Deep Learning Reconstruction Enables Prospectively Accelerated Clinical Knee MRI.

Background MRI is a powerful diagnostic tool with a long acquisition time. Recently, deep learning (DL) methods have provided accelerated high-quality image reconstructions from undersampled data, but it is unclear if DL image reconstruction can be reliably translated to everyday clinical practice. Purpose To determine the diagnostic equivalence of prospectively accelerated DL-reconstructed knee MRI compared with conventional accelerated MRI for evaluating internal derangement of the knee in a clinical setting. Materials and Methods A DL reconstruction model was trained with images from 298 clinical 3-T knee examinations. In a prospective analysis, patients clinically referred for knee MRI underwent a conventional accelerated knee MRI protocol at 3 T followed by an accelerated DL protocol between January 2020 and February 2021. The equivalence of the DL reconstruction of the images relative to the conventional images for the detection of an abnormality was assessed in terms of interchangeability. Each examination was reviewed by six musculoskeletal radiologists. Analyses pertaining to the detection of meniscal or ligament tears and bone marrow or cartilage abnormalities were based on four-point ordinal scores for the likelihood of an abnormality. Additionally, the protocols were compared with use of four-point ordinal scores for each aspect of image quality: overall image quality, presence of artifacts, sharpness, and signal-to-noise ratio. Results A total of 170 participants (mean age ± SD, 45 years ± 16; 76 men) were evaluated. The DL-reconstructed images were determined to be of diagnostic equivalence with the conventional images for detection of abnormalities. The overall image quality score, averaged over six readers, was significantly better (P < .001) for the DL than for the conventional images. Conclusion In a clinical setting, deep learning reconstruction enabled a nearly twofold reduction in scan time for a knee MRI and was diagnostically equivalent with the conventional protocol. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Roemer in this issue.

Designing Clinical MRI for Enhanced Workflow and Value.

MRI is an expensive and traditionally time-intensive modality in imaging. With the paradigm shift toward value-based healthcare, radiology departments must examine the entire MRI process cycle to identify opportunities to optimize efficiency and enhance value for patients. Digital tools such as "frictionless scheduling" prioritize patient preference and convenience, thereby delivering patient-centered care. Recent advances in conventional and deep learning-based accelerated image reconstruction methods have reduced image acquisition time to such a degree that so-called nongradient time now constitutes a major percentage of total room time. For this reason, architectural design strategies that reconfigure patient preparation processes and decrease the turnaround time between scans can substantially impact overall throughput while also improving patient comfort and privacy. Real-time informatics tools that provide an enterprise-wide overview of MRI workflow and Picture Archiving and Communication System (PACS)-integrated instant messaging can complement these efforts by offering transparent, situational data and facilitating communication between radiology team members. Finally, long-term investment in training, recruiting, and retaining a highly skilled technologist workforce is essential for building a pipeline and team of technologists committed to excellence. Here, we highlight various opportunities for optimizing MRI workflow and enhancing value by offering many of our own on-the-ground experiences and conclude by anticipating some of the future directions for process improvement and innovation in clinical MR imaging. EVIDENCE LEVEL: N/A TECHNICAL EFFICACY: Stage 1.

Artificial Intelligence for MR Image Reconstruction: An Overview for Clinicians.

Artificial intelligence (AI) shows tremendous promise in the field of medical imaging, with recent breakthroughs applying deep-learning models for data acquisition, classification problems, segmentation, image synthesis, and image reconstruction. With an eye towards clinical applications, we summarize the active field of deep-learning-based MR image reconstruction. We review the basic concepts of how deep-learning algorithms aid in the transformation of raw k-space data to image data, and specifically examine accelerated imaging and artifact suppression. Recent efforts in these areas show that deep-learning-based algorithms can match and, in some cases, eclipse conventional reconstruction methods in terms of image quality and computational efficiency across a host of clinical imaging applications, including musculoskeletal, abdominal, cardiac, and brain imaging. This article is an introductory overview aimed at clinical radiologists with no experience in deep-learning-based MR image reconstruction and should enable them to understand the basic concepts and current clinical applications of this rapidly growing area of research across multiple organ systems.

