How AI May Transform Musculoskeletal Imaging.

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Follicular Lymphoma Presenting With Symptomatic Bone Involvement: A Clinicopathologic and Molecular Analysis of 16 Cases.

Primary bone lymphoma (PBL) is rare and mostly represented by diffuse large B-cell lymphomas (DLBCL). Follicular lymphoma (FL), albeit commonly disseminating to the bone marrow, rarely presents primarily as bone lesions. Here, we studied 16 patients (12 men:4 women, median age 60 years) who presented with bone pain and/or skeletal radiologic abnormalities revealing bone FL. Lesions were multifocal in 11 patients (spine ± appendicular skeleton), and unifocal in 5 patients (femoral, tibial, or vertebral). An infiltrate of centrocytes and centroblasts (CD20+ CD5- CD10+ BCL2+ BCL6+) with abundant reactive T cells and an increased reticulin fibrosis massively replaced the marrow spaces between preserved bone trabeculae. The pattern was diffuse ± nodular, often with paratrabecular reinforcement and/or peripheral paratrabecular extension. Ki-67 was usually <15%. Two cases had necrosis. BCL2 rearrangement was demonstrated in 14 of 14 evaluable cases (with concomitant BCL6 rearrangement in one). High-throughput sequencing revealed BCL2, KMT2D, and TNFRSF14 to be the most frequently mutated genes. After staging, 5 qualified for PBL (3 limited stage) and 11 had stage IV systemic FL. All patients received rituximab ± polychemotherapy as firstline treatment, and 7 received local therapy (6 radiotherapy and 2 surgery). Three patients experienced transformation to DLBCL. At the last follow-up (15/16, median 48 months), 11 patients achieved complete remission, including all cases with PBL and most patients with limited extraosseous disease (3-year progression-free survival 71%). One patient died of unrelated cause (3-year overall survival 91%). FL may manifest as a localized or polyostotic bone disease. A minority represent PBL, whereas most reveal systemic disease.

Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: AJR Expert Panel Narrative Review.

Artificial intelligence (AI) is increasingly used in clinical practice for musculoskeletal imaging tasks, such as disease diagnosis and image reconstruction. AI applications in musculoskeletal imaging have focused primarily on radiography, CT, and MRI. Although musculoskeletal ultrasound stands to benefit from AI in similar ways, such applications have been relatively underdeveloped. In comparison with other modalities, ultrasound has unique advantages and disadvantages that must be considered in AI algorithm development and clinical translation. Challenges in developing AI for musculoskeletal ultrasound involve both clinical aspects of image acquisition and practical limitations in image processing and annotation. Solutions from other radiology subspecialties (e.g., crowdsourced annotations coordinated by professional societies), along with use cases (most commonly rotator cuff tendon tears and palpable soft-tissue masses), can be applied to musculoskeletal ultrasound to help develop AI. To facilitate creation of high-quality imaging datasets for AI model development, technologists and radiologists should focus on increasing uniformity in musculoskeletal ultrasound performance and increasing annotations of images for specific anatomic regions. This Expert Panel Narrative Review summarizes available evidence regarding AI's potential utility in musculoskeletal ultrasound and challenges facing its development. Recommendations for future AI advancement and clinical translation in musculoskeletal ultrasound are discussed.

Chances and challenges of photon-counting CT in musculoskeletal imaging.

In musculoskeletal imaging, CT is used in a wide range of indications, either alone or in a synergistic approach with MRI. While MRI is the preferred modality for the assessment of soft tissues and bone marrow, CT excels in the imaging of high-contrast structures, such as mineralized tissue. Additionally, the introduction of dual-energy CT in clinical practice two decades ago opened the door for spectral imaging applications. Recently, the advent of photon-counting detectors (PCDs) has further advanced the potential of CT, at least in theory. Compared to conventional energy-integrating detectors (EIDs), PCDs provide superior spatial resolution, reduced noise, and intrinsic spectral imaging capabilities. This review briefly describes the technical advantages of PCDs. For each technical feature, the corresponding applications in musculoskeletal imaging will be discussed, including high-spatial resolution imaging for the assessment of bone and crystal deposits, low-dose applications such as whole-body CT, as well as spectral imaging applications including the characterization of crystal deposits and imaging of metal hardware. Finally, we will highlight the potential of PCD-CT in emerging applications, underscoring the need for further preclinical and clinical validation to unleash its full clinical potential.

