Search

Fueled by new techniques, computational tools, and broader availability of imaging data, artificial intelligence has the potential to transform the practice of neuroradiology. The recent exponential increase in publications related to artificial intelligence and the central focus on artificial intelligence at recent professional and scientific radiology meetings underscores the importance. There is growing momentum behind leveraging artificial intelligence techniques to improve workflow and diagnosis and treatment and to enhance the value of quantitative imaging techniques. This article explores the reasons why neuroradiologists should care about the investments in new artificial intelligence applications, highlights current activities and the roles neuroradiologists are playing, and renders a few predictions regarding the near future of artificial intelligence in neuroradiology.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence . This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate the performance of the winning machine learning (ML) models from the 2023 RSNA Abdominal Trauma Detection Artificial Intelligence Challenge. Materials and Methods The competition was hosted on Kaggle and took place between July 26, 2023, to October 15, 2023. The multicenter competition dataset consisted of 4,274 abdominal trauma CT scans in which solid organs (liver, spleen and kidneys) were annotated as healthy, low-grade or high-grade injury. Studies were labeled as positive or negative for the presence of bowel/mesenteric injury and active extravasation. In this study, performances of the 8 award-winning models were retrospectively assessed and compared using various metrics, including the area under the receiver operating characteristic curve (AUC), for each injury category. The reported mean values of these metrics were calculated by averaging the performance across all models for each specified injury type. Results The models exhibited strong performance in detecting solid organ injuries, particularly high-grade injuries. For binary detection of injuries, the models demonstrated mean AUC values of 0.92 (range:0.91-0.94) for liver, 0.91 (range:0.87-0.93) for splenic, and 0.94 (range:0.93-0.95) for kidney injuries. The models achieved mean AUC values of 0.98 (range:0.96-0.98) for high-grade liver, 0.98 (range:0.97-0.99) for high-grade splenic, and 0.98 (range:0.97-0.98) for high-grade kidney injuries. For the detection of bowel/mesenteric injuries and active extravasation, the models demonstrated mean AUC values of 0.85 (range:0.74-0.73) and 0.85 (range:0.79-0.89) respectively. Conclusion The award-winning models from the AI challenge demonstrated strong performance in the detection of traumatic abdominal injuries on CT scans, particularly high-grade injuries. These models may serve as a performance baseline for future investigations and algorithms. ©RSNA, 2024.

Supplemental material is available for this article.

Purpose To evaluate the performance of the top models from the RSNA 2022 Cervical Spine Fracture Detection challenge on a clinical test dataset of both noncontrast and contrast-enhanced CT scans acquired at a level I trauma center. Materials and Methods Seven top-performing models in the RSNA 2022 Cervical Spine Fracture Detection challenge were retrospectively evaluated on a clinical test set of 1828 CT scans (from 1829 series: 130 positive for fracture, 1699 negative for fracture; 1308 noncontrast, 521 contrast enhanced) from 1779 patients (mean age, 55.8 years ± 22.1 [SD]; 1154 [64.9%] male patients). Scans were acquired without exclusion criteria over 1 year (January-December 2022) from the emergency department of a neurosurgical and level I trauma center. Model performance was assessed using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. False-positive and false-negative cases were further analyzed by a neuroradiologist. Results Although all seven models showed decreased performance on the clinical test set compared with the challenge dataset, the models maintained high performances. On noncontrast CT scans, the models achieved a mean AUC of 0.89 (range: 0.79-0.92), sensitivity of 67.0% (range: 30.9%-80.0%), and specificity of 92.9% (range: 82.1%-99.0%). On contrast-enhanced CT scans, the models had a mean AUC of 0.88 (range: 0.76-0.94), sensitivity of 81.9% (range: 42.7%-100.0%), and specificity of 72.1% (range: 16.4%-92.8%). The models identified 10 fractures missed by radiologists. False-positive cases were more common in contrast-enhanced scans and observed in patients with degenerative changes on noncontrast scans, while false-negative cases were often associated with degenerative changes and osteopenia. Conclusion The winning models from the 2022 RSNA AI Challenge demonstrated a high performance for cervical spine fracture detection on a clinical test dataset, warranting further evaluation for their use as clinical support tools. Keywords: Feature Detection, Supervised Learning, Convolutional Neural Network (CNN), Genetic Algorithms, CT, Spine, Technology Assessment, Head/Neck Supplemental material is available for this article. © RSNA, 2024 See also commentary by Levi and Politi in this issue.

The Radiological Society of North of America (RSNA) and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society have led a series of joint panels and seminars focused on the present impact and future directions of artificial intelligence (AI) in radiology. These conversations have collected viewpoints from multidisciplinary experts in radiology, medical imaging, and machine learning on the current clinical penetration of AI technology in radiology and how it is impacted by trust, reproducibility, explainability, and accountability. The collective points-both practical and philosophical-define the cultural changes for radiologists and AI scientists working together and describe the challenges ahead for AI technologies to meet broad approval. This article presents the perspectives of experts from MICCAI and RSNA on the clinical, cultural, computational, and regulatory considerations-coupled with recommended reading materials-essential to adopt AI technology successfully in radiology and, more generally, in clinical practice. The report emphasizes the importance of collaboration to improve clinical deployment, highlights the need to integrate clinical and medical imaging data, and introduces strategies to ensure smooth and incentivized integration. Keywords: Adults and Pediatrics, Computer Applications-General (Informatics), Diagnosis, Prognosis © RSNA, 2024.

The Radiological Society of North America (RSNA) has held artificial intelligence competitions to tackle real-world medical imaging problems at least annually since 2017. This article examines the challenges and processes involved in organizing these competitions, with a specific emphasis on the creation and curation of high-quality datasets. The collection of diverse and representative medical imaging data involves dealing with issues of patient privacy and data security. Furthermore, ensuring quality and consistency in data, which includes expert labeling and accounting for various patient and imaging characteristics, necessitates substantial planning and resources. Overcoming these obstacles requires meticulous project management and adherence to strict timelines. The article also highlights the potential of crowdsourced annotation to progress medical imaging research. Through the RSNA competitions, an effective global engagement has been realized, resulting in innovative solutions to complex medical imaging problems, thus potentially transforming health care by enhancing diagnostic accuracy and patient outcomes. Keywords: Use of AI in Education, Artificial Intelligence © RSNA, 2024.

