Musculoskeletal Imaging Research Articles

A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence.

The digitization of medical records and expanding electronic health records has created an era of "Big Data" with an abundance of available information ranging from clinical notes to imaging studies. In the field of rheumatology, medical imaging is used to guide both diagnosis and treatment of a wide variety of rheumatic conditions. Although there is an abundance of data to analyze, traditional methods of image analysis are human resource intensive. Fortunately, the growth of artificial intelligence (AI) may be a solution to handle large datasets. In particular, computer vision is a field within AI that analyzes images and extracts information. Computer vision has impressive capabilities and can be applied to rheumatologic conditions, necessitating a need to understand how computer vision works. In this article, we provide an overview of AI in rheumatology and conclude with a five step process to plan and conduct research in the field of computer vision. The five steps include (1) project definition, (2) data handling, (3) model development, (4) performance evaluation, and (5) deployment into clinical care.

Relationship between klotho and physical function in healthy aging

Epidemiological studies have reported a strong association between circulating Klotho and physical function; however, the cohorts were comprised of older adults with multiple comorbidities. Herein, we examined the relationship between Klotho and physical function in a community-based cohort of healthy adults. In this cross-sectional study, serum Klotho was measured in 80 adults who visited the Musculoskeletal Function, Imaging, and Tissue Resource Core of the Indiana Center for Musculoskeletal Health. Participants (n = 20, 10 [50%] men per group) were chosen into four age groups: 20–34, 35–49, 50–64, and ≥ 65 years, and were further grouped based on performance (low vs. high) on grip strength and chair stand tests. Klotho levels were lower in the ≥ 65 years group (703.0 [189.3] pg/mL; p = 0.022) and the 50–64 years group (722.6 [190.5] pg/mL; p = 0.045) compared to 20–34 years (916.1 [284.8] pg/mL). No differences were observed in Klotho between the low and high performers. The ≥ 65 years group walked a shorter distance during the 6-min walk test (6MWT) compared to 20–34 years (p = 0.005). Klotho was correlated with age (p < 0.001), body fat (p = 0.037), and 6MWT distance (p = 0.022). Klotho levels decline as early as the fifth decade of life, potentially before the onset of age-related impairment in exercise capacity.

Diagnostic performance of modern computed tomography in cruciate ligament injury detection: A comprehensive study

BackgroundThis study aimed to evaluate the clinical utility of modern single and dual-energy computed tomography (CT) for assessing the integrity of the cruciate ligaments in patients that sustained acute trauma. MethodsPatients who underwent single- or dual-energy CT followed by 3 Tesla magnetic resonance imaging (MRI) or knee joint arthroscopy between 01/2016 and 12/2022 were included in this retrospective, monocentric study. Three radiologists specialized in musculoskeletal imaging independently evaluated all CT images for the presence of injury to the cruciate ligaments. An MRI consensus reading of two experienced readers and arthroscopy provided the reference standard. Diagnostic accuracy parameters and area under the receiver operator characteristic curve (AUC) were the primary metrics for diagnostic performance. ResultsCT images of 204 patients (median age, 49 years; IQR 36 – 64; 113 males) were evaluated. Dual-energy CT yielded significantly higher diagnostic accuracy and AUC for the detection of injury to the anterior (94% [240/255] vs 75% [266/357] and 0.89 vs 0.66) and posterior cruciate ligaments (95% [243/255] vs 87% [311/357] and 0.90 vs 0.61) compared to single-energy CT (all parameters, p <.005). Diagnostic confidence and image quality were significantly higher in dual-energy CT compared to single-energy CT (all parameters, p <.005). ConclusionsModern dual-energy CT is readily available and can serve as a screening tool for detecting or excluding cruciate ligament injuries in patients with acute trauma. Accurate diagnosis of cruciate ligament injuries is crucial to prevent adverse outcomes, including delayed treatment, chronic instability, or long-term functional limitations.

