Most existing intracranial hematoma segmentation models target acute hemorrhages and may not generalize to the heterogeneous morphology of chronic subdural hematomas (CSDH). We compared a model trained on an open-access acute intracranial hemorrhage dataset with a model trained in combination with a CSDH dataset and further evaluated the performance of the combined dataset model across Nakaguchi subtypes of CSDH (homogeneous, laminar, separated, and trabecular) and between isodense and non-isodense hematomas. We analyzed 377 patients with 512 CSDHs. A 3D nnU-Net model was initialized with the open-access Brain Hemorrhage Segmentation Dataset (BHSD). In the second stage, the BHSD and institutional CSDH data (75

Cardiac and thoracic vascular injuries are among the most serious and life-threatening conditions seen in trauma care. These injuries often are not imaged because many patients die before reaching the hospital or require emergency surgery before imaging can be performed. However, with improvements in emergency care and imaging technology, radiologists are now more likely to encounter these injuries and must be prepared to recognize them quickly. Accurate and timely imaging is essential for guiding urgent treatment and improving outcomes in both blunt and penetrating trauma to the heart and major vessels. The authors cover the imaging features of these injuries, including multiple types of cardiac injury, ranging from contusion to laceration, pericardial rupture, coronary artery injury, pulmonary arterial and venous injuries, injury to the aortic arch branches, internal mammary and intercostal injuries, caval injuries, and other major venous injuries. As a result, radiologists will be more familiar with the spectrum of injuries, which may lead to faster diagnosis, better communication with trauma teams, and potentially life-saving interventions. ©RSNA, 2026 Supplemental material is available for this article.

Objective We explore the feasibility to estimate the exudation from chronic subdural hematoma (CSDH) membranes, by using dual-energy computed tomography (DECT) quantification of iodine leak and test if the derived quantitative variables and membrane morphology correlates with hematoma volume, internal architecture (homogeneous, laminar, separated, and trabecular types), and fractional hyperdense hematoma at presentation. Methods In this retrospective study, consecutive CSDH patients with postcontrast DECT head images from January 2020 and June 2021 were analyzed. Predictor variables derived from DECT were correlated with outcome variables followed by mixed-effects regression analysis. Results The study included 36 patients with 50 observations (mean age, 72.6 years; standard deviation, 11.6 years); 31 were men. Dual-energy CT variables that correlated with hematoma volume were external membrane volume (ρ, 0.37; P = 0.008) and iodine concentration (ρ, −0.29; P = 0.04). Variables that correlated with separated type of hematoma were total iodine leak (median [Q 1 , Q 3 ], 68.3 mg [48.5, 88.9] vs 38.8 mg [15.5, 62.9]; P = 0.001) and iodine leak per unit membrane volume (median [Q 1 , Q 3 ], 16.47 mg/mL [10.19, 20.65] vs 8.68 mg/mL [5.72, 11.41]; P = 0.002). Membrane grade was the only variable that correlated with fractional hyperdense hematoma (ρ, 0.28; P = 0.05). Regression analysis showed total iodine leak as the strongest predictor of separated type hematoma (odds ratio [95% confidence interval], 1.06 per mg [1.01, 1.1]). Conclusions Dual-energy CT demonstrates iodine leak from CSDH membranes. The variables derived from DECT correlated with hematoma volume, internal architecture, and fractional hyperdense hematoma.

This Editorial Comment discusses the following AJR article: CT Number Accuracy and Association With Object Size: A Phantom Study Comparing Energy-Integrating Detector CT and Deep Silicon Photon-Counting Detector CT.

To identify prognostic factors with emphasis on chronic subdural hematoma (CSDH) architecture that determines short-term outcome of middle meningeal artery embolization (MMAE). Consecutive CSDH patients treated by MMAE (November 2019 and March 2022) were retrospectively analyzed. Four architectures were analyzed: homogeneous, laminar, separated, and trabecular types. Predictor variables from baseline CT were correlated with radiological endpoint (≥ 50

This technical note describes a novel dual-energy CT (DECT) protocol with iodine map reconstruction that will enable visualization of chronic subdural hematoma (CSDH) membranes. We describe the technique and discuss the potential implications for surgical management. The cohort included 36 patients with 50 hematomas. Enhancing external membrane was demonstrated in all the 50 hematomas, incomplete internal membrane in 13, and complete internal membrane in 23 hematomas. A spandrel sign at the transition zone that indicates partial or complete formation of internal membrane was demonstrated in 36 hematomas. KEY POINTS: • Iodine maps from 5-min delayed post-contrast DECT provide spectral contrast difference and facilitate segregation of chronic subdural hematoma membranes. • The ability to image the membranes helps in assessing the degree of organization of the hematoma by providing the information about the membrane thickness, volume, complexity of the membranes, and the proportion of the liquefied component within the hematoma before surgical procedures are undertaken. • Membrane visualization helps in the localization of the transition zone and extension of the membranes over the cerebral lobes helping in the determination of craniotomy location and size, during membranectomy.