Purpose To evaluate and report the performance of the winning algorithms of the Radiological Society of North America Cervical Spine Fracture AI Challenge. Materials and Methods The competition was open to the public on Kaggle from July 28 to October 27, 2022. A sample of 3112 CT scans with and without cervical spine fractures (CSFx) were assembled from multiple sites (12 institutions across six continents) and prepared for the competition. The test set had 1093 scans (private test set: n = 789; mean age, 53.40 years ± 22.86 [SD]; 509 males; public test set: n = 304; mean age, 52.51 years ± 20.73; 189 males) and 847 fractures. The eight top-performing artificial intelligence (AI) algorithms were retrospectively evaluated, and the area under the receiver operating characteristic curve (AUC) value, F1 score, sensitivity, and specificity were calculated. Results A total of 1108 contestants composing 883 teams worldwide participated in the competition. The top eight AI models showed high performance, with a mean AUC value of 0.96 (95% CI: 0.95, 0.96), mean F1 score of 90% (95% CI: 90%, 91%), mean sensitivity of 88% (95% Cl: 86%, 90%), and mean specificity of 94% (95% CI: 93%, 96%). The highest values reported for previous models were an AUC of 0.85, F1 score of 81%, sensitivity of 76%, and specificity of 97%. Conclusion The competition successfully facilitated the development of AI models that could detect and localize CSFx on CT scans with high performance outcomes, which appear to exceed known values of previously reported models. Further study is needed to evaluate the generalizability of these models in a clinical environment. Keywords: Cervical Spine, Fracture Detection, Machine Learning, Artificial Intelligence Algorithms, CT, Head/Neck Supplemental material is available for this article. © RSNA, 2024.

In spite of an exponential increase in the volume of medical data produced globally, much of these data are inaccessible to those who might best use them to develop improved health care solutions through the application of advanced analytics such as artificial intelligence. Data liberation and crowdsourcing represent two distinct but interrelated approaches to bridging existing data silos and accelerating the pace of innovation internationally. In this article, we examine these concepts in the context of medical artificial intelligence research, summarizing their potential benefits, identifying potential pitfalls, and ultimately making a case for their expanded use going forward. A practical example of a crowdsourced competition using an international medical imaging dataset is provided. Keywords: Artificial Intelligence, Data Liberation, Crowdsourcing © RSNA, 2023.

MRI scanner hardware, field strengths, and sequence parameters are major variables in diffusion studies of the spinal cord. Reliability between scanners is not well known, particularly for the thoracic cord. DTI data was collected for the entire cervical and thoracic spinal cord in thirty healthy adult subjects with different MR vendors and field strengths. DTI metrics were extracted and averaged for all slices within each vertebral level. Metrics were examined for variability and then harmonized using longitudinal ComBat (longComBat). Four scanners were used: Siemens 3 T Prisma, Siemens 1.5 T Avanto, Philips 3 T Ingenia, Philips 1.5 T Achieva. Average full cord diffusion values/standard deviation for all subjects and scanners were FA: 0.63, σ = 0.10, MD: 1.11, σ = 0.12 × 10 -3 mm 2 /s, AD: 1.98, σ = 0.55 × 10 -3 mm 2 /s, RD: 0.67, σ = 0.31 × 10 -3 mm 2 /s. FA metrics averaged for all subjects by level were relatively consistent across scanners, but large variability was found in diffusivity measures. Coefficients of variation were lowest in the cervical region, and relatively lower for FA than diffusivity measures. Harmonized metrics showed greatly improved agreement between scanners. Variability in DTI of the spinal cord arises from scanner hardware differences, pulse sequence differences, physiological motion, and subject compliance. The use of longComBat resulted in large improvement in agreement of all DTI metrics between scanners. This study shows the importance of harmonization of diffusion data in the spinal cord and potential for longitudinal and multisite clinical research and clinical trials., (© 2023. The Author(s).)

In this review, concepts of algorithmic bias and fairness are defined qualitatively and mathematically. Illustrative examples are given of what can go wrong when unintended bias or unfairness in algorithmic development occurs. The importance of explainability, accountability, and transparency with respect to artificial intelligence algorithm development and clinical deployment is discussed. These are grounded in the concept of "primum no nocere" (first, do no harm). Steps to mitigate unfairness and bias in task definition, data collection, model definition, training, testing, deployment, and feedback are provided. Discussions on the implementation of fairness criteria that maximize benefit and minimize unfairness and harm to neuroradiology patients will be provided, including suggestions for neuroradiologists to consider as artificial intelligence algorithms gain acceptance into neuroradiology practice and become incorporated into routine clinical workflow., (© 2023 by American Journal of Neuroradiology.)

This dataset is composed of cervical spine CT images with annotations related to fractures; it is available at https://www.kaggle.com/competitions/rsna-2022-cervical-spine-fracture-detection/., Competing Interests: Disclosures of conflicts of interest: H.M.L. No relevant relationships. E.C. No relevant relationships. T.R. No relevant relationships. F.C.K. Consultant for MD.ai and GE HealthCare; member of the Radiological Society of North America (RSNA) Machine Learning Steering Committee member and the Society for Imaging Informatics in Medicine Machine Learning Education Subcommittee (both unpaid). L.M.P. Associate editor for Radiology: Artificial Intelligence; patents planned, issued, or pending: US-20220051060-A1, “Methods for creating privacy-protecting synthetic data leveraging a constrained generative ensemble model,” and US-20220051402-A1, “Systems for automated lesion detection and related methods.” J.T. Provided expert witness deposition for Phillips, Spallas, & Angstadt in October 2022, unrelated to this article. R.L.B. Support from RSNA to author. E.G. No relevant relationships. K.W.Y. No relevant relationships. M.H. No relevant relationships. A.L.S. Author’s lab receives funding from the National Institutes of Health (NIH); member of the advisory board for the National Cancer Institute Imaging Data Commons. J.S. No relevant relationships. D.B. No relevant relationships. S.A. No relevant relationships. A.P.L. No relevant relationships. M.I.G.A. No relevant relationships. J.O.J. No relevant relationships. J.J.P. Author’s lab receives funding from the NIH, which pays this author’s salary. M.L. No relevant relationships. H.D. No relevant relationships. E.A. No relevant relationships. A.Y. No relevant relationships. Y.M. No relevant relationships. J.K.C. Grants or contracts from GE HealthCare and Genentech; technology licensed to Boston AI; consulting fees from Siloam Vision; deputy editor of Radiology: Artificial Intelligence. A.E.F. Standing director, liaison for information technology, of RSNA board of directors; member of RSNA News editorial board., (© 2023 by the Radiological Society of North America, Inc.)

Deep learning (DL) models can harness electronic health records (EHRs) to predict diseases and extract radiologic findings for diagnosis. With ambulatory chest radiographs (CXRs) frequently ordered, we investigated detecting type 2 diabetes (T2D) by combining radiographic and EHR data using a DL model. Our model, developed from 271,065 CXRs and 160,244 patients, was tested on a prospective dataset of 9,943 CXRs. Here we show the model effectively detected T2D with a ROC AUC of 0.84 and a 16% prevalence. The algorithm flagged 1,381 cases (14%) as suspicious for T2D. External validation at a distinct institution yielded a ROC AUC of 0.77, with 5% of patients subsequently diagnosed with T2D. Explainable AI techniques revealed correlations between specific adiposity measures and high predictivity, suggesting CXRs' potential for enhanced T2D screening., (© 2023. The Author(s).)

