An ASER AI/ML expert panel formative user research study for an interpretable interactive splenic AAST grading graphical user interface prototype.

PURPOSE: The AAST Organ Injury Scale is widely adopted for splenic injury severity but suffers from only moderate inter-rater agreement. This work assesses SpleenPro, a prototype interactive explainable artificial intelligence/machine learning (AI/ML) diagnostic aid to support AAST grading, for effects on radiologist dwell time, agreement, clinical utility, and user acceptance. METHODS: Two trauma radiology ad hoc expert panelists independently performed timed AAST grading on 76 admission CT studies with blunt splenic injury, first without AI/ML assistance, and after a 2-month washout period and randomization, with AI/ML assistance. To evaluate user acceptance, three versions of the SpleenPro user interface with increasing explainability were presented to four independent expert panelists with four example cases each. A structured interview consisting of Likert scales and free responses was conducted, with specific questions regarding dimensions of diagnostic utility (DU); mental support (MS); effort, workload, and frustration (EWF); trust and reliability (TR); and likelihood of future use (LFU). RESULTS: SpleenPro significantly decreased interpretation times for both raters. Weighted Cohen's kappa increased from 0.53 to 0.70 with AI/ML assistance. During user acceptance interviews, increasing explainability was associated with improvement in Likert scores for MS, EWF, TR, and LFU. Expert panelists indicated the need for a combined early notification and grading functionality, PACS integration, and report autopopulation to improve DU. CONCLUSIONS: SpleenPro was useful for improving objectivity of AAST grading and increasing mental support. Formative user research identified generalizable concepts including the need for a combined detection and grading pipeline and integration with the clinical workflow.

A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow.

Background: Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation. Purpose: In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow. Methods: Our end-to-end automated pipeline has two major components- 1. A router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Since nnU-net has emerged as a widely-used out-of-the-box method for training segmentation models with state-of-the-art performance, feasibility of our pipleine is demonstrated by recording clock times for a traumatic pelvic hematoma nnU-net model. Results: Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 min 32 s (± SD of 1 min 26 s). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 min, and illustrates feasibility in the clinical setting where quantitative results would be expected prior to report sign-off. Inference times accounted for most of the total clock time, ranging from 2 min 41 s to 8 min 27 s. All other virtual and on-premises host steps combined ranged from a minimum of 34 s to a maximum of 48 s. Conclusion: The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/," and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.

Accelerating voxelwise annotation of cross-sectional imaging through AI collaborative labeling with quality assurance and bias mitigation.

Background: precision-medicine quantitative tools for cross-sectional imaging require painstaking labeling of targets that vary considerably in volume, prohibiting scaling of data annotation efforts and supervised training to large datasets for robust and generalizable clinical performance. A straight-forward time-saving strategy involves manual editing of AI-generated labels, which we call AI-collaborative labeling (AICL). Factors affecting the efficacy and utility of such an approach are unknown. Reduction in time effort is not well documented. Further, edited AI labels may be prone to automation bias. Purpose: In this pilot, using a cohort of CTs with intracavitary hemorrhage, we evaluate both time savings and AICL label quality and propose criteria that must be met for using AICL annotations as a high-throughput, high-quality ground truth. Methods: 57 CT scans of patients with traumatic intracavitary hemorrhage were included. No participant recruited for this study had previously interpreted the scans. nnU-net models trained on small existing datasets for each feature (hemothorax/hemoperitoneum/pelvic hematoma; n = 77-253) were used in inference. Two common scenarios served as baseline comparison- de novo expert manual labeling, and expert edits of trained staff labels. Parameters included time effort and image quality graded by a blinded independent expert using a 9-point scale. The observer also attempted to discriminate AICL and expert labels in a random subset (n = 18). Data were compared with ANOVA and post-hoc paired signed rank tests with Bonferroni correction. Results: AICL reduced time effort 2.8-fold compared to staff label editing, and 8.7-fold compared to expert labeling (corrected p < 0.0006). Mean Likert grades for AICL (8.4, SD:0.6) were significantly higher than for expert labels (7.8, SD:0.9) and edited staff labels (7.7, SD:0.8) (corrected p < 0.0006). The independent observer failed to correctly discriminate AI and human labels. Conclusion: For our use case and annotators, AICL facilitates rapid large-scale curation of high-quality ground truth. The proposed quality control regime can be employed by other investigators prior to embarking on AICL for segmentation tasks in large datasets.

