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.

Patient-centered radiology: a roadmap for outpatient imaging.

Creating a patient-centered experience is becoming increasingly important for radiology departments around the world. The goal of patient-centered radiology is to ensure that radiology services are sensitive to patients' needs and desires. This article provides a framework for addressing the patient's experience by dividing their imaging journey into three distinct time periods: pre-exam, day of exam, and post-exam. Each time period has aspects that can contribute to patient anxiety. Although there are components of the patient journey that are common in all regions of the world, there are also unique features that vary by location. This paper highlights innovative solutions from different parts of the world that have been introduced in each of these time periods to create a more patient-centered experience. CLINICAL RELEVANCE STATEMENT: Adopting innovative solutions that help patients understand their imaging journey and decrease their anxiety about undergoing an imaging examination are important steps in creating a patient centered imaging experience. KEY POINTS: • Patients often experience anxiety during their imaging journey and decreasing this anxiety is an important component of patient centered imaging. • The patient imaging journey can be divided into three distinct time periods: pre-exam, day of exam, and post-exam. • Although components of the imaging journey are common, there are local differences in different regions of the world that need to be considered when constructing a patient centered experience.

Video Radiology Reports: A Valuable Tool to Improve Patient-Centered Radiology.

BACKGROUND. Improved communication between radiologists and patients is a key component of patient-centered radiology. OBJECTIVE. The purpose of this study was to create patient-centered video radiology reports using simple-to-understand language and annotated images and to assess the effect of these reports on patients' experience and understanding of their imaging results. METHODS. During a 4-month study period, faculty radiologists created video radiology reports using a tool integrated within the diagnostic viewer that allows both image and voice capture. To aid patients' understanding of cross-sectional images, cinematically rendered images were automatically created and made immediately available to radiologists at the workstation, allowing their incorporation into video radiology reports. Video radiology reports were made available to patients via the institutional health portal along with the written radiology report and the examination images. Patient views of the video report were recorded, and descriptive analyses were performed on radiologist and examination characteristics as well as patient demographics. A survey was sent to patients to obtain feedback on their experience. RESULTS. During the study period, 105 of 227 faculty radiologists created 3763 video radiology reports (mean number of reports per radiologist, 36 ± 27 [SD] reports). Mean time to create a video report was 238 ± 141 seconds. Patients viewed 864 unique video reports. The mean overall video radiology report experience rating based on 101 patient surveys was 4.7 of 5. The mean rating for how well the video report helped patients understand their findings was also 4.7 of 5. Of the patients who responded to the survey, 91% preferred having both written and video reports together over having written reports alone. CONCLUSION. Patient-centered video radiology reports are a useful tool to help improve patient understanding of imaging results. The mechanism of creating the video reports and delivering them to patients can be integrated into existing informatics infrastructure. CLINICAL IMPACT. Video radiology reports can play an important role in patient-centered radiology, increasing patient understanding of imaging results, and they may improve the visibility of radiologists to patients and highlight the radiologist's important role in patient care.

Artificial intelligence in musculoskeletal imaging: a perspective on value propositions, clinical use, and obstacles.

Artificial intelligence and deep learning (DL) offer musculoskeletal radiology exciting possibilities in multiple areas, including image reconstruction and transformation, tissue segmentation, workflow support, and disease detection. Novel DL-based image reconstruction algorithms correcting aliasing artifacts, signal loss, and noise amplification with previously unobtainable effectiveness are prime examples of how DL algorithms deliver promised value propositions in musculoskeletal radiology. The speed of DL-based tissue segmentation promises great efficiency gains that may permit the inclusion of tissue compositional-based information routinely into radiology reports. Similarly, DL algorithms give rise to a myriad of opportunities for workflow improvements, including intelligent and adaptive hanging protocols, speech recognition, report generation, scheduling, precertification, and billing. The value propositions of disease-detecting DL algorithms include reduced error rates and increased productivity. However, more studies using authentic clinical workflow settings are necessary to fully understand the value of DL algorithms for disease detection in clinical practice. Successful workflow integration and management of multiple algorithms are critical for translating the value propositions of DL algorithms into clinical practice but represent a major roadblock for which solutions are critically needed. While there is no consensus about the most sustainable business model, radiology departments will need to carefully weigh the benefits and disadvantages of each commercially available DL algorithm. Although more studies are needed to understand the value and impact of DL algorithms on clinical practice, DL technology will likely play an important role in the future of musculoskeletal imaging.

Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge.