Objective: The clinical behavior of meningiomas is not entirely captured by its designated WHO grade, therefore other factors must be elucidated that portend increased tumor aggressiveness and associated risk of recurrence. In this study, the authors identify multiparametric MRI radiomic signatures of meningiomas using Ki-67 as a prognostic marker of clinical outcomes independent of WHO grade., Methods: A retrospective analysis was conducted of all resected meningiomas between 2012 and 2018. Preoperative MR images were used for high-throughput radiomic feature extraction and subsequently used to develop a machine learning algorithm to stratify meningiomas based on Ki-67 indices < 5% and ≥ 5%, independent of WHO grade. Progression-free survival (PFS) was assessed based on machine learning prediction of Ki-67 strata and compared with outcomes based on histopathological Ki-67., Results: Three hundred forty-three meningiomas were included: 291 with WHO grade I, 43 with grade II, and 9 with grade III. The overall rate of recurrence was 19.8% (15.1% in grade I, 44.2% in grade II, and 77.8% in grade III) over a median follow-up of 28.5 months. Grade II and III tumors had higher Ki-67 indices than grade I tumors, albeit tumor and peritumoral edema volumes had considerable variation independent of meningioma WHO grade. Forty-six high-performing radiomic features (1 morphological, 7 intensity-based, and 38 textural) were identified and used to build a support vector machine model to stratify tumors based on a Ki-67 cutoff of 5%, with resultant areas under the curve of 0.83 (95% CI 0.78-0.89) and 0.84 (95% CI 0.75-0.94) achieved for the discovery (n = 257) and validation (n = 86) data sets, respectively. Comparison of histopathological Ki-67 versus machine learning-predicted Ki-67 showed excellent performance (overall accuracy > 80%), with classification of grade I meningiomas exhibiting the greatest accuracy. Prediction of Ki-67 by machine learning classifier revealed shorter PFS for meningiomas with Ki-67 indices ≥ 5% compared with tumors with Ki-67 < 5% (p < 0.0001, log-rank test), which corroborates divergent patient outcomes observed using histopathological Ki-67., Conclusions: The Ki-67 proliferation index may serve as a surrogate marker of increased meningioma aggressiveness independent of WHO grade. Machine learning using radiomic feature analysis may be used for the preoperative prediction of meningioma Ki-67, which provides enhanced analytical insights to help improve diagnostic classification and guide patient-specific treatment strategies.

Rationale and Objectives: Computed tomography (CT) is preferred for evaluating solitary pulmonary nodules (SPNs) but access or availability may be lacking, in addition, overlapping anatomy can hinder detection of SPNs on chest radiographs. We developed and evaluated the clinical feasibility of a deep learning algorithm to generate digitally reconstructed tomography (DRT) images of the chest from digitally reconstructed frontal and lateral radiographs (DRRs) and use them to detect SPNs., Methods: This single-institution retrospective study included 637 patients with noncontrast helical CT of the chest (mean age 68 years, median age 69 years, standard deviation 11.7 years; 355 women) between 11/2012 and 12/2020, with SPNs measuring 10-30 mm. A deep learning model was trained on 562 patients, validated on 60 patients, and tested on the remaining 15 patients. Diagnostic performance (SPN detection) from planar radiography (DRRs and CT scanograms, PR) alone or with DRT was evaluated by two radiologists in an independent blinded fashion. The quality of the DRT SPN image in terms of nodule size and location, morphology, and opacity was also evaluated, and compared to the ground-truth CT images RESULTS: Diagnostic performance was higher from DRT plus PR than from PR alone (area under the receiver operating characteristic curve 0.95-0.98 versus 0.80-0.85; p < 0.05). DRT plus PR enabled diagnosis of SPNs in 11 more patients than PR alone. Interobserver agreement was 0.82 for DRT plus PR and 0.89 for PR alone; and interobserver agreement for size and location, morphology, and opacity of the DRT SPN was 0.94, 0.68, and 0.38, respectively., Conclusion: For SPN detection, DRT plus PR showed better diagnostic performance than PR alone. Deep learning can be used to generate DRT images and improve detection of SPNs., (Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing., (© 2022. The Author(s).)

Study Design: This investigation was a cohort study that included: 36 typically developing (TD) children and 19 children with spinal cord lesions who underwent spinal cord MRI., Objectives: To investigate diffusion tensor imaging (DTI) cervical and thoracic spinal cord changes in pediatric patients that have clinically traumatic and non-traumatic spinal cord injury (SCI) without MR (SCIWOMR) abnormalities., Setting: Thomas Jefferson University, Temple University, Shriners Hospitals for Children all in Philadelphia, USA., Methods: 36 TD children and 19 children with spinal cord lesions that represent either a chronic traumatic acquired SCI or chronic non-traumatic SCI (≥6 months post injury), age range, 6-16 years who underwent cervical and thoracic spinal cord MRI in 2014-2017. Additionally DTI was correlated to clinical American Spinal Injury Association Impairment Scale (AIS)., Results: Both SCIWOMR and MRI positive (+) groups showed abnormal FA and RD DTI values in the adjacent MRI-normal appearing segments of cephalad and caudal spinal cord compared to TD. The FA values demonstrated perilesional abnormal DTI findings in the middle and proximal segments of the cephalad and caudal cord in the SCIWOMR AIS A/B group compared to SCIWOMR AIS C/D group., Conclusions: We found DTI changes in children with SCIWOMR with different causes of spinal lesions. We also investigated the relationship between DTI and clinical AIS scores. This study further examined the potential diagnostic value of DTI and should be translatable to adults with spinal cord lesions., (© 2022. The Author(s), under exclusive licence to International Spinal Cord Society.)

Background and Purpose: Multi-parametric MRI, provides a variety of biomarkers sensitive to white matter integrity, However, spinal cord MRI data in pediatrics is rare compared to adults. The purpose of this work was 3-fold: 1) to develop a processing pipeline for atlas-based generation of the typically developing pediatric spinal cord WM tracts, 2) to derive atlas-based normative values of the DTI indices for various WM pathways, and 3) to investigate age-related changes in the obtained normative DTI indices along the extracted tracts., Materials and Methods: DTI scans of 30 typically developing subjects (age range, 6-16 years) were acquired on a 3T MR imaging scanner. The data were registered to the PAM50 template in the Spinal Cord Toolbox. Next, the DTI indices for various WM regions were extracted at a single section centered at the C3 vertebral body in all the 30 subjects. Finally, an ANOVA test was performed to examine the effects of the following: 1) laterality, 2) functionality, and 3) age, with DTI-derived indices in 34 extracted WM regions., Results: A postprocessing pipeline was developed and validated to delineate pediatric spinal cord WM tracts. The results of ANOVA on fractional anisotropy values showed no effect for laterality ( P  = .72) but an effect for functionality ( P < .001) when comparing the 30 primary WM labels. There was a significant ( P  < .05) effect of age and maturity of the left spinothalamic tract on mean diffusivity, radial diffusivity, and axial diffusivity values., Conclusions: The proposed automated pipeline in this study incorporates unique postprocessing steps followed by template registration and quantification of DTI metrics using atlas-based regions. This method eliminates the need for manual ROI analysis of WM tracts and, therefore, increases the accuracy and speed of the measurements., (© 2021 by American Journal of Neuroradiology.)