Pulmonary contusion: automated deep learning-based quantitative visualization.

PURPOSE: Rapid automated CT volumetry of pulmonary contusion may predict progression to Acute Respiratory Distress Syndrome (ARDS) and help guide early clinical management in at-risk trauma patients. This study aims to train and validate state-of-the-art deep learning models to quantify pulmonary contusion as a percentage of total lung volume (Lung Contusion Index, or auto-LCI) and assess the relationship between auto-LCI and relevant clinical outcomes. METHODS: 302 adult patients (age ≥ 18) with pulmonary contusion were retrospectively identified from reports between 2016 and 2021. nnU-Net was trained on manual contusion and whole-lung segmentations. Point-of-care candidate variables for multivariate regression included oxygen saturation, heart rate, and systolic blood pressure on admission. Logistic regression was used to assess ARDS risk, and Cox proportional hazards models were used to determine differences in ICU length of stay and mechanical ventilation time. RESULTS: Mean Volume Similarity Index and mean Dice scores were 0.82 and 0.67. Interclass correlation coefficient and Pearson r between ground-truth and predicted volumes were 0.90 and 0.91. 38 (14%) patients developed ARDS. In bivariate analysis, auto-LCI was associated with ARDS (p < 0.001), ICU admission (p < 0.001), and need for mechanical ventilation (p < 0.001). In multivariate analyses, auto-LCI was associated with ARDS (p = 0.04), longer length of stay in the ICU (p = 0.02) and longer time on mechanical ventilation (p = 0.04). AUC of multivariate regression to predict ARDS using auto-LCI and clinical variables was 0.70 while AUC using auto-LCI alone was 0.68. CONCLUSION: Increasing auto-LCI values corresponded with increased risk of ARDS, longer ICU admissions, and longer periods of mechanical ventilation.

A vendor-agnostic, PACS integrated, and DICOMcompatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow.

Background: Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation. Purpose: In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow. Methods: Our end-to-end automated pipeline has two major components-1. a router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Feasibility is demonstrated by recording clock times for a traumatic pelvic hematoma cascaded nnU-net model. Results: Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 minutes 32 seconds (+/- SD of 1 min 26 sec). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 minutes. Inference times accounted for most of the total clock time, ranging from 2 minutes 41 seconds to 8 minutes 27 seconds. All other virtual and on-premises host steps combined ranged from a minimum of 34 seconds to a maximum of 48 seconds. Conclusion: The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/", and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.

Artificial intelligence CAD tools in trauma imaging: a scoping review from the American Society of Emergency Radiology (ASER) AI/ML Expert Panel.

BACKGROUND: AI/ML CAD tools can potentially improve outcomes in the high-stakes, high-volume model of trauma radiology. No prior scoping review has been undertaken to comprehensively assess tools in this subspecialty. PURPOSE: To map the evolution and current state of trauma radiology CAD tools along key dimensions of technology readiness. METHODS: Following a search of databases, abstract screening, and full-text document review, CAD tool maturity was charted using elements of data curation, performance validation, outcomes research, explainability, user acceptance, and funding patterns. Descriptive statistics were used to illustrate key trends. RESULTS: A total of 4052 records were screened, and 233 full-text articles were selected for content analysis. Twenty-one papers described FDA-approved commercial tools, and 212 reported algorithm prototypes. Works ranged from foundational research to multi-reader multi-case trials with heterogeneous external data. Scalable convolutional neural network-based implementations increased steeply after 2016 and were used in all commercial products; however, options for explainability were narrow. Of FDA-approved tools, 9/10 performed detection tasks. Dataset sizes ranged from < 100 to > 500,000 patients, and commercialization coincided with public dataset availability. Cross-sectional torso datasets were uniformly small. Data curation methods with ground truth labeling by independent readers were uncommon. No papers assessed user acceptance, and no method included human-computer interaction. The USA and China had the highest research output and frequency of research funding. CONCLUSIONS: Trauma imaging CAD tools are likely to improve patient care but are currently in an early stage of maturity, with few FDA-approved products for a limited number of uses. The scarcity of high-quality annotated data remains a major barrier.