The COVID-19 pandemic has emerged as a serious global health crisis, with the predominant morbidity and mortality linked to pulmonary involvement. Point-of-Care ultrasound (POCUS) scanning, becoming one of the primary determinative methods for its diagnosis and staging, requires, however, close contact of healthcare workers with patients, therefore increasing the risk of infection. This work thus proposes an autonomous robotic solution that enables POCUS scanning of COVID-19 patients’ lungs for diagnosis and staging. An algorithm was developed for approximating the optimal position of an ultrasound probe on a patient from prior CT scans to reach predefined lung infiltrates. In the absence of prior CT scans, a deep learning method was developed for predicting 3D landmark positions of a human ribcage given a torso surface model. The landmarks, combined with the surface model, are subsequently used for estimating optimal ultrasound probe position on the patient for imaging infiltrates. These algorithms, combined with a force–displacement profile collection methodology, enabled the system to successfully image all points of interest in a simulated experimental setup with an average accuracy of 20.6 ± 14.7 mm using prior CT scans, and 19.8 ± 16.9 mm using only ribcage landmark estimation. A study on a full torso ultrasound phantom showed that autonomously acquired ultrasound images were 100% interpretable when using force feedback with prior CT and 88% with landmark estimation, compared to 75 and 58% without force feedback, respectively. This demonstrates the preliminary feasibility of the system, and its potential for offering a solution to help mitigate the spread of COVID-19 in vulnerable environments.

Dual-energy computed tomography (DE CT) is a promising tool with many current and evolving applications. Available DE CT scanners usually consist of one or two tubes, or use layered detectors for spectral separation. Most DE CT scanners can be used in single energy or dual-energy mode, except for the layered detector scanners that always acquire data in dual-energy mode. However, the layered detector scanners can retrospectively integrate the data from two layers to obtain conventional single energy images. DE CT mode enables generation of virtual monochromatic images, blended images, iodine quantification, improving conspicuity of iodinated contrast enhancement, and material decomposition maps or more sophisticated quantitative analysis not possible with conventional SE CT acquisition with an acceptable or even lower dose than the SE CT. This article reviews the basic principles of dual-energy CT and highlights many of its clinical applications in the evaluation of neurological conditions.

Ultrasound phantoms are commonly used to assess the performance of ultrasound systems and ensure their proper functionality, in addition to providing opportunities for medical training. However, Focused Assessment with Sonography for Trauma (FAST) phantoms, in particular, are prohibitively expensive and procedure specific. This work explores the use of additive manufacturing to fabricate a patient-specific, full-scale torso ultrasound phantom. Phantom geometry was derived from anonymized computed tomography scans and segments into discrete organs. The digital organs (torso, skeleton, liver, spleen) were 3-D printed and used as castable molds for producing their respective body features. These organs were integrated with artificial hemorrhages to produce a realistic training tool for FAST scans. The resulting phantom is low in cost, has a verified shelf-life of at least 1 y and was positively reviewed by a trauma and emergency radiologist for its ability to provide accurate geometric and ultrasound information.

Unintentional injury or trauma is among the leading causes of death in the United States with up to 29% of the prehospital trauma deaths attributed to uncontrolled hemorrhages. This paper reports and analyzes control strategies for a tele-manipulated robotic system to enable remote Focused Assessment with Sonography for Trauma (FAST) en route to the hospital. We compare a hybrid telemanipulation technique which combines conventional position and rate control techniques to a position-based telemanipulated system. We also evaluate the performance of a force activated virtual fixture (VF) as an addition to the tele-manipulation system to expand the potential of robotic trauma care towards rapidly initializing lifesaving diagnostics and treatment procedures. From human subject trials, it was found that the final tele-manipulated system allows the operators to easily position the probe in 25% less time than the position-based system, as well as perform a FAST exam while smoothly sweeping the probe at 70% smoother sweep velocities with a consistent contact force having a 150% lower standard deviation than a system without the VF.