Anterior Shoulder Instability in the Aging Population: MRI Injury Pattern and Management.

BACKGROUND. Literature on glenohumeral dislocations has focused on younger patient populations because of high recurrence rates. However, the spectrum of injuries sustained in younger versus older patient populations is reported to be quite different. OBJECTIVE. The purpose of this article is to describe MRI findings and management of anterior shoulder instability in the aging (≥ 60 years) population. METHODS. Shoulder MRI examinations of anterior glenohumeral dislocations in patients 40 years old and older were subdivided into groups younger than 60 years old or 60 years old and older and reviewed by two musculoskeletal radiologists for a Hill-Sachs lesion, other fracture, glenoid injury, capsulolabral injury, rotator cuff tear, muscle atrophy, and axillary nerve injury. Fischer exact test and logistic regression was evaluated for significant differences between cohorts, and interreader agreement was assessed. Surgical management was recorded, if available. RESULTS. A total of 104 shoulder MRI examinations (age range, 40-79 years; mean age, 58.3 years; 52 women, 52 men) were reviewed (54 examinations < 60 years; 50 examinations ≥ 60 years). Acute high-grade or full-thickness supraspinatus (64.0% vs 37.0%; p = .001), infraspinatus (28.0% vs 14.8%; p = .03), and subscapularis (22.0% vs 3.7%; p = .003) tears were more common in the group 60 years old and older. Hill-Sachs lesions were more common in the younger group (81.5% vs 62.0%; p = .046). Greater tuberosity fractures were seen in 15.4% of the overall cohort, coracoid fractures in 4.8%, and acute axillary nerve injuries in 9.6%. Interreader concordance was 88.5-89.4% for rotator cuff tears and 89.4-97.1% for osseous injury. In the group younger than 60 years old, 11 of 37 subjects (29.7%) had rotator cuff repair and 11 of 37 (29.7%) had labral repair, whereas 17 of 36 (47.2%) of the older group underwent rotator cuff repair, six of 36 (16.7%) underwent reverse shoulder arthroplasty, and six of 36 (16.7%) underwent labral repair. CONCLUSION. Radiologists should have a high index of suspicion for acute rotator cuff tears in anterior shoulder instability, especially in aging populations. Greater tuberosity or coracoid fractures and axillary nerve injury occur across all ages, whereas Hill-Sachs injuries are more common in younger patients. CLINICAL IMPACT. Acute high-grade or full-thickness rotator cuff tears are seen with higher frequency in older populations after anterior glenohumeral dislocation. Osseous and nerve injuries are important causes of patient morbidity that if not carefully sought out may be overlooked by the interpreting radiologist on routine imaging.

Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study.

OBJECTIVE. Deep learning (DL) image reconstruction has the potential to disrupt the current state of MRI by significantly decreasing the time required for MRI examinations. Our goal was to use DL to accelerate MRI to allow a 5-minute comprehensive examination of the knee without compromising image quality or diagnostic accuracy. MATERIALS AND METHODS. A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multisequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. After training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully sampled data acquisition and a 1.88-fold acceleration compared with our standard twofold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of six readers to detect internal derangement of the knee was compared for clinical and DL-accelerated images. RESULTS. We found a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would produce discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence. CONCLUSION. An optimized DL model allowed acceleration of knee images that performed interchangeably with standard images for detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.

Pattern Recognition in Musculoskeletal Imaging Using Artificial Intelligence.

Artificial intelligence (AI) has the potential to affect every step of the radiology workflow, but the AI application that has received the most press in recent years is image interpretation, with numerous articles describing how AI can help detect and characterize abnormalities as well as monitor disease response. Many AI-based image interpretation tasks for musculoskeletal (MSK) pathologies have been studied, including the diagnosis of bone tumors, detection of osseous metastases, assessment of bone age, identification of fractures, and detection and grading of osteoarthritis. This article explores the applications of AI for image interpretation of MSK pathologies.

