A robust near-field body area network based on coaxially-shielded textile metamaterial.

A body area network involving wearable sensors distributed around the human body can continuously monitor physiological signals, finding applications in personal healthcare and athletic evaluation. Existing solutions for near-field body area networks, while facilitating reliable and secure interconnection among battery-free sensors, face challenges including limited spectral stability against external interference. Here we demonstrate a textile metamaterial featuring a coaxially-shielded internal structure designed to mitigate interference from extraneous loadings. The metamaterial can be patterned onto clothing to form a scalable, customizable network, enabling communication between near-field reading devices and battery-free sensing nodes placed within the network. Proof of concept demonstration shows the metamaterial's robustness against mechanical deformation and exposure to lossy, conductive saline solutions, underscoring its potential applications in wet environments, particularly in athletic activities involving water or significant perspiration, offering insights for the future development of radio frequency components for a robust body area network at a system level.

Wireless, customizable coaxially shielded coils for magnetic resonance imaging.

Anatomy-specific radio frequency receive coil arrays routinely adopted in magnetic resonance imaging (MRI) for signal acquisition are commonly burdened by their bulky, fixed, and rigid configurations, which may impose patient discomfort, bothersome positioning, and suboptimal sensitivity in certain situations. Herein, leveraging coaxial cables' inherent flexibility and electric field confining property, we present wireless, ultralightweight, coaxially shielded, passive detuning MRI coils achieving a signal-to-noise ratio comparable to or surpassing that of commercially available cutting-edge receive coil arrays with the potential for improved patient comfort, ease of implementation, and substantially reduced costs. The proposed coils demonstrate versatility by functioning both independently in form-fitting configurations, closely adapting to relatively small anatomical sites, and collectively by inductively coupling together as metamaterials, allowing for extension of the field of view of their coverage to encompass larger anatomical regions without compromising coil sensitivity. The wireless, coaxially shielded MRI coils reported herein pave the way toward next-generation MRI coils.

Wearable Coaxially-Shielded Metamaterial for Magnetic Resonance Imaging.

Recent advancements in metamaterials have yielded the possibility of a wireless solution to improve signal-to-noise ratio (SNR) in magnetic resonance imaging (MRI). Unlike traditional closely packed local coil arrays with rigid designs and numerous components, these lightweight, cost-effective metamaterials eliminate the need for radio frequency cabling, baluns, adapters, and interfaces. However, their clinical adoption is limited by their low sensitivity, bulky physical footprint, and limited, specific use cases. Herein, a wearable metamaterial developed using commercially available coaxial cable, designed for a 3.0 T MRI system is introduced. This metamaterial inherits the coaxially-shielded structure of its constituent cable, confining the electric field within and mitigating coupling to its surroundings. This ensures safer clinical adoption, lower signal loss, and resistance to frequency shifts. Weighing only 50 g, the metamaterial maximizes its sensitivity by conforming to the anatomical region of interest. MRI images acquired using this metamaterial with various pulse sequences achieve an SNR comparable or even surpass that of a state-of-the-art 16-channel knee coil. This work introduces a novel paradigm for constructing metamaterials in the MRI environment, paving the way for the development of next-generation wireless MRI technology.

Computational-Design Enabled Wearable and Tunable Metamaterials via Freeform Auxetics for Magnetic Resonance Imaging.

Metamaterials hold significant promise for enhancing the imaging capabilities of magnetic resonance imaging (MRI) machines as an additive technology, due to their unique ability to enhance local magnetic fields. However, despite their potential, the metamaterials reported in the context of MRI applications have often been impractical. This impracticality arises from their predominantly flat configurations and their susceptibility to shifts in resonance frequencies, preventing them from realizing their optimal performance. Here, a computational method for designing wearable and tunable metamaterials via freeform auxetics is introduced. The proposed computational-design tools yield an approach to solving the complex circle packing problems in an interactive and efficient manner, thus facilitating the development of deployable metamaterials configured in freeform shapes. With such tools, the developed metamaterials may readily conform to a patient's knee, ankle, head, or any part of the body in need of imaging, and while ensuring an optimal resonance frequency, thereby paving the way for the widespread adoption of metamaterials in clinical MRI applications.

Computational-design Enabled Wearable and Tunable Metamaterials via Freeform Auxetics for Magnetic Resonance Imaging.