Skin segmentation plays an important role in a wide variety of biomedical image processing applications, such as skin cancer identification, skin lesion detection, and wound isolation. However, contemporary research has been mainly based on facial and hand skin datasets, with no other body regions considered for skin pixels sampling. Segmenting skin specifically in the abdominal region can aid in robotic abdominal surgeries and treatment procedures, such as robot-assisted laparoscopic surgeries and abdominal ultrasounds. A robust and highly accurate abdominal skin detection technique thus becomes imperative. To this end, we compiled a novel dataset of 1,400 segmented abdominal pictures and adapted and compared four abdominal skin segmentation techniques: one based on thresholding and three deep learning techniques, namely a fully connected neural network for pixel-level classification, and two convolution-based networks, U-Net and Mask-RCNN. We show that the U-Net model outperforms the other segmentation techniques, resulting in a pixel-to-pixel mean cross-validation accuracy of 95.51% on our Abdominal dataset. The incorporation of the Abdominal dataset in the training helped improve the abdominal skin segmentation accuracy by 10.19%. The U-Net model proved to be computationally the fastest, enabling real time skin segmentation with a processing rate of 37 frames per second.

BackgroundTraumatic hemorrhagic contusions are associated with iodine leak; however, quantification of leakage and its importance to outcome is unclear.PurposeTo identify iodine-based dual-energy CT variables that correlate with in-hospital mortality and short-term outcomes for contusions at hospital discharge.Materials and MethodsIn this retrospective study, consecutive patients with contusions from May 2016 through January 2017 were analyzed. Two radiologists evaluated CT variables from unenhanced admission head CT and follow-up head dual-energy CT scans obtained after contrast material-enhanced whole-body CT. The outcomes evaluated were in-hospital mortality, Rancho Los Amigos scale (RLAS) score, and disability rating scale (DRS) score. Logistic regression and linear regression were used to develop prediction models for categorical and continuous outcomes, respectively.ResultsThe study included 65 patients (median age, 48 years; interquartile range, 25-65.5 years); 50 were men. Dual-energy CT variables that correlated with mortality, RLAS score, and DRS score were iodine concentration, pseudohematoma volume, iodine quantity in pseudohematoma, and iodine quantity in contusion. The single-energy CT variable that correlated with mortality, RLAS score, and DRS score was hematoma volume at follow-up CT. Multiple logistic regression analysis after inclusion of clinical variables identified two predictors that enabled determination of mortality: postresuscitation Glasgow coma scale (P-GCS) (adjusted odds ratio, 0.42; 95% confidence interval [CI]: 0.2, 0.86; P = 0.01) and iodine quantity in pseudohematoma (adjusted odds ratio, 1.4 per milligram; 95% CI: 1.02 per milligram, 1.9 per milligram; P = 0.03), with a mean area under the receiver operating characteristic curve of 0.96 ± 0.05 (standard error). For RLAS, the predictors were P-GCS (mean coefficient, 0.32 ± 0.06; P < .001) and iodine quantity in contusion (mean coefficient, -0.04 per milligram ± 0.02; P = 0.01). Predictors for DRS were P-GCS (mean coefficient, -1.15 ± 0.27; P < .001), age (mean coefficient, 0.13 per year ± 0.04; P = .002), and iodine quantity in contusion (mean coefficient, 0.19 per milligram ± 0.07; P = .02).ConclusionIodine-based dual-energy CT variables correlate with in-hospital mortality and short-term outcomes for contusions at hospital discharge.© RSNA, 2019Online supplemental material is available for this article.See also the editorial by Talbott and Hess in this issue.

Trauma is among the leading causes of death in the United States with up to 29% of pre-hospital trauma deaths attributed to uncontrolled hemorrhages. This paper reports a semi-autonomous robotic system capable of assessing trauma using 2D and 3D image analysis and enabling remote focused assessment with sonography for trauma (FAST) en route to the hospital for earlier trauma diagnosis and faster initialization of life saving care. The system was able to accurately calculate FAST scan positions of patient specific phantoms using the measured phantom sizes and positions of the umbilicus. The system was capable of accurately classifying and localizing wounds, so they can be avoided during the ultrasound scan. These objects were localized with an accuracy of 0.94 ± 0.179cm and FAST exam locations were estimated with an accuracy of 2.2 ± 1.88cm. A radiologist successfully completed a remote FAST scan of the phantom using the system with improved image quality over manual scans, demonstrating feasibility of the system.