Whole-body MRI in oncology: can a single anatomic T2 Dixon sequence replace the combination of T1 and STIR sequences to detect skeletal metastasis and myeloma?

OBJECTIVES: To compare the diagnostic accuracy of a single T2 Dixon sequence to the combination T1+STIR as anatomical sequences used for detecting tumoral bone marrow lesions in whole-body MRI (WB-MRI) examinations. METHODS: Between January 2019 and January 2020, seventy-two consecutive patients (55 men, 17 women, median age = 66 years) with solid (prostate, breast, neuroendocrine) cancers at high risk of metastasis or proven multiple myeloma (MM) prospectively underwent a WB-MRI examination including coronal T1, STIR, T2 Dixon and axial diffusion-weighted imaging sequences. Two radiologists independently assessed the combination of T1+STIR sequences and the fat+water reconstructions from the T2 Dixon sequence. The reference standard was established by consensus reading of WB-MRI and concurrent imaging available at baseline and at 6 months. Repeatability and reproducibility of MRI scores (presence and semi-quantitative count of lesions), image quality (SNR: signal-to-noise, CNR: contrast-to-noise, CRR: contrast-to-reference ratios), and diagnostic characteristics (Se: sensitivity, Sp: specificity, Acc: accuracy) were assessed per-skeletal region and per-patient. RESULTS: Repeatability and reproducibility were at least good regardless of the score, region, and protocol (0.67 ≤ AC1 ≤ 0.98). CRR was higher on T2 Dixon fat compared to T1 (p < 0.0001) and on T2 Dixon water compared to STIR (p = 0.0128). In the per-patient analysis, Acc of the T2 Dixon fat+water was higher than that of T1+STIR for the senior reader (Acc = +0.027 [+0.025; +0.029], p < 0.0001) and lower for the junior reader (Acc = -0.029 [-0.031; -0.027], p < 0.0001). CONCLUSIONS: A single T2 Dixon sequence with fat+water reconstructions offers similar reproducibility and diagnostic accuracy as the recommended combination of T1+STIR sequences and can be used for skeletal screening in oncology, allowing significant time-saving. KEY POINTS: • Replacement of the standard anatomic T1 + STIR WB-MRI protocol by a single T2 Dixon sequence drastically shortens the examination time without loss of diagnostic accuracy. • A protocol based on fat + water reconstructions from a single T2 Dixon sequence offers similar inter-reader agreement and a higher contrast-to-reference ratio for detecting lesions compared to the standard T1 + STIR protocol. • Differences in the accuracy between the two protocols are marginal (+ 3% in favor of the T2 Dixon with the senior reader; -3% against the T2 Dixon with the junior reader).

Interdisciplinary consensus statements on imaging of DRUJ instability and TFCC injuries.