Fully Automated Analysis of Muscle Architecture from B-Mode Ultrasound Images with DL_Track_US

B-mode ultrasound can be used to image musculoskeletal tissues, but one major bottleneck is analyses of muscle architectural parameters (i.e., muscle thickness, pennation angle and fascicle length), which are most often performed manually. In this study we trained two different neural networks (classic U-Net and U-Net with VGG16 pre-trained encoder) to detect muscle fascicles and aponeuroses using a set of labeled musculoskeletal ultrasound images. We determined the best-performing model based on intersection over union and loss metrics. We then compared neural network predictions on an unseen test set with those obtained via manual analysis and two existing semi/automated analysis approaches (simple muscle architecture analysis [SMA] and UltraTrack). DL_Track_US detects the locations of the superficial and deep aponeuroses, as well as multiple fascicle fragments per image. For single images, DL_Track_US yielded results similar to those produced by a non-trainable automated method (SMA; mean difference in fascicle length: 5.1 mm) and human manual analysis (mean difference: -2.4 mm). Between-method differences in pennation angle were within 1.5°, and mean differences in muscle thickness were less than 1 mm. Similarly, for videos, there was overlap between the results produced with UltraTrack and DL_Track_US, with intraclass correlations ranging between 0.19 and 0.88. DL_Track_US is fully automated and open source and can estimate fascicle length, pennation angle and muscle thickness from single images or videos, as well as from multiple superficial muscles. We also provide a user interface and all necessary code and training data for custom model development.

Survey on how Australian rheumatologists use musculoskeletal ultrasound (MSUS), including challenges and unmet needs

ObjectiveWorldwide there is increasing use of musculoskeletal ultrasound (MSUS) in clinical practice, particularly by rheumatologists. Despite reported high levels of interest in the use of MSUS, lack of education and experience are often reported as barriers to rheumatologists performing MSUS in clinical practice. To evaluate current MSUS practices in Australia, we undertook a survey of rheumatologists who are current members of an Australian MSUS special interest group. MethodsDescriptive and summary statistics of responses to a web-based survey to rheumatologists who had attended a workshop with the Australian Musculoskeletal Imaging Special Interest Group (AMISIG) were undertaken. ResultsOf thirty-six respondents, 97.2 % reported using MSUS as part of clinical care, and more than a quarter also use MSUS for research and teaching. The most frequent indication for MSUS use in 94.4 % of clinicians was for early diagnosis of rheumatic diseases, followed by monitoring response to treatment. Barriers to use of MSUS were identified, including time constraints, costs and lack of training post courses and experience. To support MSUS use in Australia, respondents nominated more “hands-on” supervised training courses and supervision of advanced trainees. ConclusionMSUS use by surveyed Australian rheumatologists is most frequently to make an early diagnosis of rheumatic diseases as well as in monitoring response to treatments, in research and in teaching activities. Australian clinicians identified that increased clinical education in MSUS, particularly for rheumatology trainees, was needed.

Robust Multi-View Fracture Detection inthe Presence ofOther Abnormalities Using HAMIL-Net.

Foot and ankle fractures are the most common military health problem. Automated diagnosis can save time and personnel. It is crucial to distinguish fractures not only from normal healthy cases, but also robust against the presence of other orthopedic pathologies. Artificial intelligence (AI) deep learning has been shown to be promising. Previously, we have developed HAMIL-Net to automatically detect orthopedic injuries for upper extremity injuries. In this research, we investigated the performance of HAMIL-Net for detecting foot and ankle fractures in the presence of other abnormalities. HAMIL-Net is a novel deep neural network consisting of a hierarchical attention layer followed by a multiple-instance learning layer. The design allowed it to deal with imaging studies with multiple views. We used 148K musculoskeletal imaging studies for 51K Veterans at VA San Diego in the past 20 years to create datasets for this research. We annotated each study by a semi-automated pipeline leveraging radiology reports written by board-certified radiologists and extracting findings with a natural language processing tool and manually validated the annotations. HAMIL-Net can be trained with study-level, multiple-view examples, and detect foot and ankle fractures with a 0.87 area under the receiver operational curve, but the performance dropped when tested by cases including other abnormalities. By integrating a fracture specialized model with one that detecting a broad range of abnormalities, HAMIL-Net's accuracy of detecting any abnormality improved from 0.53 to 0.77 and F-score from 0.46 to 0.86. We also reported HAMIL-Net's performance under different study types including for young (age 18-35) patients. Automated fracture detection is promising but to be deployed in clinical use, presence of other abnormalities must be considered to deliver its full benefit. Our results with HAMIL-Net showed that considering other abnormalities improved fracture detection and allowed for incidental findings of other musculoskeletal abnormalities pertinent or superimposed on fractures.