Metamaterials hold significant promise for enhancing the imaging capabilities of MRI machines as an additive technology, due to their unique ability to enhance local magnetic fields. However, despite their potential, the metamaterials reported in the context of MRI applications have often been impractical. This impracticality arises from their predominantly flat configurations and their susceptibility to shifts in resonance frequencies, preventing them from realizing their optimal performance. Here, we introduce a computational method for designing wearable and tunable metamaterials via freeform auxetics. The proposed computational-design tools yield an approach to solving the complex circle packing problems in an interactive and efficient manner, thus facilitating the development of deployable metamaterials configured in freeform shapes. With such tools, the developed metamaterials may readily conform to a patient's kneecap, ankle, head, or any part of the body in need of imaging, and while ensuring an optimal resonance frequency, thereby paving the way for the widespread adoption of metamaterials in clinical MRI applications.

Hematocrit and lactate trends help predict outcomes in trauma independent of CT and other clinical parameters.

Background: Hematocrit and lactate have an established role in trauma as indicators of bleeding and cell death, respectively. The wide availability of CT imaging and clinical data poses the question of how these can be used in combination to predict outcomes. Purpose: To assess the utility of hematocrit or lactate trends in predicting intensive care unit (ICU) admission and hospital length of stay (LOS) in patients with torso trauma combined with clinical parameters and injury findings on CT. Materials and Methods: This was a single-center retrospective study of adults with torso trauma in one year. Trends were defined as a unit change per hour. CT findings and clinical parameters were explanatory variables. Outcomes were ICU admission and hospital LOS. Multivariate logistic and negative binomial regression models were used to calculate the odds ratio (OR) and incident rate ratio (IRR). Results: Among 840 patients, 561 (72% males, age 39 ± 18) were included, and 168 patients (30%) were admitted to the ICU. Decreasing hematocrit trend [OR 2.54 (1.41-4.58), p = 0.002] and increasing lactate trend [OR 3.85 (1.35-11.01), p = 0.012] were associated with increased odds of ICU admission. LOS median was 2 (IQR: 1-5) days. Decreasing hematocrit trend [IRR 1.37 (1.13-1.66), p = 0.002] and increasing lactate trend [2.02 (1.43-2.85), p < 0.001] were associated with longer hospital LOS. Conclusion: Hematocrit and lactate trends may be helpful in predicting ICU admission and LOS in torso trauma independent of organ injuries on CT, age, or admission clinical parameters.

Utilization of a two-material decomposition from a single-source, dual-energy CT in acute traumatic vertebral fractures.

Purpose: The purpose of this study is to utilize a two-material decomposition to quantify bone marrow edema on a dual-energy computed tomography (DECT) scanner at the cervical, thoracic, and lumbar spine acute fractures in correlation with short tau inversion recovery (STIR) hyperintensity on magnetic resonance imaging (MRI) in comparison with the normal bone marrow. Materials and methods: This retrospective institutional review board-approved study gathered patients over 18 years old who had acute cervical, thoracic, or lumbar spinal fractures scanned on a DECT scanner. Those who had a spinal MRI done with bone marrow STIR hyperintensity within 3 weeks of the DECT were included. The water (calcium) and fat (calcium) density (mg/cm3) measurements of the region of interest of the bone marrow were obtained at a normal anatomic equivalent site and at the fracture site where STIR hyperintensity was noted on MRI. A statistical analysis was performed using the paired t-test and Wilcoxon signed rank test (p > 0.05). Results: A total of 20 patients met the inclusion criteria (males n = 17 males, females n = 3). A total of 32 fractures were analyzed: 19 cervical and 13 thoracolumbar. There were statistically significant differences in the water (43 ± 24 mg/cm3) and fat (36 ± 31 mg/cm3) density (mg/cm3) at the acute thoracic and lumbar spine fractures in correlation with edema on STIR images (both paired t-test <0.001, both Wilcoxon signed ranked test p < 0.01). There were no significant differences in the water (-10 ± 46 mg/cm3) or fat (+7 ± 50 mg/cm3) density (mg/cm3) at the cervical spine fractures. Conclusion: The DECT two-material decomposition using water (calcium) and fat (calcium) analyses has the ability to quantify a bone marrow edema at the acute fracture site in the thoracic and lumbar spine.

