Non-contrast Head CT Research Articles

Intra-arterial contrast administration: a confounding appearance on stroke CT imaging.

A female patient in her 70s presented with mild slurred speech. Clinical assessment revealed only minor dysarthria. A stroke protocol CT study was performed comprising a non-contrast CT head, CT angiogram (CTA) and CT perfusion (CTP) imaging. Despite a normal non-contrast CT head, CTP imaging demonstrated a large left anterior circulation territory abnormality compatible with core infarct. The CTA displayed absent left middle cerebral artery opacification and an abnormal pattern of thalamic and posterior fossa structure enhancement. Following a neuroradiology review, it was identified that the contrast bolus had been administered into the right brachial artery causing direct arterial opacification of the right vertebral/carotid arteries and their distal branches. No contrast was present in the left carotids or distal left intracranial anterior circulation giving the false impression of a large vessel occlusion. The patient was subsequently discharged without receiving inappropriate reperfusion therapy. This case highlights the role of technical factors influencing CT interpretation, particularly when performed by artificial intelligence/automated analysis.

Dual Energy CT for Deep Learning-Based Segmentation and Volumetric Estimation of Early Ischemic Infarcts.

Ischemic changes are not visible on non-contrast head CT until several hours after infarction, though deep convolutional neural networks have shown promise in the detection of subtle imaging findings. This study aims to assess if dual-energy CT (DECT) acquisition can improve early infarct visibility for machine learning. The retrospective dataset consisted of 330 DECTs acquired up to 48h prior to confirmation of a DWI positive infarct on MRI between 2016 and 2022. Infarct segmentation maps were generated from the MRI and co-registered to the CT to serve as ground truth for segmentation. A self-configuring 3D nnU-Net was trained for segmentation on (1) standard 120kV mixed-images (2) 190keV virtual monochromatic images and (3) 120kV + 190keV images as dual channel inputs. Algorithm performance was assessed with Dice scores with paired t-tests on a test set. Global aggregate Dice scores were 0.616, 0.645, and 0.665 for standard 120kV images, 190keV, and combined channel inputs respectively. Differences in overall Dice scores were statistically significant with highest performance for combined channel inputs (p < 0.01). Small but statistically significant differences were observed for infarcts between 6 and 12h from last-known-well with higher performance for larger infarcts. Volumetric accuracy trended higher with combined inputs but differences were not statistically significant (p = 0.07). Supplementation of standard head CT images with dual-energy data provides earlier and more accurate segmentation of infarcts for machine learning particularly between 6 and 12h after last-known-well.

Vertigo as Initial Symptom of Cerebellar Hemorrhage in Adult Woman : A Case Report

Vertigo, difficulty walking, and loss of balance/coordination are among the symptoms of stroke in 50% of stroke cases. Vertigo due to cerebrovascular disease is generally associated with other neurological signs such as cranial nerve abnormalities, hemiparesis, facial weakness, diplopia, hyperesthesia, and Horner's syndrome. A 42-year-old woman came to the emergency department with complaints of dizziness, nausea, and frequent vomiting for the previous 4 hours. The symptoms are also accompanied by a feeling of tingling on the left side of the face, and the left eyelid cannot open optimally. The patient has a history of uncontrolled hypertension. The HINTS test revealed central vertigo, and the patient also found dysdiadochokinesis, ataxia, and dysmethria. A non-contrast head CT scan showed ICH in the left cerebellum with a volume of 6.9 cc. Based on the results of these examinations, the patient was diagnosed with cerebellar hemorrhage. The blood supply to the brainstem, cerebellum, and inner ear comes from the vertebrobasilar vascular system. Blockage or rupture of blood vessels in one of the main branches of this system can cause symptoms of vertigo. Symptoms of vertebrobasilar stroke vary widely and depend on which of the three main circumferential branches is affected; posterior inferior cerebellar artery, anterior inferior cerebellar artery, or superior cerebellar artery. Vertigo in patients who have risk factors for stroke accompanied by other neurological symptoms should be considered for a thorough neurological examination to evaluate the possibility of cerebrovascular disease.

Longitudinal changes in the US emergency department use of advanced neuroimaging in the mechanical thrombectomy era.