Characterising the interventions designed to affect the reporting of musculoskeletal imaging: a scoping review protocol using the COM-B model

IntroductionAttributing musculoskeletal (MSK) pain to normal and commonly occurring imaging findings, such as tendon, cartilage and spinal disc degeneration, has been shown to increase people’s fear of movement, reduce their...

Diagnostic Accuracy of Magnetic Resonance Imaging (MRI) in the Detection of Anterior Cruciate Ligament (ACL) Tear, keeping Arthroscopic Findings as Gold Standard

Objective: To determine the diagnostic accuracy of Magnetic Resonance Imaging (MRI) compared to arthroscopy in detecting anterior cruciate ligament (ACL) tears. Study Design: Cross-section study. Place and Duration of Study: Combined Military Hospital, Kharian Pakistan, from Jan 2020 to Jan 2021. Methodology: Adult patients of either gender coming to the Radiology Department for an MRI knee joint followed by arthroscopy were included in the study after the institutional ethical review committee approved the study. A consultant with experience in musculoskeletal imaging reviewed the MRI images. An experienced orthopaedic surgeon performed arthroscopy. Findings of MRI and arthroscopy were noted. The diagnostic features of MRI, including sensitivity, specificity, negative predictive values (NPV), positive predictive values (PPV) and diagnostic accuracy were calculated. Results: The study included 200 patients aged between 21-68 years, a mean age of 40.89±11.49 years. Magnetic resonance imaging had a sensitivity of 93.20%, specificity of 76.31%, positive predictive value (PPV) of 94.37%, negative predictive value(NPV) of 72.5% and diagnostic accuracy of 90%. Conclusion: Magnetic resonance imaging is an efficient imaging investigation for diagnosing ACL tears.

Measurement of Healthy and Injured Triceps Surae Morphology.

Achilles tendon injuries occur throughout the lifespan and can negatively affect quality of life and overall health. Achilles tendinopathy is generally classified as an overuse injury associated with fusiform tendon thickening, neovascularization, and interstitial tendon degeneration. Current literature suggests these structural changes are associated withsymptoms and lower physical activity levels, as well assymptoms and lower extremity function in the long term. Surgically and non-surgically managed Achilles tendon ruptures result in increased tendon cross-sectional area (CSA) and a lengthened Achilles tendon. Both structural outcomes have clinical implications, as larger CSA positively predicts function, whereas increased tendon lengthening predicts reduced function after Achilles tendon rupture. Given the relationship between structural changes associated with Achilles tendon injuries for both injury severity and injury recovery, it is critical to be able to quantify Achilles tendon structure reliably and accurately. Silbernagel's group has established a valid and reliable method for efficiently evaluating triceps surae muscle and tendon structure. In this protocol, B-mode musculoskeletal ultrasound imaging is used to measure triceps surae structure, including Achilles tendon thickness and CSA, soleus thickness, and the presence of additional findings (calcifications and bursitis). B-mode extended field-of-view is used to measure Achilles tendon length and gastrocnemius anatomical CSA. Finally, power Doppler is used to identify intratendinous neovascularization. Quantification of triceps surae structure allows for comparison between limbs as well as longitudinal changes in response to exercise and treatment for healthy individuals and those with Achilles tendon injuries. This protocol has been used in many research studies to date and proves valuable in understanding the relationship between tendon structure and injury development, severity, and recovery. As ultrasound devices are becoming more affordable and portable, this protocol proves promising as a clinical tool, given its quick and efficient methods.