A survey of ASER members on artificial intelligence in emergency radiology: trends, perceptions, and expectations.

PURPOSE: There is a growing body of diagnostic performance studies for emergency radiology-related artificial intelligence/machine learning (AI/ML) tools; however, little is known about user preferences, concerns, experiences, expectations, and the degree of penetration of AI tools in emergency radiology. Our aim is to conduct a survey of the current trends, perceptions, and expectations regarding AI among American Society of Emergency Radiology (ASER) members. METHODS: An anonymous and voluntary online survey questionnaire was e-mailed to all ASER members, followed by two reminder e-mails. A descriptive analysis of the data was conducted, and results summarized. RESULTS: A total of 113 members responded (response rate 12%). The majority were attending radiologists (90%) with greater than 10 years' experience (80%) and from an academic practice (65%). Most (55%) reported use of commercial AI CAD tools in their practice. Workflow prioritization based on pathology detection, injury or disease severity grading and classification, quantitative visualization, and auto-population of structured reports were identified as high-value tasks. Respondents overwhelmingly indicated a need for explainable and verifiable tools (87%) and the need for transparency in the development process (80%). Most respondents did not feel that AI would reduce the need for emergency radiologists in the next two decades (72%) or diminish interest in fellowship programs (58%). Negative perceptions pertained to potential for automation bias (23%), over-diagnosis (16%), poor generalizability (15%), negative impact on training (11%), and impediments to workflow (10%). CONCLUSION: ASER member respondents are in general optimistic about the impact of AI in the practice of emergency radiology and its impact on the popularity of emergency radiology as a subspecialty. The majority expect to see transparent and explainable AI models with the radiologist as the decision-maker.

Blunt splenic injury in adults: Association between volumetric quantitative CT parameters and intervention.

Several ordinal grading systems are used in deciding whether to perform angioembolization (AE) or splenectomy following blunt splenic injury (BSI). The 2018 American Association for the Surgery of Trauma (AAST) Organ Injury Scale incorporates vascular lesions but not hemoperitoneum, which is considered in the Thompson classifier. Granular and verifiable quantitative measurements of these features may have a future role in facilitating objective decision making. The purpose of this study is to compare performance of computed tomography (CT) volumetry-based quantitative modeling to the 1994 and 2018 AAST Organ Injury Scale and Thompson classifier for the following endpoints: decision to perform splenectomy (SPY), and the composite of SPY or AE. Adult BSI patients (age ≥18 years) scanned with dual-phase CT prior to intervention at a single Level I trauma center from 2017 to 2019 were included in this retrospective study (n = 174). Scoring using 2018 AAST, 1994 AAST, and Thompson systems was performed retrospectively by two radiologists and arbitrated by a third. Endpoints included (1) SPY and (2) the composite of SPY or AE. Logistic regression models were developed from segmented active bleed, contained vascular lesion, splenic parenchymal disruption, and hemoperitoneum volumes. Area under the receiver operating characteristic curve (AUC) for ordinal systems and volumetric models were compared. Forty-seven BSI patients (27%) underwent SPY, and 87 patients (50%) underwent SPY or AE. Quantitative model AUCs (0.85­SPY, 0.82­composite) were not significantly different from 2018 AAST AUCs (0.81, 0.88, p = 0.66, 0.14) for both endpoints and were significantly improved over Thompson scoring (0.76, p = 0.02; 0.77, p = 0.04). Quantitative CT volumetry can be used to model intervention for BSI with accuracy comparable to 2018 AAST scoring and significantly higher than Thompson scoring. Prognostic and Epidemiological; Level IV.

Toward automated interpretable AAST grading for blunt splenic injury.