To describe ED neuroimaging trends across the time-period spanning the early adoption of endovascular therapy for acute stroke (2013-2018). We performed a retrospective, cross-sectional study of ED visits using the 2013-2018 National Emergency Department Sample, a 20% sample of ED encounters in the United States. Neuroimaging use was determined by Common Procedural Terminology (CPT) code for non-contrast head CT (NCCT), CT angiography head (CTA), CT perfusion (CTP), and MRI brain (MRI) in non-admitted ED patients. Data was analyzed according to sampling weights and imaging rates were calculated per 100,000 ED visits. Multivariate logistic regression analysis was performed to identify hospital-level factors associated with imaging utilization. Study population comprised 571,935,906 weighted adult ED encounters. Image utilization increased between 2013 and 2018 for all modalities studied, although more pronounced in CTA (80.24/100,000 ED visits to 448.26/100,000 ED visits (p < 0.001)) and CTP (1.75/100,000 ED visits to 28.04/100,000 ED visits p < 0.001)). Regression analysis revealed that teaching hospitals were associated with higher odds of high CTA utilization (OR 1.88 for 2018, p < 0.05), while low-volume EDs and public hospitals showed the reverse (OR 0.39 in 2018, p < 0.05). We identified substantial increases in overall neuroimaging use in a national sample of non-admitted emergency department encounters between 2013 and 2018 with variability in utilization according to both patient and hospital properties. Further investigation into the appropriateness of this imaging is required to ensure that access to acute stroke treatment is balanced against the timing and cost of over-imaging.

Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.

Background: Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation. Objective: To evaluate the impact on radiologists' real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department's implementation of an AI triage and notification system for ICH detection on head NCCT examinations. Methods: This prospective single-center study included adult patients who underwent head NCCT examinations from May 12, 2021 to June 30, 2021 (phase 1) or September 30, 2021 to December 4, 2021 (phase 2). Before phase 1, the radiology department implemented a commercial AI triage system for ICH detection that processed head NCCT examinations and notified radiologists of positive results through a widget with a floating pop-up display. Examinations were interpreted by neuroradiologists or emergency radiologists, who evaluated examinations without and with AI assistance in phase 1 and phase 2, respectively. A panel of radiologists conducted a review process for all examinations with discordance between the radiology report and AI and a subset of remaining examinations, to establish the reference standard. Diagnostic performance and report turnaround times were compared using Pearson chi-square test and Wilcoxon rank-sum test, respectively. Bonferroni correction was used to account for five diagnostic performance metrics (adjusted significance threshold, .01 [α=.05/5]). Results: A total of 9954 examinations from 7371 patients (mean age, 54.8±19.8 years; 3773 female, 3598 male) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (P=.01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 99.7%), or NPV (99.7% vs 99.7%) (all P>.01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, P=.004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (P=.11). Conclusion: An AI triage system for ICH detection did not improve radiologists' diagnostic performance or report turnaround times. Clinical Impact: This large prospective real-world study does not support use of AI assistance for ICH detection.

Precise Image-level Localization of Intracranial Hemorrhage on Head CT Scans with Deep Learning Models Trained on Study-level Labels.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a highly generalizable weakly supervised model to automatically detect and localize image- level intracranial hemorrhage (ICH) using study-level labels. Materials and Methods In this retrospective study, the proposed model was pretrained on the image-level RSNA dataset and fine-tuned on a local dataset using attention-based bidirectional long-short-term memory networks. This local training dataset included 10,699 noncontrast head CT scans from 7469 patients with ICH study-level labels extracted from radiology reports. Model performance was compared with that of two senior neuroradiologists on 100 random test scans using the McNemar test, and its generalizability was evaluated on an external independent dataset. Results The model achieved a positive predictive value (PPV) of 85.7% (95% CI: [84.0%, 87.4%]) and an AUC of 0.96 (95% CI: [0.96, 0.97]) on the held-out local test set (n = 7243, 3721 female) and 89.3% (95% CI: [87.8%, 90.7%]) and 0.96 (95% CI: [0.96, 0.97]), respectively, on the external test set (n = 491, 178 female). For 100 randomly selected samples, the model achieved performance on par with two neuroradiologists, but with a significantly faster (P < .05) diagnostic time of 5.04 seconds per scan (versus 86 seconds and 22.2 seconds for the two neuroradiologists, respectively). The model's attention weights and heatmaps visually aligned with neuroradiologists' interpretations. Conclusion The proposed model demonstrated high generalizability and high PPVs, offering a valuable tool for expedited ICH detection and prioritization while reducing false-positive interruptions in radiologists' workflows. ©RSNA, 2024.

