202.84 to 499.098mGy/cm), and median effective doses were (2.85 to 6.97 mSv), in head CTs the mean values of CTDIvol were (42.4to 68.278mGy), the DLP were (781 to 1209.18mGy/cm), and effective doses were (1.636 to 2.528mSv). Conclusion: Regarding selected exams, CTDI, DLP and ED were found to be varied from low variations in head CT scan, to medium in chest CT scan and high variation in abdomen CTs among different CT scanners, The highest values of CTDI and DLP were noted in head CTs followed by abdomen, and the lowest were in chest CTs. The most factors affected the CT dose variations were the technical parameters settings, mainly the number of slices, however the scanner specifications reported some impact. Optimizing dose to a reliable standard for each anatomical part should be adjusting independently by each department according to the scanner characteristics, settings and patient factors.

Enhancing hospital course and outcome prediction in patients with traumatic brain injury: A machine learning study.

We aimed to use machine learning (ML) algorithms with clinical, lab, and imaging data as input to predict various outcomes in traumatic brain injury (TBI) patients. In this retrospective study, blood samples were analyzed for glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase L1 (UCH-L1). The non-contrast head CTs were reviewed by two neuroradiologists for TBI common data elements (CDE). Three outcomes were designed to predict: discharged or admitted for further management (prediction 1), deceased or not deceased (prediction 2), and admission only, prolonged stay, or neurosurgery performed (prediction 3). Five ML models were trained. SHapley Additive exPlanations (SHAP) analyses were used to assess the relative significance of variables. Four hundred forty patients were used to predict predictions 1 and 2, while 271 patients were used in prediction 3. Due to Prediction 3's hospitalization requirement, deceased and discharged patients could not be utilized. The Random Forest model achieved an average accuracy of 1.00 for prediction 1 and an accuracy of 0.99 for prediction 2. The Random Forest model achieved a mean accuracy of 0.93 for prediction 3. Key features were extracranial injury, hemorrhage, UCH-L1 for prediction 1; TheGlasgow Coma Scale, age, GFAP for prediction 2; and GFAP, subdural hemorrhage volume, and pneumocephalus for prediction 3, per SHAP analysis. Combining clinical and laboratory parameters with non-contrast CT CDEs allowed our ML models to accurately predict the designed outcomes of TBI patients. GFAP and UCH-L1 were among the significant predictor variables, demonstrating the importance of these biomarkers.

Adherence to the Canadian CT Head Rule in a Nova Scotian Emergency and Trauma Center.

Background and aims Choosing Wisely Nova Scotia (CWNS), an affiliate of Choosing Wisely Canada (CWC), aims to address unnecessary care and tests through literature-informed lists developed by various disciplines. CWC has identified unnecessary head CTs among the top five tests, procedures, and treatments to question within the emergency department setting. The Canadian CT-scan Head Rule (CCHR) has been found to be the most effective clinical decision rule in adults with minor head injuries. This study aimed to better understand the current status of CCHR use in Nova Scotia, we conducted a retrospective audit of patient charts at the Charles V. Keating Emergency and Trauma Center in Halifax, Nova Scotia. Materials and methods Our mixed methods design included a narrative literature review, a retrospective chart audit, and a qualitative audit-feedback component with physicians who work in the emergency department (ED). The chart audit applied the guidelines for adherence to the CCHR and reported on the level of compliance within the ED. Results Analysis of qualitative data is included here, in parallel with in-depth analysis to contextualize findings from the chart audit. A total of 302 charts of patients presenting to the surveyed site were retrospectively reviewed for this study. Of the 37 cases where the CT head was indicated as per the CCHR, a CT was ordered 32 (86.5%) times. Of the 176 cases where a CT head was not indicated as per the CCHR, a CT was not ordered 155 (88.1%) times. Therefore, the CCHR was followed in 187 (87.8%) of the total 213 cases where the CCHR should be applied. Conclusions Our review revealed that the CCHR was adhered in 87.8% of cases at the surveyed ED. Identifying contextual factors that facilitate or hinder the application of CCHR in practice is critical to achieving the goal of reducing unnecessary CTs. This work will be presented to the physician group to engage and understand factors that are enablers in the process of ED minor head injury care.