High-energy monochromatic (190 keV) images may be more reliable than standard 120 kV Images for detecting intracranial hemorrhages. We aimed to retrospectively compare virtual high monochromatic (190 keV) and standard 120 kV images from dual-energy computed tomography (CT; DECT) for the diagnosis of intracranial hemorrhages in traumatic brain injury (TBI). We analyzed admission CT studies in 100 trauma patients. Three radiologists independently reviewed four image sets: 120 kV and 190 keV (thin [1 mm] and thick [5 mm] section) images for the presence of various types of intracranial hemorrhages. The proportions of positive variables were compared and differences calculated by McNemar test and sensitivities determined by contingency tables. Randomly selected hemorrhagic lesions were analyzed for contrast index (CI). Thin-section 190 keV images were superior in the detection of subdural hematomas (SDH) (p < 0.0001), supratentorial contusions (p < 0.0001), and epidural hematomas (EDH) (p = 0.014), when compared with standard 120 kV images. However, 190 keV images were inferior to standard 120 kV images in diagnosis of subarachnoid hemorrhage (SAH) (thin-sections, p = 0.059; thick-sections, 0.0075). The 190 keV images yielded moderate increase in CI of contusions (Cohen's d > 0.53) and a large increase in CI of extra-axial hematomas (Cohen's d > 0.86). Our results indicate that virtual high monochromatic (190 keV, thin-section) images combined with standard 120 kV images may provide optimal diagnostic performance for evaluation of patients suspected of TBI.

BACKGROUND AND PURPOSE: In patients with hemorrhagic contusions, hematoma volumes are overestimated on follow-up standard 120-kV images obtained after contrast-enhanced whole-body CT. We aimed to retrospectively determine hemorrhagic progression of contusion rates on 120-kV and 190-keV images derived from dual-energy CT and the magnitude of hematoma volume overestimation. MATERIALS AND METHODS: We retrospectively analyzed admission and follow-up CT studies in 40 patients with hemorrhagic contusions. After annotating the contusions, we measured volumes from admission and follow-up 120-kV and 190-keV images using semiautomated 3D segmentation. Bland-Altman analysis was used for hematoma volume comparison. RESULTS: On 120-kV images, hemorrhagic progression of contusions was detected in 24 of the 40 patients, while only 17 patients had hemorrhagic progression of contusions on 190-keV images (P = .008). Hematoma volumes were systematically overestimated on follow-up 120-kV images (9.68 versus 8 mm(3); mean difference, 1.68 mm(3); standard error, 0.37; P < .001) compared with 190-keV images. There was no significant difference in volumes between admission 120-kV and 190-keV images. Mean and median percentages of overestimation were 29% (95% CI, 18-39) and 22% (quartile 3 - quartile 1 = 36.8), respectively. CONCLUSIONS: The 120-kV images, which are comparable with single-energy CT images, significantly overestimated the hematoma volumes, hence the rate of hemorrhagic progression of contusions, after contrast-enhanced whole-body CT. Hence, follow-up of hemorrhagic contusions should be performed on dual-energy CT, and 190-keV images should be used for the assessment of hematoma volumes.

BACKGROUND AND PURPOSE: Extravasation of iodinated contrast into subdural space following contrast-enhanced radiographic studies results in hyperdense subdural effusions, which can be mistaken as acute subdural hematomas on follow-up noncontrast head CTs. Our aim was to identify the factors associated with contrast-enhancing subdural effusion, characterize diffusion and washout kinetics of iodine in enhancing subdural effusion, and assess the utility of dual-energy CT in differentiating enhancing subdural effusion from subdural hematoma. MATERIALS AND METHODS: We retrospectively analyzed follow-up head dual-energy CT studies in 423 patients with polytrauma who had undergone contrast-enhanced whole-body CT. Twenty-four patients with enhancing subdural effusion composed the study group, and 24 randomly selected patients with subdural hematoma were enrolled in the comparison group. Postprocessing with syngo.via was performed to determine the diffusion and washout kinetics of iodine. The sensitivity and specificity of dual-energy CT for the diagnosis of enhancing subdural effusion were determined with 120-kV, virtual monochromatic energy (190-keV) and virtual noncontrast images. RESULTS: Patients with enhancing subdural effusion were significantly older (mean, 69 years; 95% CI, 60–78 years; P < .001) and had a higher incidence of intracranial hemorrhage (P = .001). Peak iodine concentration in enhancing subdural effusions was reached within the first 8 hours of contrast administration with a mean of 0.98 mg/mL (95% CI, 0.81–1.13 mg/mL), and complete washout was achieved at 38 hours. For the presence of a hyperdense subdural collection on 120-kV images with a loss of hyperattenuation on 190-keV and virtual noncontrast images, when considered as a true-positive for enhancing subdural effusion, the sensitivity was 100% (95% CI, 85.75%–100%) and the specificity was 91.67% (95% CI, 73%–99%). CONCLUSIONS: Dual-energy CT has a high sensitivity and specificity in differentiating enhancing subdural effusion from subdural hematoma. Hence, dual-energy CT has a potential to obviate follow-up studies.