Abbreviated MRI in the evaluation of dizziness: report turnaround times and impact on length of stay compared to CT, CTA, and conventional MRI.

Neuroimaging is often used in the emergency department (ED) to evaluate for posterior circulation strokes in patients with dizziness, commonly with CT/CTA due to speed and availability. Although MRI offers more sensitive evaluation, it is less commonly used, in part due to slower turnaround times. We assess the potential for abbreviated MRI to improve reporting times and impact on length of stay (LOS) compared to conventional MRI (as well as CT/CTA) in the evaluation of acute dizziness. We performed a retrospective analysis of length of stay via LASSO regression for patients presenting to the ED with dizziness and discharged directly from the ED over 4 years (1/1/2018-12/31/2021), controlling for numerous patient-level and logistical factors. We additionally assessed turnaround time between order and final report for various imaging modalities. 14,204 patients were included in our analysis. Turnaround time for abbreviated MRI was significantly lower than for conventional MRI (4.40h vs. 6.14h, p < 0.001) with decreased impact on LOS (0.58h vs. 2.02h). Abbreviated MRI studies had longer turnaround time (4.40h vs. 1.41h, p < 0.001) and was associated with greater impact on ED LOS than non-contrast CT head (0.58h vs. 0.00h), however there was no significant difference in turnaround time compared to CTA head and neck (4.40h vs. 3.86h, p = 0.06) with similar effect on LOS (0.58h vs. 0.53h). Ordering both CTA and conventional MRI was associated with a greater-than-linear increase in LOS (additional 0.37h); the same trend was not seen combining CTA and abbreviated MRI (additional 0.00h). In the acute settings where MRI is available, abbreviated MRI protocols may improve turnaround times and LOS compared to conventional MRI protocols. Since recent guidelines recommend MRI over CT in the evaluation of dizziness, implementation of abbreviated MRI protocols has the potential to facilitate rapid access to preferred imaging, while minimizing impact on ED workflows.

Sociodemographic biases in a commercial AI model for intracranial hemorrhage detection.

To evaluate whether a commercial AI tool for intracranial hemorrhage (ICH) detection on head CT exhibited sociodemographic biases. Our retrospective study reviewed 9736 consecutive, adult non-contrast head CT scans performed between November 2021 and February 2022 in a single healthcare system. Each CT scan was evaluated by a commercial ICH AI tool and a board-certified neuroradiologist; ground truth was defined as final radiologist determination of ICH presence/absence. After evaluating the AI tool's aggregate diagnostic performance, sub-analyses based on sociodemographic groups (age, sex, race, ethnicity, insurance status, and Area of Deprivation Index [ADI] scores) assessed for biases. χ2 test or Fisher's exact tests evaluated for statistical significance with p ≤ 0.05. Our patient population was 50% female (mean age 60 ± 19 years). The AI tool had an aggregate accuracy of 93% [9060/9736], sensitivity of 85% [1140/1338], specificity of 94% [7920/ 8398], positive predictive value (PPV) of 71% [1140/1618] and negative predictive value (NPV) of 98% [7920/8118]. Sociodemographic biases were identified, including lower PPV for patients who were females (67.3% [62,441/656] vs. 72.7% [699/962], p = 0.02), Black (66.7% [454/681] vs. 73.2% [686/937], p = 0.005), non-Hispanic/non-Latino (69.7% [1038/1490] vs. 95.4% [417/437]), p = 0.009), and who had Medicaid/Medicare (69.9% [754/1078]) or Private (66.5% [228/343]) primary insurance (p = 0.003). Lower sensitivity was seen for patients in the third quartile of national (78.8% [241/306], p = 0.001) and state ADI scores (79.0% [22/287], p = 0.001). In our healthcare system, a commercial AI tool had lower performance for ICH detection than previously reported and demonstrated several sociodemographic biases.