PO-1649 Style-based generative model to reconstruct head and neck 3D CTs

PO-1649 Style-based generative model to reconstruct head and neck 3D CTs

Neuroaspergillosis: Challenging Diagnosis and Management (P10-10.002)

<h3>Objective:</h3> N/A <h3>Background:</h3> Invasive fungal infections are associated with increased morbidity and mortality among immunocompromised patients, particularly due to non-specific symptoms, difficulty and delay in diagnosis, and limited therapeutic options. Aspergillosis is the leading cause of invasive fungal infections. Neuroaspergillosis commonly arises from hematogenous dissemination from invasive lung infection in immunocompromised patients and can lead to brain abscess, meningitis, and stroke from angioinvasion. Cerebral aspergillosis has a poor prognosis. <h3>Design/Methods:</h3> N/A <h3>Results:</h3> A 62-year-old man with history of chronic lymphocytic leukemia and SARS-CoV-2 pneumonia presented with acute onset right-sided weakness. Head CT exhibited bilateral hypodensities concerning for emboli or metastases. Brain MRI revealed numerous bihemispheric T2 hyperintensities with vasogenic edema. Some lesions demonstrated restricted diffusion and contrast enhancement. At this point, differential diagnosis included septic emboli, abscess, and metastatic disease. TTE did not show signs of infective endocarditis. CT of the chest, abdomen, and pelvis revealed an irregular, centrally necrotic opacity. Bronchoscopy with bronchial lavage was performed, and biopsies were negative for malignancy and positive for Aspergillus species. The patient was started on amphotericin and was switched to voriconazole due to poor tolerance. Because of mental status fluctuation caused by edema, glucocorticoids were used concurrently with antifungal treatment. He had serial head CTs which initially revealed increasing edema and increasing effacement of the left lateral ventricle and third ventricle with development of early hydrocephalus. Neurosurgery was consulted, and family declined any surgical intervention. He was managed with dexamethasone 4 mg daily, and he demonstrated improvement in symptoms and edema on imaging in 1 week. <h3>Conclusions:</h3> In immunocompromised patients found to have multiple brain enhancing lesions with unrevealing preliminary work-up, invasive <i>Aspergillosis</i> infection must be considered. Here, we present a case of aspergillus managed concurrently with steroids and voriconazole. Despite the infectious source, there appears to be a role for steroids in the management of neuroaspergillosis. <b>Disclosure:</b> Dr. Jaworski has nothing to disclose. Dr. Reyes has nothing to disclose. Dr. Yacoub has nothing to disclose.

Emergency Department Treatment of Alcohol-Related Seizures: A Retrospective Chart Review (P12-1.008)

<h3>Objective:</h3> To critically analyze the management of alcohol-related seizures including alcohol withdrawal (AW) and alcohol-induced (AI) presentations. <h3>Background:</h3> Although alcohol related seizures are common, there remains considerable difficulty in differentiating seizure etiologies among alcohol users which in turn complicates clinical decision making. <h3>Design/Methods:</h3> Between June and December 2018, 558 ED seizure visits at three urban emergency departments were reviewed to capture all alcohol-related seizures. Data was collected on patient demographics, seizure history, treatments, diagnostics, and discharge information. Data was categorized into three groups: AW (seizure &gt; 24 hours from last drink), AI (alcohol used within 24 hours), and a non-alcohol related seizure control (SC) group. Functional seizure encounters were excluded. Chi square analysis was performed with a significance level of p &lt;0.05. <h3>Results:</h3> We identified 53 AW, 60 AI, and 445 SC encounters with similar racial make-up and median age. The AW group had significantly less home anti-seizure medication (ASM) than the AI and SC groups (p &lt;0.001) and were less likely to be given an ASM in the ED (p &lt;0.001). Less ASMs were prescribed on discharge to the AI (p &lt;0.02) and AW groups (p &lt;0.001) than SC. AW group received more head CTs compared to SC (p &lt;0.02) despite similar rates of head trauma. AW had more benzodiazepines given in the ED (p &lt;0.001), inpatient admissions (p &lt;0.006), and ICU admissions (p &lt;0.001) than SC. AI group returned to the ED with seizures more often compared to SC (p &lt;0.03). <h3>Conclusions:</h3> Despite AI presenting more often with recurrent seizures, they were less likely to receive ASM treatments on discharge. AW seizures were more likely to have a head CT despite no increased history of head trauma. Larger studies are needed to determine risk factors for recurrent alcohol-related seizures to reduce ED visits and determine appropriate treatments. <b>Disclosure:</b> Mr. Hijazi has nothing to disclose. Ms. Sukkarieh has nothing to disclose. Dr. Tetarbe has nothing to disclose. Dr. Aravind has nothing to disclose. Dr. Basha has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Eisai. Dr. Zutshi has nothing to disclose.