BACKGROUND: The American Association for the Surgery of Trauma (AAST) splenic organ injury scale (OIS) is the most frequently used CT-based grading system for blunt splenic trauma. However, reported inter-rater agreement is modest, and an algorithm that objectively automates grading based on transparent and verifiable criteria could serve as a high-trust diagnostic aid. PURPOSE: To pilot the development of an automated interpretable multi-stage deep learning-based system to predict AAST grade from admission trauma CT. METHODS: Our pipeline includes 4 parts: (1) automated splenic localization, (2) Faster R-CNN-based detection of pseudoaneurysms (PSA) and active bleeds (AB), (3) nnU-Net segmentation and quantification of splenic parenchymal disruption (SPD), and (4) a directed graph that infers AAST grades from detection and segmentation results. Training and validation is performed on a dataset of adult patients (age ≥ 18) with voxelwise labeling, consensus AAST grading, and hemorrhage-related outcome data (n = 174). RESULTS: AAST classification agreement (weighted κ) between automated and consensus AAST grades was substantial (0.79). High-grade (IV and V) injuries were predicted with accuracy, positive predictive value, and negative predictive value of 92%, 95%, and 89%. The area under the curve for predicting hemorrhage control intervention was comparable between expert consensus and automated AAST grading (0.83 vs 0.88). The mean combined inference time for the pipeline was 96.9 s. CONCLUSIONS: The results of our method were rapid and verifiable, with high agreement between automated and expert consensus grades. Diagnosis of high-grade lesions and prediction of hemorrhage control intervention produced accurate results in adult patients.

CT of Sacral Fractures: Classification Systems and Management.

CT is often performed as part of a whole-body protocol in the setting of polytrauma and is the standard of care for diagnosing and characterizing sacral fractures. These fractures are not uncommon, occurring in conjunction with pelvic ring disruption in approximately 40%-50% of patients. Knowledge of basic functional anatomy and fracture biomechanics is important in understanding sacral fracture patterns, which only rarely result from direct impact. More often, sacral fractures result from an indirect mechanism with fracture lines that propagate along relative lines of weakness, leading to predictable fracture patterns. Each fracture pattern has implications with respect to neurologic injury, spinopelvic stability, management, and potential complications. The authors explore the Denis, Roy-Camille, Isler, Robles, Sabiston-Wing, and shape-based classification systems for sacral fractures. These form the basis of the subsequently discussed unified AOSpine sacral fracture classification, a consensus system developed by spine and orthopedic surgeons as a means of improving and standardizing communication. The AOSpine sacral fracture classification also includes clinical designations for neurologic status and patient-specific modifiers. When a patient is unexaminable owing to obtundation or sedation, CT is an invaluable indirect marker of nerve compression or traction injury. It also plays an important role in visualizing and characterizing the type and extent of any associated soft-tissue injuries that may warrant a delay in surgery or an alternative operative approach. ©RSNA, 2022.

Blunt splenic injury: Assessment of follow-up CT utility using quantitative volumetry.

Purpose: Trials of non-operative management (NOM) have become the standard of care for blunt splenic injury (BSI) in hemodynamically stable patients. However, there is a lack of consensus regarding the utility of follow-up CT exams and relevant CT features. The purpose of this study is to determine imaging predictors of splenectomy on follow-up CT using quantitative volumetric measurements. Methods: Adult patients who underwent a trial of non-operative management (NOM) with follow-up CT performed for BSI between 2017 and 2019 were included (n = 51). Six patients (12% of cohort) underwent splenectomy; 45 underwent successful splenic salvage. Voxelwise measurements of splenic laceration, hemoperitoneum, and subcapsular hematoma were derived from portal venous phase images of admission and follow-up scans using 3D slicer. Presence/absence of pseudoaneurysm on admission and follow-up CT was assessed using arterial phase images. Multivariable logistic regression was used to determine independent predictors of decision to perform splenectomy. Results: Factors significantly associated with splenectomy in bivariate analysis incorporated in multivariate logistic regression included final hemoperitoneum volume (p = 0.003), final subcapsular hematoma volume (p = 0.001), change in subcapsular hematoma volume between scans (p = 0.09) and new/persistent pseudoaneurysm (p = 0.003). Independent predictors of splenectomy in the logistic regression were final hemoperitoneum volume (unit OR = 1.43 for each 100 mL change; 95% CI: 0.99-2.06) and new/persistent pseudoaneurysm (OR = 160.3; 95% CI: 0.91-28315.3). The AUC of the model incorporating both variables was significantly higher than AAST grading (0.91 vs. 0.59, p = 0.025). Mean combined effective dose for admission and follow up CT scans was 37.4 mSv. Conclusion: Follow-up CT provides clinically valuable information regarding the decision to perform splenectomy in BSI patients managed non-operatively. Hemoperitoneum volume and new or persistent pseudoaneurysm at follow-up are independent predictors of splenectomy.

A pilot study of deep learning-based CT volumetry for traumatic hemothorax.