VASCULAR PARKINSONISM WITH EARLY COGNITIVE IMPAIRMENT: A CASE REPORT AND LITERATURE REVIEW

Cerebral venous sinus thrombosis (CVST) is an uncommon condition of cerebral venous sinus thrombosis with a varied clinical presentation that can be diagnostically challenging. Intravenous heparin is the optimal immediate anticoagulant according to the European Academy of Neurology (EAN) guideline 2017. This report aims to describe highly suspicious CVST clinical features and suggest a diagnostic algorithm based on two cases of CVST found in our center. The first case is a 52-year-old man who presented with serial seizures preceded by subacute headache and diparesis. Non-contrast head CT (NCCT) showed multifocal haemorrhages and cord signs. The second case is a 19-year-old woman who presented with slowly decreased consciousness, headache, and a history of upper respiratory infection. Diffuse cerebral edema was revealed in NCCT. Both of these patients had thrombosis in superior sagittal sinus, right transverse, and sigmoid sinus. Heparinization was conducted and continued with rivaroxaban with a good response. CVST is rare case and often unrecognized; since it has serious complications, early diagnosis and treatment improve prognosis and survival.

Upfront vascular imaging in acute stroke: Impact on thrombectomy transfer time at a primary stroke center

ObjectivesEarly cerebral arterial imaging is currently only recommended in the subgroup of acute ischemic stroke (AIS) patients suspected of having large vessel occlusion (LVO). There is limited data on the impact of early cerebrovascular imaging in all suspected AIS patients presenting within 24 h of symptom onset and the impact on door in-door out (DIDO) time. Materials and methodsIn January 2020, our Primary Stroke Center implemented a protocol to perform upfront head and neck CT angiography (CTA) with initial non-contrast CT head for all suspected ischemic stroke patients screening positive for BE-FAST stroke symptoms within 24 h from last known normal time. We retrospectively reviewed IV alteplase and thrombectomy-eligible patients before (January 1-December 31, 2019) and after protocol implementation (January 1, 2020-June 30, 2022). ResultsOf 86 patients meeting study criteria, up-front CTA was associated with significant reductions in door-to-CTA start (median 37 vs 15 min, p = 0.003), door-to-CTA result (median 83 vs 52 min, p = 0.023) and DIDO times (median 150 vs 106 min, p = 0.023). There was no significant difference in door-to-needle time before and after protocol implementation (median 48 vs 43 min, p = 0.450). ConclusionUp-front cerebrovascular imaging with CTA in suspected AIS patients presenting within 24 h resulted in shorter DIDO times without delaying door-to-needle times. Primary Stroke Centers should consider this approach to detect LVO early and expedite patient transport to thrombectomy capable centers.

Assessing the effectiveness of artificial intelligence (AI) in prioritising CT head interpretation: study protocol for a stepped-wedge cluster randomised trial (ACCEPT-AI)

IntroductionDiagnostic imaging is vital in emergency departments (EDs). Accessibility and reporting impacts ED workflow and patient care. With radiology workforce shortages, reporting capacity is limited, leading to image interpretation delays....

Evaluation of an Artificial Intelligence Model for Identification of Mass Effect and Vasogenic Edema on CT of the Head.

Mass effect and vasogenic edema are critical findings on CT of the head. This study compared the accuracy of an artificial intelligence model (Annalise Enterprise CTB) with consensus neuroradiologists' interpretations in detecting mass effect and vasogenic edema. A retrospective stand-alone performance assessment was conducted on data sets of noncontrast CT head cases acquired between 2016 and 2022 for each finding. The cases were obtained from patients 18 years of age or older from 5 hospitals in the United States. The positive cases were selected consecutively on the basis of the original clinical reports using natural language processing and manual confirmation. The negative cases were selected by taking the next negative case acquired from the same CT scanner after positive cases. Each case was interpreted independently by up-to-three neuroradiologists to establish consensus interpretations. Each case was then interpreted by the artificial intelligence model for the presence of the relevant finding. The neuroradiologists were provided with the entire CT study. The artificial intelligence model separately received thin (≤1.5 mm) and/or thick (>1.5 and ≤5 mm) axial series. The 2 cohorts included 818 cases for mass effect and 310 cases for vasogenic edema. The artificial intelligence model identified mass effect with a sensitivity of 96.6% (95% CI, 94.9%-98.2%) and a specificity of 89.8% (95% CI, 84.7%-94.2%) for the thin series, and 95.3% (95% CI, 93.5%-96.8%) and 93.1% (95% CI, 89.1%-96.6%) for the thick series. It identified vasogenic edema with a sensitivity of 90.2% (95% CI, 82.0%-96.7%) and a specificity of 93.5% (95% CI, 88.9%-97.2%) for the thin series, and 90.0% (95% CI, 84.0%-96.0%) and 95.5% (95% CI, 92.5%-98.0%) for the thick series. The corresponding areas under the curve were at least 0.980. The assessed artificial intelligence model accurately identified mass effect and vasogenic edema in this CT data set. It could assist the clinical workflow by prioritizing interpretation of cases with abnormal findings, possibly benefiting patients through earlier identification and subsequent treatment.