OBJECTIVES: The purpose of this agreement was to establish evidence-based consensus statements on imaging of distal radioulnar joint (DRUJ) instability and triangular fibrocartilage complex (TFCC) injuries by an expert group using the Delphi technique. METHODS: Nineteen hand surgeons developed a preliminary list of questions on DRUJ instability and TFCC injuries. Radiologists created statements based on the literature and the authors' clinical experience. Questions and statements were revised during three iterative Delphi rounds. Delphi panelists consisted of twenty-seven musculoskeletal radiologists. The panelists scored their degree of agreement to each statement on an 11-item numeric scale. Scores of "0," "5," and "10" reflected complete disagreement, indeterminate agreement, and complete agreement, respectively. Group consensus was defined as a score of "8" or higher for 80% or more of the panelists. RESULTS: Three of fourteen statements achieved group consensus in the first Delphi round and ten statements achieved group consensus in the second Delphi round. The third and final Delphi round was limited to the one question that did not achieve group consensus in the previous rounds. CONCLUSIONS: Delphi-based agreements suggest that CT with static axial slices in neutral rotation, pronation, and supination is the most useful and accurate imaging technique for the work-up of DRUJ instability. MRI is the most valuable technique in the diagnosis of TFCC lesions. The main indication for MR arthrography and CT arthrography are Palmer 1B foveal lesions of the TFCC. CLINICAL RELEVANCE STATEMENT: MRI is the method of choice for assessing TFCC lesions, with higher accuracy for central than peripheral abnormalities. The main indication for MR arthrography is the evaluation of TFCC foveal insertion lesions and peripheral non-Palmer injuries. KEY POINTS: • Conventional radiography should be the initial imaging technique in the assessment of DRUJ instability. CT with static axial slices in neutral rotation, pronation, and supination is the most accurate method for evaluating DRUJ instability. • MRI is the most useful technique in diagnosing soft-tissue injuries causing DRUJ instability, especially TFCC lesions. • The main indications for MR arthrography and CT arthrography are foveal lesions of the TFCC.

Clinical Applications and Controversies of Whole-Body MRI: AJR Expert Panel Narrative Review.

Whole-body MRI (WB-MRI) is increasing in clinical acceptance and utilization for a range of indications. WB-MRI is currently an established screening tool for children and adults at high risk of developing malignancy, with the strongest supporting evidence in patients with Li-Fraumeni syndrome. WB-MRI has been added to professional society guidelines for staging disease in patients with certain malignancies including multiple myeloma and has been proposed as a technique to screen for metastatic disease in patients with visceral malignancies including prostate cancer and breast cancer. Emerging data support the utility of WB-MRI in children with malignancies such as Ewing sarcoma, in adults with myxoid liposarcoma, and in pregnant patients with occult or newly detected malignancy. WB-MRI can further help evaluate disease extent and treatment response in patients with nononcologic conditions such as chronic nonbacterial osteomyelitis, myopathy, inflammatory arthritis, and fever of unknown origin. This AJR Expert Panel Narrative Review summarizes available evidence and recommendations supporting the clinical applications of WB-MRI. This article also highlights limitations, barriers, and controversies associated with utilization of WB-MRI in routine clinical practice.

The Many Faces of Marrow Necrosis.

Depending on the age and location within the skeleton, bone marrow can be mostly fatty or hematopoietic, and both types can be affected by marrow necrosis. This review article highlights the magnetic resonance imaging findings of disorders in which marrow necrosis is the dominant feature.Fatty marrow necrosis is detected on T1-weighted images that show an early and specific finding: the reactive interface. Collapse is a frequent complication of epiphyseal necrosis and detected on fat-suppressed fluid-sensitive sequences or using conventional radiographs. Nonfatty marrow necrosis is less frequently diagnosed. It is poorly visible on T1-weighted images, and it is detected on fat-suppressed fluid-sensitive images or by the lack of enhancement after contrast injection.Pathologies historically "misnamed" as osteonecrosis but do not share the same histologic or imaging features of marrow necrosis are also highlighted.

Advances in Bone Marrow Imaging: Strengths and Limitations from a Clinical Perspective.

Conventional magnetic resonance imaging (MRI) remains the modality of choice to image bone marrow. However, the last few decades have witnessed the emergence and development of novel MRI techniques, such as chemical shift imaging, diffusion-weighted imaging, dynamic contrast-enhanced MRI, and whole-body MRI, as well as spectral computed tomography and nuclear medicine techniques. We summarize the technical bases behind these methods, in relation to the common physiologic and pathologic processes involving the bone marrow. We present the strengths and limitations of these imaging methods and consider their added value compared with conventional imaging in assessing non-neoplastic disorders like septic, rheumatologic, traumatic, and metabolic conditions. The potential usefulness of these methods to differentiate between benign and malignant bone marrow lesions is discussed. Finally, we consider the limitations hampering a more widespread use of these techniques in clinical practice.