Neither the performance of CT in diagnosing penetrating gastrointestinal injury nor its ability to discriminate patients requiring either observation or surgery has been determined.

OBJECT:The authors conducted a study to compare the sensitivity and specificity of helical CT angiography (CTA) and digital subtraction angiography (DSA) in detecting intracranial arterial injuries after penetrating traumatic brain injury (PTBI).METHODS:In a retrospective evaluation of 48 sets of angiograms from 45 consecutive patients with PTBI, 3 readers unaware of the DSA findings reviewed the CTA images to determine the presence or absence of arterial injuries. A fourth reader reviewed all the disagreements and decided among the 3 interpretations. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of CTA were calculated on a per-injury basis and in a subpopulation of patients with traumatic intracranial aneurysms (TICAs).RESULTS:Sensitivity of CTA for detecting arterial injuries was 72.7% (95% CI 49.8%-89.3%); specificity, 93.5% (95% CI 78.6%-99.2%); PPV, 88.9% (95% CI 65.3%-98.6%); and NPV, 82.9% (95% CI 66.4%-93.4%). All 7 TICAs were correctly identified by CTA. Sensitivity, specificity, PPV, and NPV of CTA in detecting TICAs were 100%. To compare agreement with DSA, the standard of reference, confidence scores categorized as low, intermediate, and high probability yielded an overall effectiveness of 77.8% (95% CI 71.8%-82.9%).CONCLUSIONS:Computed tomography angiography had limited overall sensitivity in detecting arterial injuries in patients with PTBI. However, it was accurate in identifying TICAs, a subgroup of injuries usually managed by either surgical or endovascular approaches, and non-TICA injuries involving the first-order branches of intracranial arteries.

PURPOSE To retrospectively compare the diagnostic performance of arterial, portal venous, and dual-phase computed tomography (CT) for blunt traumatic splenic injury. MATERIALS AND METHODS Informed consent was waived for this institutional review board-approved, HIPAA-compliant study. Retrospective record review identified 120 blunt trauma patients (87 male [72.5%] 33 female [27.5%]; age range, 18-94 years) who had undergone dual-phase abdominal CT within 5 years, including 30 without splenic injury, 30 with parenchymal injury only, 30 with splenic active bleeding, and 30 with intrasplenic pseudoaneurysm. Six radiologists each performed blinded review of 20 different cases, and scored the presence of pseudoaneurysm, active bleeding, parenchymal injury, and hematoma; 20 cases were interpreted by all radiologists. Data analysis included calculation of diagnostic performance measures with confidence intervals, areas under receiver operating characteristic curves, and interobserver agreement/variability. RESULTS For intrasplenic pseudoaneurysm, arterial phase imaging was more sensitive (70% [21 of 30] vs 17% [five of 30]; P < .0002) and more accurate (87% [78 of 90] vs 72% [65 of 90]; P = .0165) than portal venous phase imaging. For active bleeding, arterial phase imaging was less sensitive (70% [21 of 30] vs 93% [28 of 30]; P = .0195) and less accurate (89% [80 of 90] vs 98% [88 of 90]; P = .0168) than portal venous phase imaging. For parenchymal injury, arterial phase CT was less sensitive (76% [68 of 90] vs 93% [84 of 90]; P = .001) and less accurate (81% [nine of 120] vs 95% [114 of 120]; P = .0008) than portal venous phase CT. For all injuries, dual-phase review was equivalent to or better than single-phase review. CONCLUSION For CT evaluation of blunt splenic injury, arterial phase is superior to portal venous phase imaging for pseudoaneurysm but inferior for active bleeding and parenchymal disruption; dual-phase CT provides optimal overall performance.