Radiomic Features of Acute Cerebral Hemorrhage on Non-Contrast CT Associated with Patient Survival.

The mortality rate of acute intracerebral hemorrhage (ICH) can reach up to 40%. Although the radiomics of ICH have been linked to hematoma expansion and outcomes, no research to date has explored their correlation with mortality. In this study, we determined the admission non-contrast head CT radiomic correlates of survival in supratentorial ICH, using the Antihypertensive Treatment of Acute Cerebral Hemorrhage II (ATACH-II) trial dataset. We extracted 107 original radiomic features from n = 871 admission non-contrast head CT scans. The Cox Proportional Hazards model, Kaplan-Meier Analysis, and logistic regression were used to analyze survival. In our analysis, the "first-order energy" radiomics feature, a metric that quantifies the sum of squared voxel intensities within a region of interest in medical images, emerged as an independent predictor of higher mortality risk (Hazard Ratio of 1.64, p < 0.0001), alongside age, National Institutes of Health Stroke Scale (NIHSS), and baseline International Normalized Ratio (INR). Using a Receiver Operating Characteristic (ROC) analysis, "the first-order energy" was a predictor of mortality at 1-week, 1-month, and 3-month post-ICH (all p < 0.0001), with Area Under the Curves (AUC) of >0.67. Our findings highlight the potential role of admission CT radiomics in predicting ICH survival, specifically, a higher "first-order energy" or very bright hematomas are associated with worse survival outcomes.

Automatic segmentation of hemorrhagic transformation on follow-up non-contrast CT after acute ischemic stroke.

Hemorrhagic transformation (HT) following reperfusion therapies is a serious complication for patients with acute ischemic stroke. Segmentation and quantification of hemorrhage provides critical insights into patients' condition and aids in prognosis. This study aims to automatically segment hemorrhagic regions on follow-up non-contrast head CT (NCCT) for stroke patients treated with endovascular thrombectomy (EVT). Patient data were collected from 10 stroke centers across two countries. We propose a semi-automated approach with adaptive thresholding methods, eliminating the need for extensive training data and reducing computational demands. We used Dice Similarity Coefficient (DSC) and Lin's Concordance Correlation Coefficient (Lin's CCC) to evaluate the performance of the algorithm. A total of 51 patients were included, with 28 Type 2 hemorrhagic infarction (HI2) cases and 23 parenchymal hematoma (PH) cases. The algorithm achieved a mean DSC of 0.66 ± 0.17. Notably, performance was superior for PH cases (mean DSC of 0.73 ± 0.14) compared to HI2 cases (mean DSC of 0.61 ± 0.18). Lin's CCC was 0.88 (95% CI 0.79-0.93), indicating a strong agreement between the algorithm's results and the ground truth. In addition, the algorithm demonstrated excellent processing time, with an average of 2.7 s for each patient case. To our knowledge, this is the first study to perform automated segmentation of post-treatment hemorrhage for acute stroke patients and evaluate the performance based on the radiological severity of HT. This rapid and effective tool has the potential to assist with predicting prognosis in stroke patients with HT after EVT.