PURPOSE: To advance research in the field of machine learning for MR image reconstruction with an open challenge. METHODS: We provided participants with a dataset of raw k-space data from 1,594 consecutive clinical exams of the knee. The goal of the challenge was to reconstruct images from these data. In order to strike a balance between realistic data and a shallow learning curve for those not already familiar with MR image reconstruction, we ran multiple tracks for multi-coil and single-coil data. We performed a two-stage evaluation based on quantitative image metrics followed by evaluation by a panel of radiologists. The challenge ran from June to December of 2019. RESULTS: We received a total of 33 challenge submissions. All participants chose to submit results from supervised machine learning approaches. CONCLUSIONS: The challenge led to new developments in machine learning for image reconstruction, provided insight into the current state of the art in the field, and highlighted remaining hurdles for clinical adoption.

Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations.

Artificial intelligence (AI) has the potential to significantly disrupt the way radiology will be practiced in the near future, but several issues need to be resolved before AI can be widely implemented in daily practice. These include the role of the different stakeholders in the development of AI for imaging, the ethical development and use of AI in healthcare, the appropriate validation of each developed AI algorithm, the development of effective data sharing mechanisms, regulatory hurdles for the clearance of AI algorithms, and the development of AI educational resources for both practicing radiologists and radiology trainees. This paper details these issues and presents possible solutions based on discussions held at the 2019 meeting of the International Society for Strategic Studies in Radiology. KEY POINTS: • Radiologists should be aware of the different types of bias commonly encountered in AI studies, and understand their possible effects. • Methods for effective data sharing to train, validate, and test AI algorithms need to be developed. • It is essential for all radiologists to gain an understanding of the basic principles, potentials, and limits of AI.

Perceptions of Radiologists and Emergency Medicine Providers Regarding the Quality, Value, and Challenges of Outside Image Sharing in the Emergency Department Setting.

OBJECTIVE. The purpose of this study is to assess the perceptions of radiologists and emergency medicine (EM) providers regarding the quality, value, and challenges associated with using outside imaging (i.e., images obtained at facilities other than their own institution). MATERIALS AND METHODS. We surveyed radiologists and EM providers at a large academic medical center regarding their perceptions of the availability and utility of outside imaging. RESULTS. Thirty-four of 101 radiologists (33.6%) and 38 of 197 EM providers (19.3%) responded. A total of 32.4% of radiologists and 55.3% of EM providers had confidence in the quality of images from outside community facilities; 20.6% and 44.7%, respectively, had confidence in the interpretations of radiologists from these outside facilities. Only 23.5% of radiologists and 5.3% of EM physicians were confident in their ability to efficiently access reports (for outside images, 47.1% and 5.3%). Very few radiologists and EM providers had accessed imaging reports from outside facilities through an available stand-alone portal. A total of 40.6% of radiologists thought that outside reports always or frequently reduced additional imaging recommendations (62.5% for outside images); 15.6% thought that reports changed interpretations of new examinations (37.5% for outside images); and 43.8% thought that reports increased confidence in interpretations of new examinations (75.0% for outside images). A total of 29.4% of EM providers thought that access to reports from outside facilities reduced repeat imaging (64.7% for outside images), 41.2% thought that they changed diagnostic or management plans (50.0% for outside images), and 50.0% thought they increased clinical confidence (67.6% for outside images). CONCLUSION. Radiologists and EM providers perceive high value in sharing images from outside facilities, despite quality concerns. Substantial challenges exist in accessing these images and reports from outside facilities, and providers are unlikely to do so using separate systems. However, even if information technology solutions for seamless image integration are adopted, providers' lack of confidence in outside studies may remain an important barrier.

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.

Improving the Speed of MRI with Artificial Intelligence.

Magnetic resonance imaging (MRI) is a leading image modality for the assessment of musculoskeletal (MSK) injuries and disorders. A significant drawback, however, is the lengthy data acquisition. This issue has motivated the development of methods to improve the speed of MRI. The field of artificial intelligence (AI) for accelerated MRI, although in its infancy, has seen tremendous progress over the past 3 years. Promising approaches include deep learning methods for reconstructing undersampled MRI data and generating high-resolution from low-resolution data. Preliminary studies show the promise of the variational network, a state-of-the-art technique, to generalize to many different anatomical regions and achieve comparable diagnostic accuracy as conventional methods. This article discusses the state-of-the-art methods, considerations for clinical applicability, followed by future perspectives for the field.

Core curriculum online lecture series in musculoskeletal imaging: initial results.