Rationale and Objectives: The clinical prognosis of outpatients with coronavirus disease 2019 (COVID-19) remains difficult to predict, with outcomes including asymptomatic, hospitalization, intubation, and death. Here we determined the prognostic value of an outpatient chest radiograph, together with an ensemble of deep learning algorithms predicting comorbidities and airspace disease to identify patients at a higher risk of hospitalization from COVID-19 infection., Materials and Methods: This retrospective study included outpatients with COVID-19 confirmed by reverse transcription-polymerase chain reaction testing who received an ambulatory chest radiography between March 17, 2020 and October 24, 2020. In this study, full admission was defined as hospitalization within 14 days of the COVID-19 test for > 2 days with supplemental oxygen. Univariate analysis and machine learning algorithms were used to evaluate the relationship between the deep learning model predictions and hospitalization for > 2 days., Results: The study included 413 patients, 222 men (54%), with a median age of 51 years (interquartile range, 39-62 years). Fifty-one patients (12.3%) required full admission. A boosted decision tree model produced the best prediction. Variables included patient age, frontal chest radiograph predictions of morbid obesity, congestive heart failure and cardiac arrhythmias, and radiographic opacity, with an internally validated area under the curve (AUC) of 0.837 (95% CI: 0.791-0.883) on a test cohort., Conclusion: Deep learning analysis of single frontal chest radiographs was used to generate combined comorbidity and pneumonia scores that predict the need for supplemental oxygen and hospitalization for > 2 days in patients with COVID-19 infection with an AUC of 0.837 (95% confidence interval: 0.791-0.883). Comorbidity scoring may prove useful in other clinical scenarios., (Copyright © 2021 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Background and Purpose: The National Institute of Neurological Disorders and Stroke common data elements initiative was created to provide a consistent method for recording and reporting observations related to neurologic diseases in clinical trials. The purpose of this study is to validate the subset of common data elements related to MR imaging evaluation of acute spinal cord injury., Materials and Methods: Thirty-five cervical and thoracic MR imaging studies of patients with acute spinal cord injury were evaluated independently in 2 rounds by 5 expert reviewers. Intra- and interrater agreement were calculated for 17 distinct MR imaging observations related to spinal cord injury. These included ordinal, categoric, and continuous measures related to the length and location of spinal cord hemorrhage and edema as well as spinal canal and cord measurements. Level of agreement was calculated using the interclass correlation coefficient and kappa., Results: The ordinal common data elements spinal cord injury elements for lesion center and rostral or caudal extent of edema or hemorrhage demonstrated agreement ranging from interclass correlation coefficient 0.68 to 0.99. Reproducibility ranged from 0.95 to 1.00. Moderate agreement was observed for absolute length of hemorrhage and edema (0.54 to 0.60) with good reproducibility (0.78 to 0.83). Agreement for the Brain and Spinal Injury Center score showed the lowest interrater agreement with an overall kappa of 0.27 (0.20, 0.34). For 7 of the 8 variables related to spinal cord injury, agreement improved between the first and second evaluation. Continuous diameter measures of the spinal cord and spinal canal using interclass correlation coefficient varied substantially (0.23 to 0.83)., Conclusions: Agreement was more consistent for the ordinal measures of spinal cord injury than continuous measures. Good to excellent agreement on length and location of spinal cord hemorrhage and edema can be achieved with ordinal measures alone., (© 2021 by American Journal of Neuroradiology.)

Background and Purpose: Prior research has shown substantial shifts in procedure shares between specialty groups providing lumbar punctures. Our aim was to analyze national trends in lumbar punctures among the Medicare population from 2010 to 2018., Materials and Methods: Medicare Part B Physician/Supplier Procedure Summary Master Files from 2010 to 2018 were analyzed for all Current Procedural Terminology, Version 4 codes related to lumbar punctures (62270 and 62272). Lumbar puncture procedure volume and utilization rates were assessed and stratified by place of service and specialty background of the providers., Results: From 2010 to 2018, the overall number of lumbar puncture procedures essentially has not changed (92,579 versus 92,533). Radiologists hold the largest and an increasing procedure share of diagnostic and overall lumbar punctures (overall share, 45.7% in 2010 [ n  = 42,296] versus 52.3% in 2018 [ n  = 48,414]). Advanced practice providers have increased their procedure share (3.7% in 2010 [ n  = 3388] versus 8.4% in 2018 [ n  = 7785], + 129.8% procedure volume). Emergency medicine physicians and neurologists have a decreasing procedure share (21.8% versus 15.3% and 12.5% versus 8.8%, respectively). The inpatient hospital setting remains the largest place of service for lumbar punctures, recording a 5.3% increase in procedure share. The emergency department lumbar puncture volume has declined, with a 7.4% decrease in the overall procedure share. Similarly, the hospital outpatient department procedure volume has increased (+4%), while the private office volume has decreased (-1.7%)., Conclusions: During the past decade, lumbar puncture procedures among the Medicare population have remained stable, with a shift in procedure volume from the emergency department and private offices to the hospital setting, which has mainly affected radiologists and advanced practice providers., (© 2021 by American Journal of Neuroradiology.)

In recent years the concept of precision medicine has become a popular topic particularly in medical oncology. Besides the identification of new molecular prognostic and predictive biomarkers and the development of new targeted and immunotherapeutic drugs, imaging has started to play a central role in this new era. Terms such as "radiomics", "radiogenomics" or "radi…-omics" are becoming increasingly common in the literature and soon they will represent an integral part of clinical practice. The use of artificial intelligence, imaging and "-omics" data can be used to develop models able to predict, for example, the features of the tumor immune microenvironment through imaging, and to monitor the therapeutic response beyond the standard radiological criteria. The aims of this narrative review are to provide a simplified guide for clinicians to these concepts, and to summarize the existing evidence on radiomics and "radi…-omics" in cancer immunotherapy., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Fueled by new techniques, computational tools, and broader availability of imaging data, artificial intelligence has the potential to transform the practice of neuroradiology. The recent exponential increase in publications related to artificial intelligence and the central focus on artificial intelligence at recent professional and scientific radiology meetings underscores the importance. There is growing momentum behind leveraging artificial intelligence techniques to improve workflow and diagnosis and treatment and to enhance the value of quantitative imaging techniques. This article explores the reasons why neuroradiologists should care about the investments in new artificial intelligence applications, highlights current activities and the roles neuroradiologists are playing, and renders a few predictions regarding the near future of artificial intelligence in neuroradiology., (© 2020 by American Journal of Neuroradiology.)