Machine Learning Empowering Personalized Medicine: A Comprehensive Review of Medical Image Analysis Methods

Artificial intelligence (AI) advancements, especially deep learning, have significantly improved medical image processing and analysis in various tasks such as disease detection, classification, and anatomical structure segmentation. This work overviews fundamental concepts, state-of-the-art models, and publicly available datasets in the field of medical imaging. First, we introduce the types of learning problems commonly employed in medical image processing and then proceed to present an overview of commonly used deep learning methods, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs), with a focus on the image analysis task they are solving, including image classification, object detection/localization, segmentation, generation, and registration. Further, we highlight studies conducted in various application areas, encompassing neurology, brain imaging, retinal analysis, pulmonary imaging, digital pathology, breast imaging, cardiac imaging, bone analysis, abdominal imaging, and musculoskeletal imaging. The strengths and limitations of each method are carefully examined, and the paper identifies pertinent challenges that still require attention, such as the limited availability of annotated data, variability in medical images, and the interpretability issues. Finally, we discuss future research directions with a particular focus on developing explainable deep learning methods and integrating multi-modal data.

Hybrid CNN-transformer network for interactive learning of challenging musculoskeletal images

Background and objectivesSegmentation of regions of interest (ROIs) such as tumors and bones plays an essential role in the analysis of musculoskeletal (MSK) images. Segmentation results can help with orthopaedic surgeons in surgical outcomes assessment and patient's gait cycle simulation. Deep learning-based automatic segmentation methods, particularly those using fully convolutional networks (FCNs), are considered as the state-of-the-art. However, in scenarios where the training data is insufficient to account for all the variations in ROIs, these methods struggle to segment the challenging ROIs that with less common image characteristics. Such characteristics might include low contrast to the background, inhomogeneous textures, and fuzzy boundaries. Methodswe propose a hybrid convolutional neural network – transformer network (HCTN) for semi-automatic segmentation to overcome the limitations of segmenting challenging MSK images. Specifically, we propose to fuse user-inputs (manual, e.g., mouse clicks) with high-level semantic image features derived from the neural network (automatic) where the user-inputs are used in an interactive training for uncommon image characteristics. In addition, we propose to leverage the transformer network (TN) – a deep learning model designed for handling sequence data, in together with features derived from FCNs for segmentation; this addresses the limitation of FCNs that can only operate on small kernels, which tends to dismiss global context and only focus on local patterns. ResultsWe purposely selected three MSK imaging datasets covering a variety of structures to evaluate the generalizability of the proposed method. Our semi-automatic HCTN method achieved a dice coefficient score (DSC) of 88.46 ± 9.41 for segmenting the soft-tissue sarcoma tumors from magnetic resonance (MR) images, 73.32 ± 11.97 for segmenting the osteosarcoma tumors from MR images and 93.93 ± 1.84 for segmenting the clavicle bones from chest radiographs. When compared to the current state-of-the-art automatic segmentation method, our HCTN method is 11.7%, 19.11% and 7.36% higher in DSC on the three datasets, respectively. ConclusionOur experimental results demonstrate that HCTN achieved more generalizable results than the current methods, especially with challenging MSK studies.

Medical student perspectives on radiology subspecialties prior to core clerkship

Rationale and objectivesRadiology remains underrepresented in U.S. medical school clinical curricula, and preconceived opinions about the field may impact whether students pursue elective exposure. A core radiology clerkship at one academic institution presents an opportunity to evaluate students’ early preferences for different radiology subspecialties, thus informing curricular design and inspiring student recruitment. Materials and methodsAt a single allopathic medical school, a required, four-week, clinical-year radiology clerkship that occurs in the second year includes immersive one-week experiences in two subspecialties. Prior to their clerkship, students rank their immersion preferences by distributing 100 points across eight fields, the values of which were analyzed as a proxy for interest. A secondary survey was distributed to active first- and second-year medical students to further investigate the factors drawing them to radiology. ResultsImmersive experiences in musculoskeletal, body, and breast imaging were most preferred, earning ≥20 points from 41.6 %, 34.3 %, and 31.9 % of students, respectively. Women were significantly more likely than men to express interest in breast imaging (35.8 % vs. 24.8 %, p = 0.037) and pediatric radiology (28.8 % vs. 12.8 %, p = 0.001). Men were significantly more likely than women to prefer body imaging (41.9 % vs. 30.2 %, p = 0.034), neuroradiology (29.1 % vs. 19.5 %, p = 0.048), and nuclear medicine (11.1 % vs. 5.1 %, p = 0.044). ConclusionEarly in their clinical education, medical students prefer certain subspecialties, especially musculoskeletal, body, and breast imaging. Women expressed significantly stronger interest in breast imaging and pediatric radiology, while men indicated significantly stronger interest in body imaging, neuroradiology, and nuclear medicine.