Bayesian reconstruction of magnetic resonance images using Gaussian processes.

A central goal of modern magnetic resonance imaging (MRI) is to reduce the time required to produce high-quality images. Efforts have included hardware and software innovations such as parallel imaging, compressed sensing, and deep learning-based reconstruction. Here, we propose and demonstrate a Bayesian method to build statistical libraries of magnetic resonance (MR) images in k-space and use these libraries to identify optimal subsampling paths and reconstruction processes. Specifically, we compute a multivariate normal distribution based upon Gaussian processes using a publicly available library of T1-weighted images of healthy brains. We combine this library with physics-informed envelope functions to only retain meaningful correlations in k-space. This covariance function is then used to select a series of ring-shaped subsampling paths using Bayesian optimization such that they optimally explore space while remaining practically realizable in commercial MRI systems. Combining optimized subsampling paths found for a range of images, we compute a generalized sampling path that, when used for novel images, produces superlative structural similarity and error in comparison to previously reported reconstruction processes (i.e. 96.3% structural similarity and < 0.003 normalized mean squared error from sampling only 12.5% of the k-space data). Finally, we use this reconstruction process on pathological data without retraining to show that reconstructed images are clinically useful for stroke identification. Since the model trained on images of healthy brains could be directly used for predictions in pathological brains without retraining, it shows the inherent transferability of this approach and opens doors to its widespread use.

Quantification of spinal bone marrow fat fraction using three-material decomposition technique on dual-energy CT: A phantom study.

BACKGROUND: Two-material decomposition is insufficient to quantify the fat fraction of spinal bone marrow, which is comprised of a mixture of bone minerals, water, and yellow marrow (fat). PURPOSE: To develop an accurate three-material decomposition-based bone marrow fat fraction ( F F 3 M D $F{F_{3MD}}$ ) quantification technique for dual-energy CT. METHODS: Bone marrow edema phantoms containing trabecular bone minerals, water, and fat were constructed using fat fractions and bone mineral density values matching those expected in healthy and edematous bone, and scanned on a commercial dual-energy CT. Fat quantified by F F 3 M D $F{F_{3MD}}$ were compared to MRI-based fat fraction ( F F M R I $F{F_{MRI}}$ ) and conventional two-material-decomposition-based fat fraction ( F F 2 M D $F{F_{2MD}}$ ) to evaluate its accuracy and dependency on various bone mineral densities. RESULTS: F F 3 M D $F{F_{3MD}}$ demonstrated an excellent correlation with F F M R I $F{F_{MRI}}\;$ (r = 0.97, R2  = 0.96) in the phantom, significantly more accurate than FF2MD when confounding bone minerals are present (50 mg/cm3 : r = 1.02, R2  = 0.95 vs. r = 0.65, R2  = 0.79 (p < 0.01); 100 mg/cm3 : r = 0.81, R2  = 0.47 vs. r = 0.21, R2  = 0.21 (p < 0.05)). CONCLUSIONS: F F 3 M D $F{F_{3MD}}$ accurately quantified bone marrow fat fraction, when compared with F F M R I $F{F_{MRI}}$ , in the specially constructed bone marrow phantom.

Gadolinium Deposition in the Rat Brain Measured with Quantitative MRI versus Elemental Mass Spectrometry.