Supraspinatus muscle shear wave elastography (SWE): detection of biomechanical differences with varying tendon quality prior to gray-scale morphologic changes.

OBJECTIVE: The purpose of this study was to determine whether SWE can detect biomechanical changes in the supraspinatus muscle that occur with increasing supraspinatus tendon abnormality prior to morphologic gray-scale changes. MATERIALS AND METHODS: An IRB approved, HIPAA compliant retrospective study of shoulder ultrasounds from 2013-2018 was performed. The cohort consisted of 88 patients (mean age 55 ± 15 years old) with 110 ultrasounds. Images were acquired in longitudinal orientation to the supraspinatus muscle with shear wave velocity (SWV) point quantification. The tendon and muscle were graded in order of increasing tendinosis/tear (1-4 scale) and increasing fatty infiltration (0-3 scale). Mixed model analysis of variance, analysis of covariance, and Spearman rank correlation were used for statistical analysis. RESULTS: There was no statistically significant age or sex dependence for supraspinatus muscle SWV (p = 0.314, 0.118, respectively). There was no significant correlation between muscle SWV and muscle or tendon grade (p = 0.317, 0.691, respectively). In patients with morphologically normal muscle on gray-scale ultrasound, there were significant differences in muscle SWV when comparing tendon grade 3 with grades 1, 2, and 4 (p = 0.018, 0.025, 0.014, respectively), even when adjusting for gender and age (p = 0.044, 0.028, 0.018, respectively). Pairwise comparison of tendon grades other than those mentioned did not achieve statistical significance (p > 0.05). CONCLUSION: SWE can detect biomechanical differences within the supraspinatus muscle that are not morphologically evident on gray-scale ultrasound. Specifically, supraspinatus tendon partial tears with moderate to severe tendinosis may correspond to biomechanically distinct muscle properties compared to both lower grades of tendon abnormality and full-thickness tears.

Ulnar Collateral Ligament Insertional Injuries in Pediatric Overhead Athletes: Are MRI Findings Predictive of Symptoms or Need for Surgery?

OBJECTIVE: The purpose of this study was to determine whether ulnar collateral ligament (UCL) insertion below the articular margin (so-called T sign) exists in the pediatric population and whether MRI features can be used to identify insertional UCL injuries in overhead athletes that are symptomatic or require surgery. MATERIALS AND METHODS: Retrospective review of elbow MR images of patients younger than 21 years from 2011 to 2017 yielded 26 control subjects who were not overhead athletes and 97 overhead athletes. According to the clinical diagnosis, 50 of the overhead athletes had symptoms. Two radiologists evaluated the UCL for thickness, abnormal insertional signal intensity, insertion distance, and adjacent marrow or soft-tissue edema. Insertion distance was defined as the coronal length of any T sign measured from the articular margin. RESULTS: Mean insertion distance was greater in overhead athletes than in control subjects (1.42 vs 0.23 mm, p = 0.001) but not significantly different in athletes with symptoms compared with those without symptoms or in those who underwent operative treatment compared with those who did not. Mean UCL thickness was greater in overhead athletes than in control subjects (2.64 vs 1.74 mm, p < 0.0001), athletes with than those without symptoms (2.84 vs 2.41 mm, p = 0.005), and athletes who did versus those who did not undergo operative treatment (3.40 vs 2.73 mm, p = 0.011). Marrow (p = 0.002) and soft-tissue (p = 0.016) edema were found more frequently in athletes with symptoms. ROC analysis of UCL thickness and insertion distance as predictors of symptoms showed AUCs of 0.69 and 0.49, respectively. CONCLUSION: The T sign is likely not an anatomic variation but is a poor predictor of symptoms and need for surgery. Soft-tissue and marrow edema are more frequently seen in overhead athletes with symptomatic injuries and can aid in the diagnosis of clinically relevant injury.