The appropriate imaging of patients with headache presents a number of important and vexing challenges for clinicians. Despite a number of guidelines and studies demonstrating a lack of cost-effectiveness, clinicians continue to image patients with chronic nonfocal headaches, and the trend toward imaging is increasing. The reasons are complex and include the fear of missing a clinically significant lesion and litigation, habitual and standard of care practices, lack of tort reform, regulatory penalties and potential impact on one's professional reputation, patient pressures, and financial motivation. Regulatory and legislative reforms are needed to encourage best practices without fear of professional sanctions when following the guidelines. The value of negative findings on imaging tests requires better understanding because they appear to provide some measure of societal value. Clinical decision support tools and machine intelligence may offer additional guidance and improve quality and cost-efficient management of this challenging patient population., (© 2020 by American Journal of Neuroradiology.)

This dataset is composed of annotations of the five hemorrhage subtypes (subarachnoid, intraventricular, subdural, epidural, and intraparenchymal hemorrhage) typically encountered at brain CT., Competing Interests: Disclosures of Conflicts of Interest: A.E.F. disclosed no relevant relationships. L.M.P. Activities related to the present article: institution receives time-limited loaner access by OSU AI Lab to NVIDIA GPUs via Master Research Agreement between The Ohio State University and NVIDIA, no money transfer; time-limited access by OSU AI Lab to WIP postprocessing software via Master Research Agreement between OSU and Siemens Healthineers. No money transfer; unrestrictive support of OSU AI Lab by DeBartolo Family Funds. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. G.S. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: board member and shareholder of MD.ai but no money paid to author or MD.ai. Other relationships: disclosed no relevant relationships. S.S.H. disclosed no relevant relationships. J.K. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: author is consultant for INFOTECH, Soft; institution receives grants from Genentech and GE. Other relationships: disclosed no relevant relationships. R.B. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: previously employed by Roam Analytics (employment ended prior to working on this study); stockholder in Roam Analytics. Other relationships: disclosed no relevant relationships. J.T.M. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: consultant for Siemens (PAMA clinical decision support related); institution receives grants from GE (past and pending grants related to PTX detection); author may receive future royalties from GE related to PTX AI detector licensed to GE. Other relationships: disclosed no relevant relationships. A.S. Activities related to the present article: employee and shareholder in MD.ai. Activities not related to the present article: employee and shareholder in MD.ai. Other relationships: disclosed no relevant relationships. F.C.K. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: consultant for MD.ai; employed by Diagnósticos da América (DASA). Other relationships: disclosed no relevant relationships. M.P.L. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: consultant for and stockholder in Nines, SegMed, and Bunker Hill. Other relationships: disclosed no relevant relationships. G.C. disclosed no relevant relationships. L. Cala disclosed no relevant relationships. L. Coelho disclosed no relevant relationships. M.M. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: consultant for Cerebrotech Medical Systems. Other relationships: disclosed no relevant relationships. F.M. disclosed no relevant relationships. E.M. disclosed no relevant relationships. I.I. disclosed no relevant relationships. V.Z. disclosed no relevant relationships. O.M. disclosed no relevant relationships. C.L. disclosed no relevant relationships. L.S. disclosed no relevant relationships. D.J. disclosed no relevant relationships. A.A. disclosed no relevant relationships. R.K.L. disclosed no relevant relationships. J.N. disclosed no relevant relationships., (2020 by the Radiological Society of North America, Inc.)

The aim of this study is to determine the strength and accuracy of diffusion tensor imaging (DTI) parameters to predict neurological injury and recovery in adult cervical spinal cord injury (SCI). DTI magnetic resonance imaging (MRI) was performed on 23 acute cervical SCI patients within 12 h after injury and on 45 controls utilizing a rapid DTI sequence (∼5 min). Neurological assessments were conducted from within 24 h of injury up to 6 months utilizing detailed International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI) examinations. Spearman correlation and receiver operating characteristic (ROC) analysis were used to identify relationships between the DTI parameters at the lesion epicenter and adjacent regions, with injury severity and recovery. In proximity to the anatomical injury (within one level above and below epicenter), there was significant reduction in fractional anisotropy (FA), and elevation in mean diffusivity (MD) and radial diffusivity (RD). DTI values measured one level rostral to the injury epicenter showed stronger correlations with multiple clinical features at several time-points. Area under the curve (AUC) obtained from ROC analysis showed FA (AUC = 0.77) measured at lesion epicenter, and FA (0.83), MD (0.76), and RD (0.83) values measured immediately rostral (one level above) to epicenter discriminate injury severity. Further, MD (0.78) measured at lesion epicenter, and MD (0.79) and RD (0.74) values measured immediately rostral to epicenter discriminate neurological recovery. DTI indices measured immediately rostral to the anatomical level of injury consistently showed better correlation (moderate to strong) and accuracy in predicting neurological injury (FA, r = -0.51 and RD, r = 0.54) and recovery (MD, r = -0.51) than indices measured at the epicenter. There was weak to moderate correlation of all measures at lesion epicenter in predicting neurological injury (FA: r = -0.48; MD: r = 0.23; RD: r = 0.34; axial diffusivity [AD]: r = 0.02) and recovery (FA: r = 0.27; MD: r = -0.44; RD: r = -0.35; AD: r = -0.34).

Traumatic spinal cord injury (SCI) leads to immediate neuronal and axonal damage at the focal injury site and triggers secondary pathologic series of events resulting in sensorimotor and autonomic dysfunction below the level of injury. Although there is no cure for SCI, neuroprotective and regenerative therapies show promising results at the preclinical stage. There is a pressing need to develop non-invasive outcome measures that can indicate whether a candidate therapeutic agent or a cocktail of therapeutic agents are positively altering the underlying disease processes. Recent conventional MRI studies have quantified spinal cord lesion characteristics and elucidated their relationship between severity of injury to clinical impairment and recovery. Next to the quantification of the primary cord damage, quantitative MRI measures of spinal cord (rostrocaudally to the lesion site) and brain integrity have demonstrated progressive and specific neurodegeneration of afferent and efferent neuronal pathways. MRI could therefore play a key role to ultimately uncover the relationship between clinical impairment/recovery and injury-induced neurodegenerative changes in the spinal cord and brain. Moreover, neuroimaging biomarkers hold promises to improve clinical trial design and efficiency through better patient stratification. The purpose of this narrative review is therefore to propose a guideline of clinically available MRI sequences and their derived neuroimaging biomarkers that have the potential to assess tissue damage at the macro- and microstructural level after SCI. In this piece, we make a recommendation for the use of key MRI sequences-both conventional and advanced-for clinical work-up and clinical trials.