Background T1-weighted MRI and quantitative longitudinal relaxation rate (R1) mapping have been used to evaluate gadolinium retention in the brain after gadolinium-based contrast agent (GBCA) administration. Whether MRI measures accurately reflect gadolinium regional distribution and concentration in the brain remains unclear. Purpose To compare gadolinium retention in rat forebrain measured with in vivo quantitative MRI R1 and ex vivo laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) mapping after gadobenate, gadopentetate, gadodiamide, or gadobutrol administration. Materials and Methods Adult female Sprague-Dawley rats were randomly assigned to one of five groups (eight per group) and administered gadobenate, gadopentetate, gadodiamide, gadobutrol (2.4 mmol/kg per week for 5 weeks), or saline (4.8 mL/kg per week for 5 weeks). MRI R1 mapping was performed at baseline and 1 week after the final injection to determine R1 and ΔR1. Postmortem brains from the same rats were analyzed with LA-ICP-MS elemental mapping to determine regional gadolinium concentrations. Student t tests were performed to compare results between GBCA and saline groups. Results Rats that were administered gadobenate showed gadolinium-related MRI ΔR1 in 39.5% of brain volume (ΔR1 = 0.087 second-1 ± 0.051); gadopentetate, 20.6% (ΔR1 = 0.069 second-1 ± 0.018); gadodiamide, 5.4% (ΔR1 = 0.055 second-1 ± 0.019); and gadobutrol, 2.2% (ΔR1 = 0.052 second-1 ± 0.041). Agent-specific gadolinium-related ΔR1 was detected in multiple forebrain regions (neocortex, hippocampus, dentate gyrus, thalamus, and caudate-putamen) in rats treated with gadobenate or gadopentetate, whereas rats treated with gadodiamide showed gadolinium-related ΔR1 in caudate-putamen. By contrast, LA-ICP-MS elemental mapping showed a similar regional distribution pattern of heterogeneous retained gadolinium in the forebrain of rats treated with gadobenate, gadopentetate, or gadodiamide, with the average gadolinium concentration of 0.45 µg · g-1 ± 0.07, 0.50 µg · g-1 ± 0.10, and 0.60 µg · g-1 ± 0.11, respectively. Low levels (0.01 µg · g-1 ± 0.00) of retained gadolinium were detected in the forebrain of gadobutrol-treated rats. Conclusion Differences in in vivo MRI longitudinal relaxation rate versus ex vivo elemental mass spectrometry measures of retained gadolinium in rat forebrains suggest that some forms of retained gadolinium may escape detection with MRI. © RSNA, 2022 Online supplemental material is available for this article.

Quantitative Ultrasound Assessment of Hepatic Steatosis.

Background/Aims: Non-alcoholic fatty liver disease (NAFLD) is widespread chronic disease of the live in humans with the prevalence of 30% of the United States population.1,2 The goal of the study is to validate the performance of quantitative ultrasound algorithms in the assessment of hepatic steatosis in patients with suspected NAFLD. Methods: This prospective study enrolled a total of 31 patients with clinical suspicion of NAFLD to receive liver fat measurements by quantitative ultrasound and reference MRI measurements (proton density fat-fraction, PDFF). The following ultrasound (US) parameters based on both raw ultrasound RF (Radio Frequency) data and 2D B-mode images of the liver were analyzed with subsequent correlation with MRI-PDFF: hepatorenal index, acoustic attenuation coefficient, Nakagami coefficient parameter, shear wave viscosity, shear wave dispersion and shear wave elasticity. Ultrasound parameters were also correlated with the presence of hypertension and diabetes. Results: The mean (± SD) age and body mass index of the patients were 49.03 (± 12.49) and 30.12 (± 6.15), respectively. Of the aforementioned ultrasound parameters, the hepatorenal index and acoustic attenuation coefficient showed a strong correlation with MRI-PDFF derivations of hepatic steatosis, with r-values of 0.829 and 0.765, respectively. None of the remaining US parameters showed strong correlations with PDFF. Significant differences in Nakagami parameters and acoustic attenuation coefficients were found in those patients with and without hypertension. Conclusions: Hepatorenal index and acoustic attenuation coefficient correlate well with MRI-PDFF-derived measurements of hepatic steatosis. Quantitative ultrasound is a promising tool for the diagnosis and assessment of patients with NAFLD.

Quantification of bone marrow edema using dual-energy CT at fracture sites in trauma.

PURPOSE: The purpose of our study was to analyze the change in water and fat density within the bone marrow using the GE Revolution dual-energy computed tomography (DECT) platform using two-material decomposition analyses at extremity, spine, and pelvic fracture sites compared to normal bone marrow at equivalent anatomic sites in adult patients who sustained blunt trauma. METHODS: This retrospective study included 26 consecutive adults who sustained blunt torso trauma and an acute fracture of the thoracolumbar vertebral body, pelvis, or upper and lower extremities with a total of 32 fractures evaluated. Two-material decomposition images were analyzed for quantitative analysis. Statistical analysis was performed using the paired t-test and Shapiro-Wilk test for normality. RESULTS: There were statistically significant differences in the water and fat densities in the bone marrow at the site of an extremity, vertebral body, or pelvic fracture when compared to the normal anatomic equivalent (p < 0.01). CONCLUSION: In this preliminary study, DECT basis material images, using water (calcium) and fat (calcium) decomposition illustrated significant differences in water and fat content between fracture sites and normal bone in a variety of anatomical sites.