Shoulder Injuries in the Overhead-Throwing Athlete: Epidemiology, Mechanisms of Injury, and Imaging Findings.

The unparalleled velocity achieved by overhead throwers subjects the shoulder to extreme forces, resulting in both adaptive changes and pathologic findings that can be detected at imaging. A key biomechanical principle of throwing is achieving maximum external rotation, which initially leads to adaptive changes that may result in a pathologic cascade of injuries. In addition to the well-established concepts of glenohumeral internal rotation deficit and internal impingement, osseous and soft-tissue injuries of the shoulder unique to overhead athletes are illustrated. The epidemiology and biomechanics of throwing injuries are reviewed, and examples from the authors' institutional experience with competitive, collegiate, and professional baseball players are provided to demonstrate the constellation of unique imaging findings seen in overhead throwing athletes. Given the widespread popularity of baseball, and other sports relying on overhead throwing motions at all playing levels from recreational to professional, it is important for radiologists in various practice settings to be familiar with the special mechanisms, locations, and types of shoulder injuries seen in the overhead throwing population. © RSNA, 2018.

Elbow Injuries in Pediatric Overhead Athletes.

OBJECTIVE: The purpose of this article is to discuss common elbow injuries found in pediatric athletes who participate in sports that entail overhead movements with focus on mechanism, clinical features, imaging appearance, and treatment options. CONCLUSION: Elbow injuries are commonly seen in pediatric overhead athletes and have been on the rise owing to the increased participation in and demand of youth sports. Imaging plays a critical role in identifying the type and severity of injury, which helps to determine appropriate treatment options.

Elbow Injuries in Adult Overhead Athletes.

OBJECTIVE: The purpose of this article is to review common elbow injuries found in overhead athletes with focus on mechanism, clinical features, imaging appearance, and treatment options. CONCLUSION: The overhead throwing motion subjects the elbow to a variety of complex forces, which places both osseous and soft-tissue structures at high risk for injury.

Adventures and Misadventures in Plastic Surgery and Soft-Tissue Implants.

Soft-tissue augmentation and implants are increasingly seen by the radiologist as more techniques emerge for a variety of indications and locations. Some surgical and implant procedures are performed for purely cosmetic reasons in otherwise healthy patients seeking to improve their body image, and some are performed for reconstruction after cancer or other chronic illnesses. Abdominoplasty, liposuction, and autologous fat grafting can be performed for abdominal and gluteal contouring. Injection of liquid injectable silicone has historically been fraught with legal issues, although it continues to be used for augmentation in a variety of anatomic locations. Newer solid silicone implants have revolutionized cosmetic and reconstructive muscular contouring. Subdermal implants placed by nonmedical professionals are relatively new and unrecognized within the medical establishment, although such implants have been described in the popular culture. Perhaps the most rapidly increasing segment of cosmetic procedures, however, is minimally invasive cosmesis in the form of soft-tissue fillers in the hands and face. Finally, the major principles of breast augmentation and penile implants are also reviewed. Regardless of the location and the type of implant, complications of plastic surgery and soft-tissue implants can generally be classified into the following categories: seroma, hematoma, infection, migration, vascular or nerve compression, fibrosis, foreign-body reaction, and rupture or breakdown. Key concepts include knowing the appropriate anatomic location and the normal postoperative appearance so that complications can be properly detected. A broad range of approved, off-label, and illicit plastic surgical and implant procedures are described and their complications illustrated with cases with classic imaging findings. ©RSNA, 2017.

Shoulder Arthroplasty, from Indications to Complications: What the Radiologist Needs to Know.