The 2018 RSNA Summit on AI in Radiology brought together a diverse group of stakeholders to identify and prioritize areas of need related to artificial intelligence in radiology. This article presents the proceedings of the summit with emphasis on RSNA's role in leading, organizing, and catalyzing change during this important time in radiology. © RSNA, 2019., Competing Interests: Disclosures of Conflicts of Interest: F.H.C. disclosed no relevant relationships. A.E.F. disclosed no relevant relationships. L.M.P. disclosed no relevant relationships. C.P.L. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: consultant for whiterabbit.ai (retainer paid for service on medical advisory board); received stock options for service on medical advisory boards from Nines.ai, whiterabbit.ai, Bunker Hill, and Galileo CDS. Other relationships: disclosed no relevant relationships., (2019 by the Radiological Society of North America, Inc.)

In recent years, there has been enormous interest in applying artificial intelligence (AI) to radiology. Although some of this interest may have been driven by exaggerated expectations that the technology can outperform radiologists in some tasks, there is a growing body of evidence that illustrates its limitations in medical imaging. The true potential of the technique probably lies somewhere in the middle, and AI will ultimately play a key role in medical imaging in the future. The limitless power of computers makes AI an ideal candidate to provide the standardization, consistency, and dependability needed to support radiologists in their mission to provide excellent patient care. However, important roadblocks currently limit the expansion of this field in medical imaging. This article reviews some of the challenges and potential solutions to advance the field forward, with focus on the experience gained by hosting image-based competitions., (2019 by the Radiological Society of North America, Inc.)

The American Society of Neuroradiology has teamed up with the American College of Radiology and the Radiological Society of North America to create a catalog of neuroradiology common data elements that addresses specific clinical use cases. Fundamentally, a common data element is a question, concept, measurement, or feature with a set of controlled responses. This could be a measurement, subjective assessment, or ordinal value. Common data elements can be both machine- and human-generated. Rather than redesigning neuroradiology reporting, the goal is to establish the minimum number of "essential" concepts that should be in a report to address a clinical question. As medicine shifts toward value-based service compensation methodologies, there will be an even greater need to benchmark quality care and allow peer-to-peer comparisons in all specialties. Many government programs are now focusing on these measures, the most recent being the Merit-Based Incentive Payment System and the Medicare Access Children's Health Insurance Program Reauthorization Act of 2015. Standardized or structured reporting is advocated as one method of assessing radiology report quality, and common data elements are a means for expressing these concepts. Incorporating common data elements into clinical practice fosters a number of very useful downstream processes including establishing benchmarks for quality-assurance programs, ensuring more accurate billing, improving communication to providers and patients, participating in public health initiatives, creating comparative effectiveness research, and providing classifiers for machine learning. Generalized adoption of the recommended common data elements in clinical practice will provide the means to collect and compare imaging report data from multiple institutions locally, regionally, and even nationally, to establish quality benchmarks., (© 2019 by American Journal of Neuroradiology.)

Providing a fast and accurate diagnosis of acute large-vessel occlusion on computed tomography angiograms (CTAs) is essential for timely intervention and good stroke outcomes. However, the detection and appropriate management of incidental findings are also important parts of any clinical radiology practice and can greatly affect patient care. The intricate anatomy covered by CTAs of the head and neck coupled with the time pressures of acute stroke diagnosis creates an environment in which unrelated, important findings can potentially be missed. The purpose of our study was to document clinically actionable incidental findings on CTA in 225 patients undergoing acute stroke intervention. After institutional review board approval, a retrospective six-year review of CTAs of the head and neck in patients undergoing acute stroke intervention was performed for actionable incidental vascular and nonvascular findings. A total of 225 patients undergoing acute stroke intervention with documented intracranial large-vessel occlusion on CTAs were consecutively enrolled in the study. Incidental vascular findings were identified in 17 of 225 patients (7.5%, 95% confidence interval 5% to 12%). Previously unreported aneurysms ranging from 2 mm to 10 mm in size represented 18 of 19 vascular findings in these patients. Incidental nonvascular findings were identified in 32 patients (14%, 95% confidence interval 5% to 12%). These included malpositioned support lines and tubes; pneumothorax; interstitial lung disease; newly diagnosed metastatic disease; nasopharyngeal, parotid, and pituitary masses; and cervical spine compression fractures. CTAs of the head and neck in patients undergoing acute stroke intervention contain a relatively high frequency of vascular and nonvascular incidental findings requiring further follow-up, and therefore should be evaluated carefully and systematically.

The purpose of this study was to evaluate an improved and reliable visualization method for pediatric spinal cord MR images in healthy subjects and patients with spinal cord injury (SCI). A total of 15 pediatric volunteers (10 healthy subjects and 5 subjects with cervical SCI) with a mean age of 11.41 years (range 8-16 years) were recruited and scanned using a 3.0T Siemens Verio MR scanner. T2-weighted axial images were acquired covering entire cervical spinal cord level C1 to C7. These gray-scale images were then converted to color images by using five different techniques including hue-saturation-value (HSV), rainbow, red-green-blue (RGB), and two enhanced RGB techniques using automated contrast stretching and intensity inhomogeneity correction. Performance of these techniques was scored visually by two neuroradiologists within three selected cervical spinal cord intervertebral disk levels (C2-C3, C4-C5, and C6-C7) and quantified using signal to noise ratio (SNR) and contrast to noise ratio (CNR). Qualitative and quantitative evaluation of the color images shows consistent improvement across all the healthy and SCI subjects over conventional gray-scale T2-weighted gradient echo (GRE) images. Inter-observer reliability test showed moderate to strong intra-class correlation (ICC) coefficients in the proposed techniques (ICC > 0.73). The results suggest that the color images could be used for quantification and enhanced visualization of the spinal cord structures in addition to the conventional gray-scale images. This would immensely help towards improved delineation of the gray/white and CSF structures and further aid towards accurate manual or automatic drawings of region of interests (ROIs).

Background and Purpose: The zonally magnified oblique multislice EPI (ZOOM-EPI) diffusion-weighted sequence has been visually shown to provide superior MR diffusion image quality compared with the full-FOV single-shot EPI sequence (non-ZOOM-EPI) in the adult cervical spinal cord. The purpose of this study was to examine the diffusion tensor imaging indices in the normal human cervical spinal cord between ZOOMED and non-ZOOMED DTI acquisitions and determine whether DTI values are comparable between direct and indirect age-matched groups., Materials and Methods: Fifty-four subjects 23-58 years of age (9 direct age-matched and 45 indirect age-matched) were scanned using a 1.5T scanner. Diffusion tensor indices including fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity were generated from the DTI dataset. These DTI values were calculated for both ZOOM and non-ZOOM acquisitions and compared at each intervertebral disc level. The variability of the DTI values for ZOOM and non-ZOOM sequences was measured using a coefficient of variation within direct and indirect age-matched controls., Results: The mean diffusivity, axial diffusivity, and radial diffusivity values obtained along the cervical spinal cord in the age-matched controls showed a significant decrease using the ZOOM sequence ( P = .05, P = .002, and P < .001). Mean fractional anisotropy showed a significant increase ( P = .04) using the ZOOM sequence. The indirect age-matched controls showed a statistically significant increase in fractional anisotropy ( P = .03) and a decrease in mean diffusivity ( P = .002), axial diffusivity ( P < .001), and radial diffusivity ( P = .002) using the ZOOM sequence. Less variability has been shown in DTI using the ZOOM sequence compared with the non-ZOOM sequence in both direct and indirect age groups. The ZOOM sequence exhibited higher SNR (SNR ZOOM = 22.84 ± 7.59) compared with the non-ZOOM sequence (SNR non-ZOOM = 19.7 ± 7.05). However, when we used a 2-tailed t test assuming unequal variances, the ZOOM sequence did not demonstrate a statistically significant increase., Conclusions: ZOOM DTI acquisition methods provide superior image quality and precision over non-ZOOM techniques and are recommended over conventional full-FOV single-shot EPI DTI for clinical applications in cervical spinal cord imaging., (© 2018 by American Journal of Neuroradiology.)