Metamaterial-enhanced near-field readout platform for passive microsensor tags.

Radiofrequency identification (RFID), particularly passive RFID, is extensively employed in industrial applications to track and trace products, assets, and material flows. The ongoing trend toward increasingly miniaturized RFID sensor tags is likely to continue as technology advances, although miniaturization presents a challenge with regard to the communication coverage area. Recently, efforts in applying metamaterials in RFID technology to increase power transfer efficiency through their unique capacity for electromagnetic wave manipulation have been reported. In particular, metamaterials are being increasingly applied in far-field RFID system applications. Here, we report the development of a magnetic metamaterial and local field enhancement package enabling a marked boost in near-field magnetic strength, ultimately yielding a dramatic increase in the power transfer efficiency between reader and tag antennas. The application of the proposed magnetic metamaterial and local field enhancement package to near-field RFID technology, by offering high power transfer efficiency and a larger communication coverage area, yields new opportunities in the rapidly emerging Internet of Things (IoT) era.

Fat Fraction Measurements Using a Three-Material Decomposition Dual-Energy CT Technique Accounting for Bone Minerals: Evaluation in a Bone Marrow Phantom Using MRI as Reference.

Conventional two-material dual-energy CT (DECT) decomposition is insufficient to model bone marrow, which contains three materials: bone minerals, red marrow (water), and yellow marrow (fat). We explore an image-domain three-material decomposition DECT technique accounting for bone minerals in a bone-water-fat phantom. Three-material decomposition fat fraction (FF3MD) exhibited stronger correlation than two-material decomposition fat fraction (FF2MD) with MRI-based fat fraction (r = 0.95 vs r = 0.69). With increasing bone minerals, correlation of FF3MD remained stable (r = 0.81-1.02), whereas correlation of FF2MD decreased (r = 0.21-0.65).

Auxetics-Inspired Tunable Metamaterials for Magnetic Resonance Imaging.

Auxetics refers to structures or materials with a negative Poisson's ratio, thereby capable of exhibiting counterintuitive behaviors. Herein, auxetic structures are exploited to design mechanically tunable metamaterials in both planar and hemispherical configurations operating at megahertz (MHz) frequencies, optimized for their application to magnetic resonance imaging (MRI). Specially, the reported tunable metamaterials are composed of arrays of interjointed unit cells featuring metallic helices, enabling auxetic patterns with a negative Poisson's ratio. The deployable deformation of the metamaterials yields an added degree of freedom with respect to frequency tunability through the resultant modification of the electromagnetic interactions between unit cells. The metamaterials are fabricated using 3D printing technology and an ≈20 MHz frequency shift of the resonance mode is enabled during deformation. Experimental validation is performed in a clinical (3.0 T) MRI system, demonstrating that the metamaterials enable a marked boost in radiofrequency field strength under resonance-matched conditions, ultimately yielding a dramatic increase in the signal-to-noise ratio (≈4.5×) of MRI. The tunable metamaterials presented herein offer a novel pathway toward the practical utilization of metamaterials in MRI, as well as a range of other emerging applications.

Tryptophan metabolites suppress the Wnt pathway and promote adverse limb events in chronic kidney disease.

Chronic kidney disease (CKD) imposes a strong and independent risk for peripheral artery disease (PAD). While solutes retained in CKD patients (uremic solutes) inflict vascular damage, their role in PAD remains elusive. Here, we show that the dietary tryptophan-derived uremic solutes including indoxyl sulfate (IS) and kynurenine (Kyn) at concentrations corresponding to those in CKD patients suppress ß-catenin in several cell types, including microvascular endothelial cells (ECs), inhibiting Wnt activity and proangiogenic Wnt targets in ECs. Mechanistic probing revealed that these uremic solutes downregulated ß-catenin in a manner dependent on serine 33 in its degron motif and through the aryl hydrocarbon receptor (AHR). Hindlimb ischemia in adenine-induced CKD and IS solute-specific mouse models showed diminished ß-catenin and VEGF-A in the capillaries and reduced capillary density, which correlated inversely with blood levels of IS and Kyn and AHR activity in ECs. An AHR inhibitor treatment normalized postischemic angiogenic response in CKD mice to a non-CKD level. In a prospective cohort of PAD patients, plasma levels of tryptophan metabolites and plasma's AHR-inducing activity in ECs significantly increased the risk of future adverse limb events. This work uncovers the tryptophan metabolite/AHR/ß-catenin axis as a mediator of microvascular rarefaction in CKD patients and demonstrates its targetability for PAD in CKD models.