Knowledge, attitude, and perception of Nigerian-based physiotherapists on the utilization of musculoskeletal ultrasound imaging in the clinical management of musculoskeletal conditions

BackgroundMusculoskeletal ultrasound imaging (MSUI) is an efficient monitoring and re-evaluation tool used for the management of musculoskeletal conditions in several clinical domains. Its utilization among physiotherapists, particularly in African countries, is yet to be explored.ObjectiveThis study investigated the knowledge, attitude, and perception of physiotherapists on the utilization of MSUI in the clinical management of musculoskeletal conditions.MethodsOne hundred and ninety-two consenting Nigerian-based physiotherapists practicing in public and private health institutions participated in this cross-sectional survey. They responded to a three-sectioned structured questionnaire, investigating socio-demographic and occupational characteristics, knowledge, attitude, and utilization of MSUI for the management of musculoskeletal conditions. Data were analyzed with descriptive statistics and Pearson’s chi-square test at a significant level of 0.05.ResultsThe majority (79.2%) of the respondents had positive knowledge of MSUI and its benefits as a clinical modality for managing MSCs. However, only 4.2% had utilized MSUI in clinical practice. Non-utilization of MSUI was commonly attributed to a lack of access to MSUI (60.3%) and its unavailability in most diagnostic centers (42.9%). Almost all (99.0%) of them agreed to the necessity for increased availability of MSUI to physiotherapists for enhancement of physiotherapy interventions in the management of MSCs.ConclusionKnowledge of MSUI among Nigerian-based physiotherapists is adequate, but its utilization as a clinical tool is poor. Improved availability of MSUI to physiotherapists is necessary as well as specialty training on the utilization and interpretation of MSUI.

Polymyalgia rheumatica: An update (Review).

Polymyalgia rheumatica (PMR) is a chronic inflammatory disease which affects the connective vascular tissue, characterized by pain accompanied by morning stiffness, predominantly of the neck muscles, hip and shoulder girdle. Usually, patients with this disease are >50 years of age and biological inflammatory syndrome is present with an increase in both the erythrocyte sedimentation rate and C-reactive protein levels, aspects similar to giant cell arteritis. The aim of the present review was to depict the current pathogenic hypothesis, diagnostic and treatment approach for patients with PMR, and novelties since the development of the currently used 2012 European League Against Rheumatism and American College of Rheumatology provisional classification criteria. PMR is a prevalent disease that can occasionally prove difficult to diagnose and treat. Possibly, the most abundant type of evidence and data revealed over the past decade have been acquired through musculoskeletal imaging, with implications in diagnosis, disease monitoring and relapse, prognosis and changes with treatment. Further research on pathophysiology is required to gain a deeper understanding of the underlying processes, which will serve as the foundation for future personalized treatments. In addition, there is an increasing demand for improved diagnostic techniques, which should include a further development of various imaging modalities, in order to provide accurate diagnosis and appropriate therapy.

Bone Tumor Risk Stratification and Management System: A Consensus Guideline from the ACR Bone Reporting and Data System Committee