Magnetic Resonance Imaging of Accelerated Bone Remodeling.

A regional acceleration of bone remodeling may possibly follow biomechanical insults to the bone. This review assesses the literature and clinical arguments supporting the hypothetical association between accelerated bone remodeling and bone marrow edema (BME)-like signal intensity on magnetic resonance imaging. BME-like signal is defined as a confluent ill-delimited area of bone marrow with a moderate decrease in signal intensity on fat-sensitive sequences and a high signal intensity on fat-suppressed fluid-sensitive sequences. In addition to this confluent pattern, a linear subcortical pattern and a patchy disseminated pattern have also been recognized on fat-suppressed fluid-sensitive sequences. These particular BME-like patterns may remain occult on T1-weighted spin-echo images. We hypothesize that these BME-like patterns, with particular characteristics in terms of distribution and signal, are associated with accelerated bone remodeling. Limitations in recognizing these BME-like patterns are also discussed.

Morphological assessment of cartilage and osteoarthritis in clinical practice and research: Intermediate-weighted fat-suppressed sequences and beyond.

Magnetic resonance imaging (MRI) is widely regarded as the primary modality for the morphological assessment of cartilage and all other joint tissues involved in osteoarthritis. 2D fast spin echo fat-suppressed intermediate-weighted (FSE FS IW) sequences with a TE between 30 and 40ms have stood the test of time and are considered the cornerstone of MRI protocols for clinical practice and trials. These sequences offer a good balance between sensitivity and specificity and provide appropriate contrast and signal within the cartilage as well as between cartilage, articular fluid, and subchondral bone. Additionally, FS IW sequences enable the evaluation of menisci, ligaments, synovitis/effusion, and bone marrow edema-like signal changes. This review article provides a rationale for the use of FSE FS IW sequences in the morphological assessment of cartilage and osteoarthritis, along with a brief overview of other clinically available sequences for this indication. Additionally, the article highlights ongoing research efforts aimed at improving FSE FS IW sequences through 3D acquisitions with enhanced resolution, shortened examination times, and exploring the potential benefits of different magnetic field strengths. While most of the literature on cartilage imaging focuses on the knee, the concepts presented here are applicable to all joints. KEY POINTS: 1. MRI is currently considered the modality of reference for a "whole-joint" morphological assessment of osteoarthritis. 2. Fat-suppressed intermediate-weighted sequences remain the keystone of MRI protocols for the assessment of cartilage morphology, as well as other structures involved in osteoarthritis. 3. Trends for further development in the field of cartilage and joint imaging include 3D FSE imaging, faster acquisition including AI-based acceleration, and synthetic imaging providing multi-contrast sequences.

[Diagnosis and management of tenosynovial giant cell tumor]. / Diagnostic et prise en charge de la tumeur à cellules géantes ténosynoviale.

Tenosynovial giant cell tumor is a benign condition that originates from synovial cells within joints, tendon sheaths, or bursae and may present either in localized (benign) or diffuse (locally aggressive) forms. Currently, the primary treatment approach is surgical, yielding satisfactory results with low recurrence rates in the localized forms, whereas the diffuse type displays high recurrence rates. In parallel, clinical trials are underway to explore pharmaceutical treatment options for the advanced diffuse type. This article aims at consolidating current knowledge about diagnosis and management of this rare tumor, additionally proposing a brief overview of novel therapeutic approaches.

La tumeur à cellules géantes ténosynoviale, bénigne, prend son origine dans les cellules synoviales des articulations, des gaines tendineuses ou des bourses et se présente dans une forme soit localisée (bénigne), soit diffuse (localement agressive). Le traitement principal est chirurgical, offrant des résultats satisfaisants à long terme, avec un faible risque de récidive dans la forme localisée, alors que le taux de récidives est élevé dans la forme diffuse. Parallèlement, des essais cliniques sont en cours pour explorer des options de traitement systémique pour les formes diffuses sévères. Cet article rappelle les connaissances actuelles pour le diagnostic et la prise en charge de cette tumeur rare. De plus, nous proposons un aperçu succinct des nouvelles approches thérapeutiques.