Acute cholecystitis: diagnostic value of dual-energy CT-derived iodine map and low-keV virtual monoenergetic images.

PURPOSE: To compare conventional and dual-energy CT (DECT) for the diagnosis of acute cholecystitis and gangrene. METHODS: Fifty-seven consecutive adult patients with abdominal pain who underwent IV contrast-enhanced abdominal DECT on a dual-layer (dlDECT) or rapid-switching (rsDECT) scanner from September, 2018 to April, 2021 with cholecystectomy and pathology-confirmed cholecystitis were retrospectively reviewed, and compared with 57 consecutive adult patients without cholecystitis from the same interval scanned with DECT. Images were reviewed independently by two abdominal radiologists with 12 and 16 years of experience in two sessions 4 weeks apart, blinded to clinical data. Initially, only blended reconstructions (simulating conventional single-energy CT images) were reviewed (CT). Subsequently, CT and DECT reconstructions including low-keV virtual monoenergetic images and iodine maps were reviewed. Gallbladder fossa hyperemia, pericholecystic fluid, subjective presence of gangrene, heterogeneous wall enhancement, sloughed membranes, intramural air, abscess, overall impression of the presence of acute cholecystitis, and intramural iodine density were assessed. RESULTS: Gallbladder fossa hyperemia was detected with increased sensitivity on DECT (R1, 61.4%; R2, 75.4%) vs. CT (R1, 22.8%; R2, 15.8%). DECT showed increased sensitivity for gangrene (R1, 24.6%; R2, 38.6%) vs. CT (R1, 5.3%; R2, 14%), heterogeneous wall enhancement (DECT: R1, 33.3%; R2, 63.2% vs. CT: R1, 7%; R2, 31.6%), and cholecystitis (DECT: R1, 86%; R2, 89.5% vs. CT: R1, 77.2%; R2, 70.2%). In addition, DECT was more sensitive for the detection of acute cholecystitis (R1, 86%; R2, 89.5%) vs. CT (R1, 77.2%; R2, 70.2%). Iodine density threshold of 1.2 mg/ml, 0.8 mg/mL, and 0.5 mg/mL showed specificity for gangrenous cholecystitis of 78.26%, 86.96%, and 95.65%, respectively, using the rsDECT platform. CONCLUSION: DECT showed improved sensitivity compared to conventional CT for detection of acute cholecystitis. Iodine density measurements may be helpful to diagnose gangrene.

An Automated Deep Learning Method for Tile AO/OTA Pelvic Fracture Severity Grading from Trauma whole-Body CT.

Admission trauma whole-body CT is routinely employed as a first-line diagnostic tool for characterizing pelvic fracture severity. Tile AO/OTA grade based on the presence or absence of rotational and translational instability corresponds with need for interventions including massive transfusion and angioembolization. An automated method could be highly beneficial for point of care triage in this critical time-sensitive setting. A dataset of 373 trauma whole-body CTs collected from two busy level 1 trauma centers with consensus Tile AO/OTA grading by three trauma radiologists was used to train and test a triplanar parallel concatenated network incorporating orthogonal full-thickness multiplanar reformat (MPR) views as input with a ResNeXt-50 backbone. Input pelvic images were first derived using an automated registration and cropping technique. Performance of the network for classification of rotational and translational instability was compared with that of (1) an analogous triplanar architecture incorporating an LSTM RNN network, (2) a previously described 3D autoencoder-based method, and (3) grading by a fourth independent blinded radiologist with trauma expertise. Confusion matrix results were derived, anchored to peak Matthews correlation coefficient (MCC). Associations with clinical outcomes were determined using Fisher's exact test. The triplanar parallel concatenated method had the highest accuracies for discriminating translational and rotational instability (85% and 74%, respectively), with specificity, recall, and F1 score of 93.4%, 56.5%, and 0.63 for translational instability and 71.7%, 75.7%, and 0.77 for rotational instability. Accuracy of this method was equivalent to the single radiologist read for rotational instability (74.0% versus 76.7%, p = 0.40), but significantly higher for translational instability (85.0% versus 75.1, p = 0.0007). Mean inference time was < 0.1 s per test image. Translational instability determined with this method was associated with need for angioembolization and massive transfusion (p = 0.002-0.008). Saliency maps demonstrated that the network focused on the sacroiliac complex and pubic symphysis, in keeping with the AO/OTA grading paradigm. A multiview concatenated deep network leveraging 3D information from orthogonal thick-MPR images predicted rotationally and translationally unstable pelvic fractures with accuracy comparable to an independent reader with trauma radiology expertise. Model output demonstrated significant association with key clinical outcomes.