PURPOSE: We employ nnU-Net, a state-of-the-art self-configuring deep learning-based semantic segmentation method for quantitative visualization of hemothorax (HTX) in trauma patients, and assess performance using a combination of overlap and volume-based metrics. The accuracy of hemothorax volumes for predicting a composite of hemorrhage-related outcomes - massive transfusion (MT) and in-hospital mortality (IHM) not related to traumatic brain injury - is assessed and compared to subjective expert consensus grading by an experienced chest and emergency radiologist. MATERIALS AND METHODS: The study included manually labeled admission chest CTs from 77 consecutive adult patients with non-negligible (≥ 50 mL) traumatic HTX between 2016 and 2018 from one trauma center. DL results of ensembled nnU-Net were determined from fivefold cross-validation and compared to individual 2D, 3D, and cascaded 3D nnU-Net results using the Dice similarity coefficient (DSC) and volume similarity index. Pearson's r, intraclass correlation coefficient (ICC), and mean bias were also determined for the best performing model. Manual and automated hemothorax volumes and subjective hemothorax volume grades were analyzed as predictors of MT and IHM using AUC comparison. Volume cut-offs yielding sensitivity or specificity ≥ 90% were determined from ROC analysis. RESULTS: Ensembled nnU-Net achieved a mean DSC of 0.75 (SD: ± 0.12), and mean volume similarity of 0.91 (SD: ± 0.10), Pearson r of 0.93, and ICC of 0.92. Mean overmeasurement bias was only 1.7 mL despite a range of manual HTX volumes from 35 to 1503 mL (median: 178 mL). AUC of automated volumes for the composite outcome was 0.74 (95%CI: 0.58-0.91), compared to 0.76 (95%CI: 0.58-0.93) for manual volumes, and 0.76 (95%CI: 0.62-0.90) for consensus expert grading (p = 0.93). Automated volume cut-offs of 77 mL and 334 mL predicted the outcome with 93% sensitivity and 90% specificity respectively. CONCLUSION: Automated HTX volumetry had high method validity, yielded interpretable visual results, and had similar performance for the hemorrhage-related outcomes assessed compared to manual volumes and expert consensus grading. The results suggest promising avenues for automated HTX volumetry in research and clinical care.

Dual-Energy CT and Cinematic Rendering to Improve Assessment of Pelvic Fracture Instability.

Background Grading of pelvic fracture instability is challenging in patients with pelvic binders. Dual-energy CT (DECT) and cinematic rendering can provide ancillary information regarding osteoligamentous integrity, but the utility of these tools remains unknown. Purpose To assess the added diagnostic value of DECT and cinematic rendering, with respect to single-energy CT (SECT), for discriminating any instability and translational instability in patients with pelvic binders. Materials and Methods In this retrospective analysis, consecutive adult patients (age ≥18 years) were stabilized with pelvic binders and scanned in dual-energy mode using a 128-section CT scanner at one level I trauma center between August 2016 and January 2019. Young-Burgess grading by orthopedists served as the reference standard. Two radiologists performed blinded consensus grading with the Young-Burgess system in three reading sessions (session 1, SECT; session 2, SECT plus DECT; session 3, SECT plus DECT and cinematic rendering). Lateral compression (LC) type 1 (LC-1) and anteroposterior compression (APC) type 1 (APC-1) injuries were considered stable; LC type 2 and APC type 2, rotationally unstable; and LC type 3, APC type 3, and vertical shear, translationally unstable. Diagnostic performance for any instability and translational instability was compared between reading sessions using the McNemar and DeLong tests. Radiologist agreement with the orthopedic reference standard was calculated with the weighted κ statistic. Results Fifty-four patients (mean age, 41 years ± 16 [SD]; 41 men) were analyzed. Diagnostic performance was greater with SECT plus DECT and cinematic rendering compared with SECT alone for any instability, with an area under the receiver operating characteristic curve (AUC) of 0.67 for SECT alone and 0.82 for SECT plus DECT and cinematic rendering (P = .04); for translational instability, the AUCs were 0.80 for SECT alone and 0.95 for SECT plus DECT and cinematic rendering (P = .01). For any instability, corresponding sensitivities were 61% (22 of 36 patients) for SECT alone and 86% (31 of 36 patients) for SECT plus DECT and cinematic rendering (P < .001). The corresponding specificities were 72% (13 of 18 patients) and 78% (14 of 18 patients), respectively (P > .99). Agreement (κ value) between radiologists and orthopedist reference standard improved from 0.44 to 0.76 for SECT versus the combination of SECT, DECT, and cinematic rendering. Conclusion Combined use of single-energy CT, dual-energy CT, and cinematic rendering improved instability assessment over that with single-energy CT alone. © RSNA, 2022 Online supplemental material is available for this article.