OBJECTIVE: To augment the educational resources available to training programs and trainees in musculoskeletal (MSK) radiology by creating a comprehensive series of Web-based open-access core curriculum lectures. MATERIALS AND METHODS: Speakers with recognized content and lecturing expertise in MSK radiology were invited to create digitally recorded lecture presentations across a series of 42 core curriculum topics in MSK imaging. Resultant presentation recordings, organized under curriculum subject headings, were archived as open-access video file recordings for online viewing on a dedicated Web page (http://radiologycorelectures.org/msk/). Information regarding the online core curriculum lecture series was distributed to members of the International Skeletal Society, Society of Skeletal Radiology, Society of Chairs of Academic Radiology Departments, and the Association of Program Directors in Radiology. Web page and online lecture utilization data were collected using Google Analytics (Alphabet, Mountain View, CA, USA). RESULTS: Forty-two lectures, by 38 speakers, were recorded, edited and hosted online. Lectures spanned ACGME curriculum categories of musculoskeletal trauma, arthritis, metabolic diseases, marrow, infection, tumors, imaging of internal derangement of joints, congenital disorders, and orthopedic imaging. Online access to the core curriculum lectures was opened on March 4, 2018. As of January 20, 2019, the core curriculum lectures have had 77,573 page views from 34,977 sessions. CONCLUSIONS: To date, the MSK core curriculum lecture series lectures have been widely accessed and viewed. It is envisioned that the initial success of the project will serve to promote ongoing content renewal and expansion to the lecture materials over time.

Assessment of the generalization of learned image reconstruction and the potential for transfer learning.

PURPOSE: Although deep learning has shown great promise for MR image reconstruction, an open question regarding the success of this approach is the robustness in the case of deviations between training and test data. The goal of this study is to assess the influence of image contrast, SNR, and image content on the generalization of learned image reconstruction, and to demonstrate the potential for transfer learning. METHODS: Reconstructions were trained from undersampled data using data sets with varying SNR, sampling pattern, image contrast, and synthetic data generated from a public image database. The performance of the trained reconstructions was evaluated on 10 in vivo patient knee MRI acquisitions from 2 different pulse sequences that were not used during training. Transfer learning was evaluated by fine-tuning baseline trainings from synthetic data with a small subset of in vivo MR training data. RESULTS: Deviations in SNR between training and testing led to substantial decreases in reconstruction image quality, whereas image contrast was less relevant. Trainings from heterogeneous training data generalized well toward the test data with a range of acquisition parameters. Trainings from synthetic, non-MR image data showed residual aliasing artifacts, which could be removed by transfer learning-inspired fine-tuning. CONCLUSION: This study presents insights into the generalization ability of learned image reconstruction with respect to deviations in the acquisition settings between training and testing. It also provides an outlook for the potential of transfer learning to fine-tune trainings to a particular target application using only a small number of training cases.

Artificial Intelligence in Musculoskeletal Imaging: Current Status and Future Directions.

OBJECTIVE. The objective of this article is to show how artificial intelligence (AI) has impacted different components of the imaging value chain thus far as well as to describe its potential future uses. CONCLUSION. The use of AI has the potential to greatly enhance every component of the imaging value chain. From assessing the appropriateness of imaging orders to helping predict patients at risk for fracture, AI can increase the value that musculoskeletal imagers provide to their patients and to referring clinicians by improving image quality, patient centricity, imaging efficiency, and diagnostic accuracy.

Optimization of MRI Turnaround Times Through the Use of Dockable Tables and Innovative Architectural Design Strategies.

OBJECTIVE: The purpose of this study is to increase the value of MRI by reengineering the MRI workflow at a new imaging center to shorten the interval (i.e., turnaround time) between each patient examination by at least 5 minutes. MATERIALS AND METHODS: The elements of the MRI workflow that were optimized included the use of dockable tables, the location of patient preparation rooms, the number of doors per scanning room, and the storage location and duplication of coils. Turnaround times at the new center and at two existing centers were measured both for all patients and for situations when the next patient was ready to be brought into the scanner room after the previous patient's examination was completed. RESULTS: Workflow optimizations included the use of dockable tables, dedicated patient preparation rooms, two doors in each MRI room, positioning the scanner to provide the most direct path to the scanner, and coil storage in the preparation rooms, with duplication of the most frequently used coils. At the new imaging center, the median and mean (± SD) turnaround times for situations in which patients were ready for scanning were 115 seconds (95% CI, 113-117 seconds) and 132 ± 72 seconds (95% CI, 129-135 seconds), respectively, and the median and mean turnaround times for all situations were 141 seconds (95% CI, 137-146 seconds) and 272 ± 270 seconds (95% CI, 263-282 seconds), respectively. For existing imaging centers, the median and mean turnaround times for situations in which patients were ready for scanning were 430 seconds (95% CI, 424-434 seconds) and 460 ± 156 seconds (95% CI, 455-465 seconds), respectively, and the median and mean turnaround times for all situations were 481 seconds (95% CI, 474-486 seconds) and 537 ± 219 seconds (95% CI, 532-543 seconds), respectively. CONCLUSION: The optimized MRI workflow resulted in a mean time savings of 5 minutes 28 seconds per patient.