Background and Objective: Diffusion tensor imaging (DTI) and diffusion tensor tractography (DTT) are two techniques that can measure white matter integrity of the spinal cord. Recently, DTI indices have been shown to change with age. The purpose of this study is (a) to evaluate the maturational states of the entire pediatric spinal cord using DTI and DTT indices including fractional anisotropy (FA), mean diffusivity (MD), mean length of white matter fiber tracts and tract density and (b) to analyze the DTI and DTT parameters along the entire spinal cord as a function of spinal cord levels and age., Method: A total of 23 typically developing (TD) pediatric subjects ranging in age from 6 to 16 years old (11.94 ± 3.26 (mean ± standard deviation), 13 females and 10 males) were recruited, and scanned using 3.0 T MR scanner. Reduced FOV diffusion tensor images were acquired axially in the same anatomical location prescribed for the T2-weighted images to cover the entire spinal cord (C1-mid L1 levels). To mitigate motion induced artifacts, diffusion directional images were aligned with the reference image (b0) using a rigid body registration algorithm performed by in-house software developed in Matlab (MathWorks, Natick, Massachusetts). Diffusion tensor maps (FA and MD) and streamline deterministic tractography were then generated from the motion corrected DTI dataset. DTI and DTT parameters were calculated by using ROIs drawn to encapsulate the whole cord along the entire spinal cord by an independent board certified neuroradiologist. These indices then were compared between two age groups (age group A = 6-11 years ( n  = 11) and age group B = 12-16 years ( n  = 12)) based on similar standards and age definitions used for reporting spinal cord injury in the pediatric population. Standard least squared linear regression based on a restricted maximum likelihood (REML) method was used to evaluate the relationship between age and DTI and DTT parameters., Results: An increase in FA (group A = 0.42 ± 0.097, group B = 0.49 ± 0.116), white matter tract density (group A = 368.01 ± 236.88, group B = 440.13 ± 245.24) and mean length of fiber tracts (group A = 48.16 ± 20.48 mm, group B = 60.28 ± 23.87 mm) and a decrease in MD (group A = 1.06 ± 0.23 × 10 -3  mm 2 /s, group B = 0.82 ± 0.24 × 10 -3  mm 2 /s) were observed with age along the entire spinal cord. Statistically significant increases have been shown in FA ( p  = 0.004, R 2  = 0.57), tract density ( p  = 0.0004, R 2  = 0.58), mean length of fiber tracts ( p  < 0.001, R 2  = 0.5) and a significant decrease has been shown in MD ( p  = 0.002, R 2  = 0.59) between group A and group B. Also, it has been shown DTI and DTT parameters vary along the spinal cord as a function of intervertebral disk and mid-vertebral body level., Conclusion: This study provides an initial understanding of age related changes of DTI values as well as DTT metrics of the spinal cord. The results show significant differences in DTI and DTT parameters which may result from decreasing water content, myelination of fiber tracts, and the thickening diameter of fiber tracts during the maturation process. Consequently, when quantitative DTI and DTT of the spinal cord is undertaken in the pediatric population an age and level matched normative dataset should be used to accurately interpret the quantitative results.

The aim of this study is to assess the utility and effectiveness of diffusion tensor imaging (DTI) and diffusion tensor tractography (DTT) of the entire pediatric cervical and thoracic spinal cord toward discrimination of typically developing (TD) controls and subjects with spinal cord injury (SCI). A total of 43 pediatric subjects, including 23 TD subjects ranging in age from 6 to 16 years old and 20 subjects with SCI ranging in age from 7 to 16 years, were recruited and scanned using a 3.0 Tesla magnetic resonance scanner. Reduced field of view diffusion tensor images were acquired axially to cover the entire spinal cord across two slabs. For DTI analysis, motion correction was performed by coregistration of the diffusion-weighted images to the reference image (b0). Streamline deterministic tractography results were generated from the preprocessed data. DTI and DTT parameters of the whole cord, including fractional anisotropy (FA), mean diffusivity (MD), tract length, and tract density, were calculated, averaged across the whole spinal cord, and compared between the TD and SCI groups. Statistically significant decreases have been shown in FA (TD = 0.46 ± 0.11; SCI = 0.37 ± 0.09; p < 0.0001) and tract density (TD = 405.93 ± 243.84; SCI = 268.90 ± 270.34; p < 0.0001). However, the mean length of tracts and MD did not show significant differences. When investigating differences in DTI and DTT parameters above and below the injury site, it was shown that the FA and tract density in patients with cervical SCI decreased significantly in the thoracic region. An identical trend was observed in the cervical region for patients with thoracic SCI as well. When comparing TD and SCI subjects, FA and tract density were the most sensitive parameters in detecting functional changes of the spinal cord in chronic pediatric SCI. The results show that both DTI and DTT have the potential to be imaging biomarkers in the diagnosis of SCI.

Purpose: Lower-grade gliomas (WHO grade II/III) have been classified into clinically relevant molecular subtypes based on IDH and 1p/19q mutation status. The purpose was to investigate whether T2/FLAIR MRI features could distinguish between lower-grade glioma molecular subtypes. Experimental Design: MRI scans from the TCGA/TCIA lower grade glioma database ( n = 125) were evaluated by two independent neuroradiologists to assess (i) presence/absence of homogenous signal on T2WI; (ii) presence/absence of "T2-FLAIR mismatch" sign; (iii) sharp or indistinct lesion margins; and (iv) presence/absence of peritumoral edema. Metrics with moderate-substantial agreement underwent consensus review and were correlated with glioma molecular subtypes. Somatic mutation, DNA copy number, DNA methylation, gene expression, and protein array data from the TCGA lower-grade glioma database were analyzed for molecular-radiographic associations. A separate institutional cohort ( n = 82) was analyzed to validate the T2-FLAIR mismatch sign. Results: Among TCGA/TCIA cases, interreader agreement was calculated for lesion homogeneity [ κ = 0.234 (0.111-0.358)], T2-FLAIR mismatch sign [ κ = 0.728 (0.538-0.918)], lesion margins [ κ = 0.292 (0.135-0.449)], and peritumoral edema [ κ = 0.173 (0.096-0.250)]. All 15 cases that were positive for the T2-FLAIR mismatch sign were IDH -mutant, 1p/19q non-codeleted tumors ( P < 0.0001; PPV = 100%, NPV = 54%). Analysis of the validation cohort demonstrated substantial interreader agreement for the T2-FLAIR mismatch sign [ κ = 0.747 (0.536-0.958)]; all 10 cases positive for the T2-FLAIR mismatch sign were IDH -mutant, 1p/19q non-codeleted tumors ( P < 0.00001; PPV = 100%, NPV = 76%). Conclusions: Among lower-grade gliomas, T2-FLAIR mismatch sign represents a highly specific imaging biomarker for the IDH -mutant, 1p/19q non-codeleted molecular subtype. Clin Cancer Res; 23(20); 6078-85. ©2017 AACR ., (©2017 American Association for Cancer Research.)