320 Emergency Department Use of Neuroimaging and Hospitalization for Transient Ischemic Attacks in the United States: A Cross-Sectional Study

OBJECTIVES/GOALS: A TIA is a transient episode of symptoms attributed to a cerebrovascular cause, and associated with an increased risk of stroke. Care of these patients often requires substantial resources in the Emergency Department (ED). We therefore described neuroimaging and hospitalization use for TIA within a nationally representative sample of US ED visits. METHODS/STUDY POPULATION: Retrospective cross-sectional analysis using TIA encounters in the 2018 National Emergency Department Sample (NEDS), an AHRQ dataset consisting of a weighted sample of 20% of all US ED encounters. Non-contrast Head CT, CTA Head, Carotid Ultrasound, MRI and CT Perfusion imaging utilization was determined based on Common Procedural Terminology (CPT) codes in the non-admitted encounters. The study population includes all adult patients with a discharge diagnosis of TIA as determined by ICD-10 codes (H34.0, G45.0-3, G45.8 G45.9) in any diagnosis position. The percentage of patients receiving each neuroimaging test was reported with the corresponding 95% confidence interval (CI). We utilized survey sample weights to generate reliable national estimates. RESULTS/ANTICIPATED RESULTS: The study population consisted of 80,803 ED encounters with a discharge diagnosis of TIA, representing 326,802 weighted ED visits nationally. Among this group, 46.8% of patients were discharged and 41.8% were admitted to the same hospital, 7% of patients were transferred to another facility, and the remaining 5% left AMA, were dispositioned to home health, died in the ED, or had an unknown disposition. Because discharged encounters retain their more precise CPT coding of procedural information, imaging analysis was conducted in discharged TIA encounters only. Of these encounters, 73% (95% CI, 70.7-76.5) received a noncontrast head CT, 20.9% (95% CI, 19.1-22.7) a CTA Head, 22.5% (95% CI, 20.6-24.4) a carotid ultrasound, and 31.5% (95% CI, 29.3-33.7) an MRI brain without contrast. DISCUSSION/SIGNIFICANCE: The discharge rate of just under 50% of patients is consistent with other published data, and represents a gradual trend over the past decade of decreased admissions for TIA. The fact that for many of these patients, the entire episode of care occurs in the ED setting suggests that the ED may be a rich target for future innovations in care for TIA.

Hyperdense sign as a predictor for successful recanalization and clinical outcome in acute ischemic stroke: A systematic review and meta-analysis.

To assess the prognostic values of hyperdense sign on pretreatment non-contrast head CT scan for successful recanalization (mTICI ≥2b) and 90-day good functional outcome (mRs 0-2) in patients with acute ischemic stroke undergoing mechanical thrombectomy (MT). Literature search on PubMed, EMBASE, and Cochrane databases from inception up to 1 November 2023 was conducted. Twelve studies which reported hyperdense sign, recanalization and clinical outcomes were included in qualitative synthesis and meta-analysis. Pooled analysis demonstrated a statistically significant association between successful recanalization and hyperdense sign-positive patients who underwent MT (odd ratios (OR) = 1.47, 95% confidence interval (CI) = 1.03-2.10, p = 0.04). No statistically significant association was demonstrated between presence of hyperdense sign and good functional outcome (OR = 1.04, 95% CI: 0.72-1.49, p = 0.85) or symptomatic intracranial hemorrhage sICH (OR: 1.80, 95% CI 0.72-4.47, p = 0.21). This meta-analysis demonstrated that pre-intervention hyperdense sign on CT imaging might be useful in prediction of successful recanalization after MT.

Nonaneurysmal perimesencephalic subarachnoid hemorrhage on noncontrast head CT: An accuracy, inter-rater, and intra-rater reliability study

Background and purposeTo evaluate the reliability and accuracy of nonaneurysmal perimesencephalic subarachnoid hemorrhage (NAPSAH) on Noncontrast Head CT (NCCT) between numerous raters. Materials and methods45 NCCT of adult patients with SAH who also had a catheter angiography (CA) were independently evaluated by 48 diverse raters; 45 raters performed a second assessment one month later. For each case, raters were asked: 1) whether they judged the bleeding pattern to be perimesencephalic; 2) whether there was blood anterior to brainstem; 3) complete filling of the anterior interhemispheric fissure (AIF); 4) extension to the lateral part of the sylvian fissure (LSF); 5) frank intraventricular hemorrhage; 6) whether in the hypothetical presence of a negative CT angiogram they would still recommend CA. An automatic NAPSAH diagnosis was also generated by combining responses to questions 2–5. Reliability was estimated using Gwet's AC1 (κG), and the relationship between the NCCT diagnosis of NAPSAH and the recommendation to perform CA using Cramer's V test. Multi-rater accuracy of NCCT in predicting negative CA was explored. ResultsInter-rater reliability for the presence of NAPSAH was moderate (κG = 0.58; 95%CI: 0.47, 0.69), but improved to substantial when automatically generated (κG = 0.70; 95%CI: 0.59, 0.81). The most reliable criteria were the absence of AIF filling (κG = 0.79) and extension to LSF (κG = 0.79). Mean intra-rater reliability was substantial (κG = 0.65). NAPSAH weakly correlated with CA decision (V = 0.50). Mean sensitivity and specificity were 58% (95%CI: 44%, 71%) and 83 % (95%CI: 72 %, 94%), respectively. ConclusionNAPSAH remains a diagnosis of exclusion. The NCCT diagnosis was moderately reliable and its impact on clinical decisions modest.