The assessment and subsequent management of a potentially neoplastic bone lesion seen at diagnostic radiography is often complicated by diagnostic uncertainty and inconsistent management recommendations. Appropriate clinical management should be directed by risk of malignancy. Herein, the ACR-sponsored Bone Reporting and Data System (Bone-RADS) Committee, consisting of academic leaders in the fields of musculoskeletal oncology imaging and orthopedic oncology, presents the novel Bone-RADS scoring system to aid in risk assignment and provide risk-aligned management suggestions. When viewed in the proper clinical context, a newly identified bone lesion can be risk stratified as having very low, low, intermediate, or high risk of malignancy. Radiographic features predictive of risk are reviewed include margination, pattern of periosteal reaction, depth of endosteal erosion, pathological fracture, and extra-osseous soft tissue mass. Other radiographic features predictive of histopathology are also briefly discussed. To apply the Bone-RADS scoring system to a potentially neoplastic bone lesion, radiographic features predictive of risk are each given a point value. Point values are summed to yield a point total, which can be translated to a Bone-RADS score (1-4) with corresponding risk assignment (very low, low, intermediate, high). For each score, evidence-based and best practice consensus management suggestions are outlined. Examples of each Bone-RADS scores are presented, and a standardized diagnostic radiography report template is provided.

A pilot investigation of muscle integrity in patients with ADSSL1 myopathy using electrical impedance myography.

ADSSL1 myopathy (OMIM 617030) is a recently discovered, congenital myopathic disease caused by a pathogenic variant in ADSSL1. ADSSL1 is an enzyme involved in the purine nucleotide process and facilitates the conversion of inosine monophosphate to adenosine monophosphate within myocytes. Electrical impedance myography (EIM) is a portable, non-invasive, and cost-effective method for characterizing muscle integrity. Three ADSSL1 patients are presented in whom characterization of muscle integrity using EIM was performed. A 15-y-old male, 20-y-old female, and 63-y-old male each with a pathogenic variant in ADSSL1 [c.901G > A] as well as three, age-gender matched healthy controls (HCs) were enrolled. Study participants were phenotyped using a virtual EIM procedure. ADSSL1 myopathy patients presented with variable onset of physical disability, disease progression, and severity of muscle weakness. Across multiple proximal and distal muscles groups and relative to HCs, ADSSL1 myopathy patients demonstrated lower phase and reactance values, while resistance was higher, which together indicated diseased muscle. EIM can provide a novel, non-invasive and objective biomarker to evaluate muscle integrity in patients with ADSSL1 myopathy. Combining EIM with musculoskeletal imaging and histologic assessments in follow-up studies may further inform on the pathophysiology of ADSSL1 myopathy.

Biplanar quadrature coil for versatile low-field extremity MRI

Biplanar magnets offer extended flexibility in MRI, particularly appealing due to unmatched accessibility to the patient. At low field strength (&amp;lt;0.2 T), such geometries could be particularly suitable for interventional settings or purpose-built applications such as musculoskeletal imaging. In the proposed work, we present a dual-channel, biplanar coil array for low-field MRI featuring almost fully open access when sited in a biplanar magnet. The proposed detector relies on the assembly of two orthogonal biplanar coils (single transmit channel, two receive channels in quadrature) respectively interfaced with custom inductive couplers. Simulations of the B1 field in each element were performed before the quadrature coil was built and used at ∼ 0.1 T (4.33 MHz). Once assembled, the best performance in our setup was achieved in undermatched conditions in place of conventional 50-Ω matching. Phantom images display the extended coverage of the quadrature coil, with similar SNR from each individual biplanar coil. The combined images show an expected SNR gain of 2 that confirms good decoupling between the two channels (−36 dB). To the best of our knowledge, the proposed coil represents the first implementation of a biplanar geometry at low field and the first quadrature detection for a biplanar design. The open design and overall good sensitivity of our biplanar design enabled fast and quasi-isotropic 3D imaging with (1.6 × 1.6 × 2.2) mm3 resolution in vivo in human extremities.

Clustering Research Proposal Submissions to Understand the Unmet Needs ofMilitary Clinicians.