Roles of Trauma CT and CTA in Salvaging the Threatened or Mangled Extremity.

Extremity arterial injuries account for up to 50% of all arterial traumas. The speed, accuracy, reproducibility, and close proximity of modern CT scanners to the trauma bay have led to the liberal use of CT angiography (CTA) when a limb is in ischemic jeopardy or is a potential source of life-threatening hemorrhage. The radiologist plays a critical role in the rapid communication of findings related to vessel transection and occlusion. Another role of CT that is often overlooked involves adding value to surgical planning. The following are some of the key questions addressed in this review: How does CTA help determine whether a limb is salvageable? How do concurrent multisystem injuries affect decision making? Which arterial injuries can be safely managed with observation alone? What damage control techniques are used to address compartment syndrome and hemorrhage? What options are available for definitive revascularization? Ideally, the radiologist should be familiar with the widely used Gustilo-Anderson open-fracture classification system, which was developed to prognosticate the likelihood of a functional limb salvage on the basis of soft-tissue and bone loss. When functional salvage is feasible or urgent hemorrhage control is required, communication with trauma surgeon colleagues is augmented by an understanding of the unique surgical, endovascular, and hybrid approaches available for each anatomic region of the upper and lower extremities. The radiologist should also be familiar with the common postoperative appearances of staged vascular, orthopedic, and plastic reconstructions for efficient clinically relevant reporting of potential down-range complications. Online supplemental material is available for this article. ©RSNA, 2022.

External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation With Limited Data.

The spleen is one of the most commonly injured solid organs in blunt abdominal trauma. The development of automatic segmentation systems from multi-phase CT for splenic vascular injury can augment severity grading for improving clinical decision support and outcome prediction. However, accurate segmentation of splenic vascular injury is challenging for the following reasons: 1) Splenic vascular injury can be highly variant in shape, texture, size, and overall appearance; and 2) Data acquisition is a complex and expensive procedure that requires intensive efforts from both data scientists and radiologists, which makes large-scale well-annotated datasets hard to acquire in general. In light of these challenges, we hereby design a novel framework for multi-phase splenic vascular injury segmentation, especially with limited data. On the one hand, we propose to leverage external data to mine pseudo splenic masks as the spatial attention, dubbed external attention, for guiding the segmentation of splenic vascular injury. On the other hand, we develop a synthetic phase augmentation module, which builds upon generative adversarial networks, for populating the internal data by fully leveraging the relation between different phases. By jointly enforcing external attention and populating internal data representation during training, our proposed method outperforms other competing methods and substantially improves the popular DeepLab-v3+ baseline by more than 7% in terms of average DSC, which confirms its effectiveness.

POCS-Augmented CycleGAN for MR Image Reconstruction.

Recent years have seen increased research interest in replacing the computationally intensive Magnetic resonance (MR) image reconstruction process with deep neural networks. We claim in this paper that the traditional image reconstruction methods and deep learning (DL) are mutually complementary and can be combined to achieve better image reconstruction quality. To test this hypothesis, a hybrid DL image reconstruction method was proposed by combining a state-of-the-art deep learning network, namely a generative adversarial network with cycle loss (CycleGAN), with a traditional data reconstruction algorithm: Projection Onto Convex Set (POCS). The output of the first iteration's training results of the CycleGAN was updated by POCS and used as the extra training data for the second training iteration of the CycleGAN. The method was validated using sub-sampled Magnetic resonance imaging data. Compared with other state-of-the-art, DL-based methods (e.g., U-Net, GAN, and RefineGAN) and a traditional method (compressed sensing), our method showed the best reconstruction results.

Improving Sensitivity of Arterial Spin Labeling Perfusion MRI in Alzheimer's Disease Using Transfer Learning of Deep Learning-Based ASL Denoising.