The replaced shoulder is increasingly encountered by the radiologist, both on a dedicated and incidental basis, in this era of the growing population of aging patients wishing to preserve their mobility and function. Knowledge of the normal biomechanics of the glenohumeral joint-particularly the function of the rotator cuff and the unique relationship of the humeral head to the glenoid-is essential for understanding the need for shoulder replacement and its subsequent complications, because the intent of shoulder arthroplasty is to approximate the normal joint as closely as possible. The most common indications for shoulder arthroplasty are osteoarthritis, inflammatory arthritis, proximal humerus fractures, irreparable rotator cuff tears, rotator cuff arthropathy, and avascular necrosis of the humeral head. Knowledge of the key imaging features of these indications helps facilitate a correlative understanding between the initial diagnosis and the choice of which type of arthroplasty is used-total shoulder arthroplasty, reverse total shoulder arthroplasty, or partial joint replacement (humeral head resurfacing arthroplasty or hemiarthroplasty). The preoperative requirements and usual postoperative appearance of each arthroplasty type are summarized, as well as the complications of shoulder arthroplasty, including those unique to or closely associated with each type of arthroplasty and those that can be encountered with any type of shoulder arthroplasty.

Artificial Intelligence-Driven Ultra-Fast Superresolution MRI: 10-Fold Accelerated Musculoskeletal Turbo Spin Echo MRI Within Reach.

ABSTRACT: Magnetic resonance imaging (MRI) is the keystone of modern musculoskeletal imaging; however, long pulse sequence acquisition times may restrict patient tolerability and access. Advances in MRI scanners, coil technology, and innovative pulse sequence acceleration methods enable 4-fold turbo spin echo pulse sequence acceleration in clinical practice; however, at this speed, conventional image reconstruction approaches the signal-to-noise limits of temporal, spatial, and contrast resolution. Novel deep learning image reconstruction methods can minimize signal-to-noise interdependencies to better advantage than conventional image reconstruction, leading to unparalleled gains in image speed and quality when combined with parallel imaging and simultaneous multislice acquisition. The enormous potential of deep learning-based image reconstruction promises to facilitate the 10-fold acceleration of the turbo spin echo pulse sequence, equating to a total acquisition time of 2-3 minutes for entire MRI examinations of joints without sacrificing spatial resolution or image quality. Current investigations aim for a better understanding of stability and failure modes of image reconstruction networks, validation of network reconstruction performance with external data sets, determination of diagnostic performances with independent reference standards, establishing generalizability to other centers, scanners, field strengths, coils, and anatomy, and building publicly available benchmark data sets to compare methods and foster innovation and collaboration between the clinical and image processing community. In this article, we review basic concepts of deep learning-based acquisition and image reconstruction techniques for accelerating and improving the quality of musculoskeletal MRI, commercially available and developing deep learning-based MRI solutions, superresolution, denoising, generative adversarial networks, and combined strategies for deep learning-driven ultra-fast superresolution musculoskeletal MRI. This article aims to equip radiologists and imaging scientists with the necessary practical knowledge and enthusiasm to meet this exciting new era of musculoskeletal MRI.

Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI.

BACKGROUND: Detection of rotator cuff tears, a common cause of shoulder disability, can be time-consuming and subject to reader variability. Deep learning (DL) has the potential to increase radiologist accuracy and consistency. PURPOSE: The aim of this study was to develop a prototype DL model for detection and classification of rotator cuff tears on shoulder magnetic resonance imaging into no tear, partial-thickness tear, or full-thickness tear. MATERIALS AND METHODS: This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included a total of 11,925 noncontrast shoulder magnetic resonance imaging scans from 2 institutions, with 11,405 for development and 520 dedicated for final testing. A DL ensemble algorithm was developed that used 4 series as input from each examination: fluid-sensitive sequences in 3 planes and a sagittal oblique T1-weighted sequence. Radiology reports served as ground truth for training with categories of no tear, partial tear, or full-thickness tear. A multireader study was conducted for the test set ground truth, which was determined by the majority vote of 3 readers per case. The ensemble comprised 4 parallel 3D ResNet50 convolutional neural network architectures trained via transfer learning and then adapted to the targeted domain. The final tear-type prediction was determined as the class with the highest probability, after averaging the class probabilities of the 4 individual models. RESULTS: The AUC overall for supraspinatus, infraspinatus, and subscapularis tendon tears was 0.93, 0.89, and 0.90, respectively. The model performed best for full-thickness supraspinatus, infraspinatus, and subscapularis tears with AUCs of 0.98, 0.99, and 0.95, respectively. Multisequence input demonstrated higher AUCs than single-sequence input for infraspinatus and subscapularis tendon tears, whereas coronal oblique fluid-sensitive and multisequence input showed similar AUCs for supraspinatus tendon tears. Model accuracy for tear types and overall accuracy were similar to that of the clinical readers. CONCLUSIONS: Deep learning diagnosis of rotator cuff tears is feasible with excellent diagnostic performance, particularly for full-thickness tears, with model accuracy similar to subspecialty-trained musculoskeletal radiologists.