The Advanced Medical Technology Initiative (AMTI) program solicits research proposals for technology demonstrations and performance improvement projects in the domain of military medicine. Advanced Medical Technology Initiative is managed by the U.S. Army Telemedicine and Advanced Technology Research Center (TATRC). Advanced Medical Technology Initiative proposals span a wide range of topics, for example, treatment of musculoskeletal injury, application of virtual health technology, and demonstration of medical robots. The variety and distribution of central topics in these proposals (problems to be solved and technological solutions proposed) are not well characterized. Characterizing this content over time could highlight over- and under-served problem domains, inspire new technological applications, and inform future research solicitation efforts. This research sought to analyze and categorize historic AMTI proposals from 2010 to 2022 (n = 825). The analysis focused specifically on the "Problem to Be Solved" and "Technology to Demonstrated" sections of the proposals, whose categorizations are referred to as "Problem-Sets" and Solution-Sets" (PS and SS), respectively. A semi-supervised document clustering process was applied independently to the two sections. The process consisted of three stages: (1) Manual Document Annotation-a sample of proposals were manually labeled along each thematic axis; (2) Clustering-semi-supervised clustering, informed by the manually annotated sample, was applied to the proposals to produce document clusters; (3) Evaluation and Selection-quantitative and qualitative means were used to evaluate and select an optimal cluster solution. The results of the clustering were then summarized and presented descriptively. The results of the clustering process identified 24 unique PS and 20 unique SS. The most prevalent PS were Musculoskeletal Injury (12%), Traumatic Injury (11%), and Healthcare Systems Optimization (11%). The most prevalent SS were Sensing and Imaging Technology (27%), Virtual Health (23%), and Physical and Virtual Simulation (11.5%). The most common problem-solution pair was Healthcare Systems Optimization-Virtual Health, followed by Musculoskeletal Injury-Sensing and Imaging Technology. The analysis revealed that problem-solution-set co-occurrences were well distributed throughout the domain space, demonstrating the variety of research conducted in this research domain. A semi-supervised document clustering approach was applied to a repository of proposals to partially automate the process of document annotation. By applying this process, we successfully extracted thematic content from the proposals related to problems to be addressed and proposed technological solutions. This analysis provides a snapshot of the research supply in the domain of military medicine over the last 12 years. Future work should seek to replicate and improve the document clustering process used. Future efforts should also be made to compare these results to actual published work in the domain of military medicine, revealing differences in demand for research as determined by funding and publishing decision-makers and supply by researchers.

Initial Clinical Images From a Second-Generation Prototype Silicon-Based Photon-Counting Computed Tomography System

To demonstrate the feasibility andpotential of using a second-generation prototype photon-counting computed tomography (CT) system to provide simultaneous high spatial resolution images and high spectral resolution material information across a range of routine imaging tasks using clinical patient exposure levels. The photon-counting system employs an innovative silicon-based photon-counting detector to provide a balanced approach to ultra-high-resolution spectral CT imaging. An initial cohort of volunteer subjects was imaged using the prototype photon-counting system. Acquisition technique parameters and radiation dose exposures were guided by routine clinical exposure levels used at the institution. Images were reconstructed in native slice thickness using an early version of a spectral CT reconstruction algorithm Samples of images across a range of clinical tasks were selected and presented for review. Clinical cases are presented across inner ear, carotid angiography, chest, and musculoskeletal imaging tasks. Initial reconstructed images illustrate ultra-high spatial resolution imaging. The fine detail of small structures and pathologies is clearly visualized, and structural boundaries are well delineated. The prototype system additionally provides concomitant spectral information with high spatial resolution. This initial study demonstrates that routine imaging at clinically appropriate patient exposure levels is feasible using a novel deep-silicon photon-counting detector CT system. Furthermore, a deep-silicon detector may provide a balanced approach to photon-counting CT, providing high spatial resolution imaging with simultaneous high-fidelity spectral information.

The promise and limitations of artificial intelligence in musculoskeletal imaging.

With the recent developments in deep learning and the rapid growth of convolutional neural networks, artificial intelligence has shown promise as a tool that can transform several aspects of the musculoskeletal imaging cycle. Its applications can involve both interpretive and non-interpretive tasks such as the ordering of imaging, scheduling, protocoling, image acquisition, report generation and communication of findings. However, artificial intelligence tools still face a number of challenges that can hinder effective implementation into clinical practice. The purpose of this review is to explore both the successes and limitations of artificial intelligence applications throughout the muscuskeletal imaging cycle and to highlight how these applications can help enhance the service radiologists deliver to their patients, resulting in increased efficiency as well as improved patient and provider satisfaction.