Machine learning combining CT findings and clinical parameters improves prediction of length of stay and ICU admission in torso trauma.

OBJECTIVE: To develop machine learning (ML) models capable of predicting ICU admission and extended length of stay (LOS) after torso (chest, abdomen, or pelvis) trauma, by using clinical and/or imaging data. MATERIALS AND METHODS: This was a retrospective study of 840 adult patients admitted to a level 1 trauma center after injury to the torso over the course of 1 year. Clinical parameters included age, sex, vital signs, clinical scores, and laboratory values. Imaging data consisted of any injury present on CT. The two outcomes of interest were ICU admission and extended LOS, defined as more than the median LOS in the dataset. We developed and tested artificial neural network (ANN) and support vector machine (SVM) models, and predictive performance was evaluated by area under the receiver operating characteristic (ROC) curve (AUC). RESULTS: The AUCs of SVM and ANN models to predict ICU admission were up to 0.87 ± 0.03 and 0.78 ± 0.02, respectively. The AUCs of SVM and ANN models to predict extended LOS were up to 0.80 ± 0.04 and 0.81 ± 0.05, respectively. Predictions based on imaging alone or imaging with clinical parameters were consistently more accurate than those based solely on clinical parameters. CONCLUSIONS: The best performing models incorporated imaging findings and outperformed those with clinical findings alone. ML models have the potential to help predict outcomes in trauma by integrating clinical and imaging findings, although further research may be needed to optimize their performance. KEY POINTS: • Artificial neural network and support vector machine-based models were used to predict the intensive care unit admission and extended length of stay after trauma to the torso. • Our input data consisted of clinical parameters and CT imaging findings derived from radiology reports, and we found that combining the two significantly enhanced the prediction of both outcomes with either model. • The highest accuracy (83%) and highest area under the receiver operating characteristic curve (0.87) were obtained for artificial neural networks and support vector machines, respectively, by combining clinical and imaging features in the prediction of intensive care unit admission.

Clinical and laboratory parameters in blunt pelvic trauma not associated with subsequent positive conventional angiography in patients with positive CTA.

PURPOSE: This study evaluates clinical and laboratory parameters, as well as extravasation and hematoma size on CTA as potential predictors of conventional angiogram (CA) results. METHODS: This is a retrospective study of 380 adult patients presenting with pelvic trauma over a 9-year period. Of these patients, 91 were found to have active arterial extravasation on initial CTA. Statistical analysis between the two groups +CA versus -CA was performed to determine whether clinical and laboratory parameters, as well as extravasation size and hematoma size could predict CA results. RESULTS: There were no significant differences in all clinical and laboratory data, including hemodynamic instability (defined as systolic blood pressure < 90 mmHg) on presentation (22.2% vs. 21.4%), except for Glasgow Coma Scale (p = 0.015) when comparing the two groups. Extravasation size and hematoma size as continuous or categorical variables were not predictive of subsequent positive CA. Secondary analysis demonstrated no association between select parameters (i.e., hematocrit, systolic blood pressure, and lactate) and subsequent positive CA while controlling for extravasation size or hematoma size. CONCLUSION: Clinical and laboratory parameters in blunt pelvic trauma with arterial hemorrhage were not significantly associated with subsequent conventional angiography results, once accounting for degree of hemorrhage. The area of the foci of active extravasation and hematoma size in the axial plane were not significantly associated with the need for embolization. We conclude from these findings that catheter angiography should be considered in patients with blunt pelvic trauma found to have active arterial extravasation, regardless of size of bleed or the patient's clinical or laboratory values.