New-Generation Low-Field Magnetic Resonance Imaging of Hip Arthroplasty Implants Using Slice Encoding for Metal Artifact Correction: First In Vitro Experience at 0.55 T and Comparison With 1.5 T.

OBJECTIVES: Despite significant progress, artifact-free visualization of the bone and soft tissues around hip arthroplasty implants remains an unmet clinical need. New-generation low-field magnetic resonance imaging (MRI) systems now include slice encoding for metal artifact correction (SEMAC), which may result in smaller metallic artifacts and better image quality than standard-of-care 1.5 T MRI. This study aims to assess the feasibility of SEMAC on a new-generation 0.55 T system, optimize the pulse protocol parameters, and compare the results with those of a standard-of-care 1.5 T MRI. MATERIALS AND METHODS: Titanium (Ti) and cobalt-chromium total hip arthroplasty implants embedded in a tissue-mimicking American Society for Testing and Materials gel phantom were evaluated using turbo spin echo, view angle tilting (VAT), and combined VAT and SEMAC (VAT + SEMAC) pulse sequences. To refine an MRI protocol at 0.55 T, the type of metal artifact reduction techniques and the effect of various pulse sequence parameters on metal artifacts were assessed through qualitative ranking of the images by 3 expert readers while taking measured spatial resolution, signal-to-noise ratios, and acquisition times into consideration. Signal-to-noise ratio efficiency and artifact size of the optimized 0.55 T protocols were compared with the 1.5 T standard and compressed-sensing SEMAC sequences. RESULTS: Overall, the VAT + SEMAC sequence with at least 6 SEMAC encoding steps for Ti and 9 for cobalt-chromium implants was ranked higher than other sequences for metal reduction ( P < 0.05). Additional SEMAC encoding partitions did not result in further metal artifact reductions. Permitting minimal residual artifacts, low magnetic susceptibility Ti constructs may be sufficiently imaged with optimized turbo spin echo sequences obviating the need for SEMAC. In cross-platform comparison, 0.55 T acquisitions using the optimized protocols are associated with 45% to 64% smaller artifacts than 1.5 T VAT + SEMAC and VAT + compressed-sensing/SEMAC protocols at the expense of a 17% to 28% reduction in signal-to-noise ratio efficiency. B 1 -related artifacts are invariably smaller at 0.55 T than 1.5 T; however, artifacts related to B 0 distortion, although frequently smaller, may appear as signal pileups at 0.55 T. CONCLUSIONS: Our results suggest that new-generation low-field SEMAC MRI reduces metal artifacts around hip arthroplasty implants to better advantage than current 1.5 T MRI standard of care. While the appearance of B 0 -related artifacts changes, reduction in B 1 -related artifacts plays a major role in the overall benefit of 0.55 T.

Multidisciplinary approach to diagnosis and management of intraductal papillary mucinous neoplasms of the pancreas.