Learning a variational network for reconstruction of accelerated MRI data.

PURPOSE: To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning. THEORY AND METHODS: Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applied online to previously unseen data. RESULTS: The variational network approach is evaluated on a clinical knee imaging protocol for different acceleration factors and sampling patterns using retrospectively and prospectively undersampled data. The variational network reconstructions outperform standard reconstruction algorithms, verified by quantitative error measures and a clinical reader study for regular sampling and acceleration factor 4. CONCLUSION: Variational network reconstructions preserve the natural appearance of MR images as well as pathologies that were not included in the training data set. Due to its high computational performance, that is, reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow. Magn Reson Med 79:3055-3071, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Informatics Solutions for Driving an Effective and Efficient Radiology Practice.

Radiologists are facing increasing workplace pressures that can lead to decreased job satisfaction and burnout. The increasing complexity and volumes of cases and increasing numbers of noninterpretive tasks, compounded by decreasing reimbursements and visibility in this digital age, have created a critical need to develop innovations that optimize workflow, increase radiologist engagement, and enhance patient care. During their workday, radiologists often must navigate through multiple software programs, including picture archiving and communication systems, electronic health records, and dictation software. Furthermore, additional noninterpretive duties can interrupt image review. Fragmented data and frequent task switching can create frustration and potentially affect patient care. Despite the current successful technological advancements across industries, radiology software systems often remain nonintegrated and not leveraged to their full potential. Each step of the imaging process can be enhanced with use of information technology (IT). Successful implementation of IT innovations requires a collaborative team of radiologists, IT professionals, and software programmers to develop customized solutions. This article includes a discussion of how IT tools are used to improve many steps of the imaging process, including examination protocoling, image interpretation, reporting, communication, and radiologist feedback. ©RSNA, 2018.

Advanced Imaging Techniques in the Knee: Benefits and Limitations of New Rapid Acquisition Strategies for Routine Knee MRI.

OBJECTIVE: The purpose of this article is to review current and emerging techniques and strategies that can be used to accelerate acquisition times in routine knee MRI. CONCLUSION: Specific techniques reviewed include 3D fast spin-echo imaging as well as new approaches to rapid image acquisition techniques (parallel imaging, compressed sensing, simultaneous multislice, and neural network reconstruction techniques) and their potential application to knee MRI.

Technologist-Directed Repeat Musculoskeletal and Chest Radiographs: How Often Do They Impact Diagnosis?

OBJECTIVE: Radiologic technologists may repeat images within a radiographic examination because of perceived suboptimal image quality, excluding these original images from submission to a PACS. This study assesses the appropriateness of technologists' decisions to repeat musculoskeletal and chest radiographs as well as the utility of repeat radiographs in addressing examinations' clinical indication. MATERIALS AND METHODS: We included 95 musculoskeletal and 87 chest radiographic examinations in which the technologist repeated one or more images because of perceived image quality issues, rejecting original images from PACS submission. Rejected images were retrieved from the radiograph unit and uploaded for viewing on a dedicated server. Musculoskeletal and chest radiologists reviewed rejected and repeat images in their timed sequence, in addition to the studies' remaining images. Radiologists answered questions regarding the added value of repeat images. RESULTS: The reviewing radiologist agreed with the reason for rejection for 64.2% of musculoskeletal and 60.9% of chest radiographs. For 77.9% and 93.1% of rejected radiographs, the clinical inquiry could have been satisfied without repeating the image. For 75.8% and 64.4%, the repeated images showed improved image quality. Only 28.4% and 3.4% of repeated images were considered to provide additional information that was helpful in addressing the clinical question. CONCLUSION: Most repeated radiographs (chest more so than musculoskeletal radiographs) did not add significant clinical information or alter diagnosis, although they did increase radiation exposure. The decision to repeat images should be made after viewing the questionable image in context with all images in a study and might best be made by a radiologist rather than the performing technologist.

Comparative Effectiveness Research in Musculoskeletal Imaging.

The primary goal of comparative effectiveness research (CER) is to define the optimal choice among alternative diagnostic and interventional strategies for a given clinical scenario among major stakeholders in the health care system. In an era where health care decision makers are demanding greater evidence of improved patient outcomes from the use of medical technologies, musculoskeletal (MSK) imagers must be more engaged in generating quality CER. We provide an overview of CER and its expanding role in U.S. health care, the current funding environment for CER and MSK imaging, potential areas for CER in MSK radiology, and a discussion of foreseeable challenges for CER in MSK imaging.