Background and Purpose: More than 75 million Americans have less than adequate health literacy skills according to the National Center for Education Statistics. Readability scores are used as a measure of how well populations read and understand patient education materials. The purpose of this study was to assess the readability of Web sites dedicated to patient education for radiologic spine imaging and interventions., Materials and Methods: Eleven search terms relevant to radiologic spine imaging were searched on the public Internet, and the top 10 links for each term were collected and analyzed to determine readability scores by using 10 well-validated quantitative readability assessments from patient-centered education Web sites. The search terms included the following: x-ray spine, CT spine, MR imaging spine, lumbar puncture, kyphoplasty, vertebroplasty, discogram, myelogram, cervical spine, thoracic spine, and lumbar spine., Results: Collectively, the 110 articles were written at an 11.3 grade level (grade range, 7.1-16.9). None of the articles were written at the American Medical Association and National Institutes of Health recommended 3rd-to-7th grade reading levels. The vertebroplasty articles were written at a statistically significant ( P < .05) more advanced level than the articles for x-ray spine, CT spine, and MR imaging spine., Conclusions: Increasing use of the Internet to obtain health information has made it imperative that on-line patient education be written for easy comprehension by the average American. However, given the discordance between readability scores of the articles and the American Medical Association and National Institutes of Health recommended guidelines, it is likely that many patients do not fully benefit from these resources., (© 2017 by American Journal of Neuroradiology.)

Objectives: To develop a comprehensive set of common data elements (CDEs), data definitions, case report forms and guidelines for use in spinal cord injury (SCI) clinical research, as part of the CDE project at the National Institute of Neurological Disorders and Stroke (NINDS) of the US National Institutes of Health., Setting: International Working Groups., Methods: Nine working groups composed of international experts reviewed existing CDEs and instruments, created new elements when needed and provided recommendations for SCI clinical research. The project was carried out in collaboration with and cross-referenced to development of the International Spinal Cord Society (ISCoS) International SCI Data Sets. The recommendations were compiled, subjected to internal review and posted online for external public comment. The final version was reviewed by all working groups and the NINDS CDE team before release., Results: The NINDS SCI CDEs and supporting documents are publically available on the NINDS CDE website and the ISCoS website. The CDEs span the continuum of SCI care and the full range of domains of the International Classification of Functioning, Disability and Health., Conclusion: Widespread use of CDEs can facilitate SCI clinical research and trial design, data sharing and retrospective analyses. Continued international collaboration will enable consistent data collection and reporting, and will help ensure that the data elements are updated, reviewed and broadcast as additional evidence is obtained.

Diagnostic radiology training programs must produce highly skilled diagnostic radiologists capable of interpreting radiological examinations and communicating results to clinicians. Established training performance tools evaluate interpretive skills, but trainees' competency in reporting skills is also essential. Our semi-automated passive electronic tool entitled the Quantitative Reporting Skills Evaluation (QRSE) allows radiology training programs to evaluate the quantity of edits made to trainee preliminary reports by attending physicians as a metric to evaluate trainee reporting performance. Consecutive report pairs and metadata extracted from the radiology information system were anonymized and exported to a MySQL database. To perform the QRSE, for each report pair, open source software was first utilized to calculate the Levenshtein Percent (LP), the percent of character changes required to convert each preliminary report to its corresponding final report. The average LP (ALP), ALP for each trainee, and standard deviations were calculated. Eighty-four trainees and 56 attending radiologists interpreted 228,543 radiological examinations during the study period. The overall ALP was 6.38 %. Trainee-specific ALPs ranged from 1.1 to 15.3 %. Among trainee-specific ALPs, the standard deviation was 3.7 %. Our analysis identified five trainees with trainee-specific ALPs above 2 standard deviations from the mean and 14 trainees with trainee-specific ALPs less than 1 standard deviation below the mean. The QRSE methodology allows for the passive, quantitative, and longitudinal evaluation of the reporting skills of trainees during diagnostic radiology residency training. The QRSE identifies trainees with high and low levels of edits to their preliminary reports, as a marker for trainee overall reporting skills, and thus represents a novel performance metric for radiology training programs.

Intracranial vertebral artery dissection (VAD) represents the underlying etiology in a significant percentage of posterior circulation ischemic strokes and subarachnoid hemorrhages. These lesions are particularly challenging in their diagnosis, management, and in the prediction of long-term outcome. Advances in the understanding of underlying processes leading to dissection, as well as the evolution of modern imaging techniques are discussed. The data pertaining to medical management of intracranial VADs, with emphasis on anticoagulants and antiplatelet agents, is reviewed. Surgical intervention is discussed, including, the selection of operative candidates, open and endovascular procedures, and potential complications. The evolution of endovascular technology and techniques is highlighted.

Attending radiologists routinely edit radiology trainee dictated preliminary reports as part of standard workflow models. Time constraints, high volume, and spatial separation may not always facilitate clear discussion of these changes with trainees. However, these edits can represent significant teaching moments that are lost if they are not communicated back to trainees. We created an electronic method for retrieving and displaying changes made to resident written preliminary reports by attending radiologists during the process of radiology report finalization. The Radiology Information System is queried. Preliminary and final radiology reports, as well as report metadata, are extracted and stored in a database indexed by accession number and trainee/radiologist identity. A web application presents to trainees their 100 most recent preliminary and final report pairs both side by side and in a "track changes" mode. Web utilization audits showed regular utilization by trainees. Surveyed residents stated they compared reports for educational value, to improve future reports, and to improve patient care. Residents stated that they compared reports more frequently after deployment of this software solution and that regular assessment of their work using the Report Comparator allowed them to routinely improve future report quality and improved radiological understanding. In an era with increasing workload demands, trainee work hour restrictions, and decentralization of department resources (e.g., faculty, PACS), this solution helps to retain an important part of the educational experience that would have otherwise run the risk of being lost and provides it to the trainees in an efficient and highly consumable manner.