Intraductal papillary mucinous neoplasms have gained recognition in recent years as premalignant precursors to pancreatic cancer that enable early detection and often are found incidentally at imaging. Accurate diagnosis and optimal, finely tuned management of these lesions are important and require collaboration across various disciplines, including radiology, endoscopy, surgery, and pathology. Several imaging modalities can visualize these lesions adequately, each with specific advantages and disadvantages. Multidetector computed tomography and magnetic resonance cholangiopancreatography are generally the first-line imaging modalities; endoscopic imaging such as endoscopic ultrasound and endoscopic retrograde cholangiopancreatography are beneficial when the former 2 modalities are equivocal. Surgical candidates generally include patients with main duct lesions or branch duct lesions greater than 3 cm or any possessing a solid component. A management algorithm indicating when surgery should be pursued is proposed. For nonsurgical and postsurgical patients, follow-up management is important to monitor growth and recurrence, and risks from repeated radiation exposure should be taken into account. Furthermore, issues of multifocality and increased predisposition of the pancreas to ductal adenocarcinoma must be addressed at follow-up evaluation. A follow-up management algorithm also is proposed in this review.

Anteroposterior Radiograph of the Ankle with Cross-Sectional Imaging Correlation.

The focus of this article is to illustrate various pathologic entities and variants, heralding disease about the ankle, based on scrutiny of AP radiographs of the ankle, with correlative findings on cross-sectional imaging. Many of these entities can only be detected on the AP ankle radiograph and, if not recognized, may lead to delayed diagnosis and persistent morbidity to the patient. However, a vigilant radiologist, equipped with the knowledge of the characteristic appearance and typical locations of the imaging findings, should be able to make the crucial initial diagnosis and surmise additional findings to be confirmed on cross-sectional imaging.

Improving Emergency Department Flow: Reducing Turnaround Time for Emergent CT Scans.

Emergency departments across the U.S. are more congested than ever, and there is a pressing need to create capacity by improving patient flow. The long turnaround time of imaging tests, such as computed tomography (CT) scans, are a major reason for delays in treatment and disposition. Over an eight-month pre-intervention period during which 10,063 CT scans were ordered in our emergency department, the average time from a CT order to the availability of the radiologist's final report was 5.9 hours (median=4.2 hours). We created a multi-disciplinary team of physicians, nurses, technicians, transporters, informaticians, and engineers to identify barriers and implement technical as well as human-factors solutions. In the corresponding eight-month period after the implementation of the intervention bundle, there was a 1.2 hour reduction in CT turnaround time, despite a 13.8% increase in the number of CT scans ordered (p<0.0001).

Radiology ExamWeb: development and implementation of a national web-based examination system for medical students in radiology.

RATIONALE AND OBJECTIVES: Faculty are often limited in time, knowledge, and resources to develop efficient, effective, and valid computer-based examinations to evaluate students. Our purpose was to develop a web-based pool of standardized National Board of Medical Examiners (NBME)-format, peer-reviewed, and peer-tested questions based on the Alliance of Medical Student Educators in Radiology (AMSER) National Medical Student Curriculum to evaluate the radiologic knowledge of medical students. MATERIALS AND METHODS: Members of the AMSER Electronics Committee submitted questions they had written for their institutions and later developed a 113-question standardized examination. Questions were edited by 24 subspeciality editors and then further edited by the authors to NBME recommendations. Software was developed using commercially available software (www.ExamWeb.com) with extensive modifications and additions following initial deployment. Students take examinations online and receive their scores immediately. Items were validated by identifying those answered >30 times and analyzing the following: number of times deployed, number of times correctly answered, distractor-specific breakdown, difficulty level (P), and point biserial coefficient (rbi). RESULTS: Radiology ExamWeb (REW) is available online with 3500 registered students from 65 institutions and 1800 active questions. Instructors can create examinations or use "shared examinations" made by another instructor but enabled for other institutions to administer or modify. More than 300 shared examinations have been developed. The AMSER curriculum was converted into database format and crosschecked with question items to ensure that the question pool adequately covered the spectrum of the curriculum. An AMSER standardized examination has been developed and deployed within REW. CONCLUSIONS: REW has provided medical student educators with the means to evaluate students in a systematic way, using a nationally edited and regularly reviewed web-based process.