Nilai Entrance Skin Dose Tiroid antara menggunakan Thyroid Shield dan tanpa Thyroid Shield pada Pemeriksaan CT Scan Kepala

Background: CT scans have a much greater dose than conventional radiographic examinations. The thyroid organ is an organ that is sensitive to radiation which is located near the head, precisely in the inferior part of the head so that when a CT scan of the head is carried out, the thyroid organ will be exposed to radiation. The aim of this study was to determine the difference in thyroid skin dose entry value between using a thyroid shield and without a thyroid shield on a head CT scan.Methods: This study is a type of quantitative research with a pre-experimental design. The object of research is Entrance Skin Dose (ESE) of ThyroidOrgan on non-contrast head CT Scan examination. The research location is at the Radiology Department at the Regional General Hospital Prof. Dr. Margono Soekarjo Purwokerto. Sample data number is 50 people (25 samples of non-contrast head CT scans without thyroid shield, and 25 samples of non-contrast head CT scans with thyroid shield. Data was obtained by measuring the radiation dose using a dosimeter placed over the thyroid area during a non-contrast CT scan between using a thyroid shield and without using a thyroid shield. Data analysis was performed using statistical tests Results: The results of measuring the radiation dose to the samples showed that the average radiation dose to the skin surface of the thyroid organ on a non-contrast CT scan without using a thoracic shield was 884.96 µSv and using a thyroid shield was 428.64 µSv. This shows that the average radiation dose from the skin surface of the thyroid organ decreased by 456.32 µSv (51.56%).Conclusions: There is a significant difference in the amount of radiation dose to the surface of the skin of the thyroid organ in non-contrast head CT scans between using a thyroid shield and without using a shield with a dose reduction of 51.6% of the radiation dose without using a thyroid shield.

Predicting hematoma expansion in acute spontaneous intracerebral hemorrhage: integrating clinical factors with a multitask deep learning model for non-contrast head CT

PurposeTo predict hematoma growth in intracerebral hemorrhage patients by combining clinical findings with non-contrast CT imaging features analyzed through deep learning.MethodsThree models were developed to predict hematoma expansion (HE) in 572 patients. We utilized multi-task learning for both hematoma segmentation and prediction of expansion: the Image-to-HE model processed hematoma slices, extracting features and computing a normalized DL score for HE prediction. The Clinical-to-HE model utilized multivariate logistic regression on clinical variables. The Integrated-to-HE model combined image-derived and clinical data. Significant clinical variables were selected using forward selection in logistic regression. The two models incorporating clinical variables were statistically validated.ResultsFor hematoma detection, the diagnostic performance of the developed multi-task model was excellent (AUC, 0.99). For expansion prediction, three models were evaluated for predicting HE. The Image-to-HE model achieved an accuracy of 67.3%, sensitivity of 81.0%, specificity of 64.0%, and an AUC of 0.76. The Clinical-to-HE model registered an accuracy of 74.8%, sensitivity of 81.0%, specificity of 73.3%, and an AUC of 0.81. The Integrated-to-HE model, merging both image and clinical data, excelled with an accuracy of 81.3%, sensitivity of 76.2%, specificity of 82.6%, and an AUC of 0.83. The Integrated-to-HE model, aligning closest to the diagonal line and indicating the highest level of calibration, showcases superior performance in predicting HE outcomes among the three models.ConclusionThe integration of clinical findings with non-contrast CT imaging features analyzed through deep learning showed the potential for improving the prediction of HE in acute spontaneous intracerebral hemorrhage patients.

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.