BACKGROUND: Arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI) denoising through deep learning (DL) often faces insufficient training data from patients. One solution is to train DL models using healthy subjects' data which are more widely available and transfer them to patients' data. PURPOSE: To evaluate the transferability of a DL-based ASL MRI denoising method (DLASL). STUDY TYPE: Retrospective. SUBJECTS: Four hundred and twenty-eight subjects (189 females) from three cohorts. FIELD STRENGTH/SEQUENCE: 3 T two-dimensional (2D) echo-planar imaging (EPI)-based pseudo-continuous ASL (PCASL) and 2D EPI-based pulsed ASL (PASL) sequences. ASSESSMENT: DLASL was trained using young healthy adults' PCASL data (Dataset 1: 250/30 subjects as training/validation set) and was directly transferred (DTF) to PCASL data from Dataset 2 (45 subjects test set) of normal controls (NC) and Alzheimer's disease (AD) groups. DLASL was fine-tuned (DLASLFT) and tested on PASL data from Dataset 3 (103 subjects test set) of NC and AD. An existing non-DL method (NonDL) was used for comparison. Cerebral blood flow (CBF) images from ASL MRI were compared between NC and AD to assess characteristic hypoperfusion (lower CBF) patterns in AD. CBF image quality and CBF map sensitivity for detecting hypoperfusion using peak t-value and suprathreshold cluster size are outcome measures. STATISTICAL TESTS: Paired t-test, two-sample t-test, one-way analysis of variance, and Tukey honestly significant difference, and linear mixed-effects models were used. P < 0.05 was considered statistically significant. RESULTS: Mean contrast-to-noise ratio (CNR) of Dataset 2 showed that DTF outperformed NonDL (AD: 3.38 vs. 2.64, NC: 3.80 vs. 3.36). On Dataset 3, DLASLFT outperformed NonDL measured by mean CNR (AD: 2.45 vs. 1.87, NC: 2.54 vs. 2.17) and mean radiologic score (2.86 vs. 2.44). Image quality improvement was significant on both test sets. DTF and DLASLFT improved sensitivity for detecting AD-related hypoperfusion patterns compared with NonDL. DATA CONCLUSION: We demonstrated the DLASL's transferability across different ASL sequences and different populations. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Postoperative Computed Tomography for Facial Fractures.

In order for a radiologist to create reports that are meaningful to facial reconstructive surgeons, an understanding of the principles that guide surgical management and the hardware employed is imperative. This article is intended to promote efficient and salient reporting by illustrating surgical approaches and rationale. Hardware selection can be inferred and a defined set of potential complications anticipated when assessing the adequacy of surgical reconstruction on postoperative computed tomography for midface, internal orbital, and mandible fractures.

CT of Skull Base Fractures: Classification Systems, Complications, and Management.

As advances in prehospital and early hospital care improve survival of the head-injured patient, radiologists are increasingly charged with understanding the myriad skull base fracture management implications conferred by CT. Successfully parlaying knowledge of skull base anatomy and fracture patterns into precise actionable clinical recommendations is a challenging task. The authors aim to provide a pragmatic overview of CT for skull base fractures within the broader context of diagnostic and treatment planning algorithms. Laterobasal, frontobasal, and posterior basal fracture patterns are emphasized. CT often plays a complementary, supportive, or confirmatory role in management of skull base fractures in conjunction with results of physical examination, laboratory testing, and neurosensory evaluation. CT provides prognostic information about short- and long-term risk of cerebrospinal fluid (CSF) leak, encephalocele, meningitis, facial nerve paralysis, hearing and vision loss, cholesteatoma, vascular injuries, and various cranial nerve palsies and syndromes. The radiologist should leverage understanding of specific strengths and limitations of CT to anticipate next steps in the skull base fracture management plan. Additional imaging is warranted to clarify ambiguity (particularly for potential sources of CSF leak); in other cases, clinical and CT criteria alone are sufficient to determine the need for intervention and the choice of surgical approach. The radiologist should be able to envision stepping into a multidisciplinary planning discussion and engaging neurotologists, neuro-ophthalmologists, neurosurgeons, neurointerventionalists, and facial reconstructive surgeons to help synthesize an optimal management plan after reviewing the skull base CT findings at hand. Online supplemental material is available for this article. ©RSNA, 2021.