MRI signal and morphological alterations of the suprapatellar fat pad in asymptomatic subjects: are these normal variants?

OBJECTIVE: To study the prevalence of suprapatellar fat pad (SPFP) MR alterations in asymptomatic subjects, in relation to a wide range of clinical/imaging parameters, including muscle performance tests and physical activity data. MATERIALS AND METHODS: We prospectively included 110 asymptomatic subjects as part of a cohort study. Inclusion criteria were no knee pain in the last year. Exclusion criteria were any medical/surgical history of a knee disorder. Subjects underwent knee and low-dose posture radiographs [EOS®], 3 T MRI, clinical examination including muscle performance tests, and physical activity monitoring. The presence/absence of SPFP alterations (hyperintensity and mass effect) were assessed through consensus reading on fluid-sensitive sequences. Differences between groups of knees with SPFP alterations and controls were tested for a total of 55 categorical/continuous clinical/imaging parameters, including SPFP relative-T2-signal, trochlear/patellar/lower-limb morphologic measurements. Wilcoxon-rank-sum and chi-square tests were used to compare groups of patients. The histological correlation was obtained in a cadaveric specimen. RESULTS: SPFP alterations were common in asymptomatic subjects: hyperintensity 57% (63/110) and mass effect 37% (41/110), with 27% (30/110) showing both. Among the 55 imaging, clinical, or activity parameters tested, only increased patellar tilt angle (p = 0.02) and TT-TG distance (p = 0.03) were statistically different between groups of SPFP alterations and controls. The histological correlation showed more abundant connective tissue in SPFP compared to the prefemoral fat pad. CONCLUSIONS: SPFP hyperintensity and mass effect are common MRI findings in asymptomatic knees, and they are not related to most imaging, clinical, and activity parameters. Care should be taken not to overcall them pathological findings as they most likely represent normal variants.

Ossification of the acetabular rim: a highly prevalent finding in asymptomatic non-osteoarthritic hips of all ages.

OBJECTIVE: To estimate the prevalence of acetabular rim ossifications in the adult population with asymptomatic, morphologically normal hips at CT and to determine whether the presence of these ossifications is associated with patient- or hip-related parameters. METHODS: We prospectively included all patients undergoing thoracoabdominal CT over a 3-month period. After exclusion of patients with a clinical history of hip pathology and/or with signs of osteoarthritis on CT, we included a total of 150 hips from 75 patients. We analyzed the presence and the size of ossifications around the acetabular rim. The relationships between the size of acetabular rim ossifications and patient-related (sex, age, BMI) or hip-related parameters (joint space width, and cam- and pincer-type femoroacetabular impingement morphology) were tested using multiple regression analysis. RESULTS: The prevalence of acetabular rim ossifications in this population of asymptomatic, non-osteoarthritic hips was 96% (95% CI = [80.1; 100.0]). The presence of ossifications and their size were correlated between the right and left hips (Spearman coefficient = 0.64 (95% CI = [0.46;0.79]), p < 0.05)). The size of acetabular rim ossifications was significantly associated with age (p < 0.0001) but not with BMI (p = 0.35), gender (p = 0.05), joint space width (p ≥ 0.53 for all locations), or any of the qualitative or quantitative parameters associated with femoroacetabular morphology (p ≥ 0.34). CONCLUSION: Acetabular rim ossifications are highly prevalent in asymptomatic, non-osteoarthritic adult hips at all ages. Their size is not correlated with any patient- or hip-related parameters except for age. These findings suggest that ossifications at the acetabular rim, when present in isolation, should not be considered a sign of osteoarthritis or femoroacetabular impingement morphology. KEY POINTS: • Acetabular rim ossifications are extremely common in asymptomatic, non-osteoarthritic adult hips. • Acetabular rim ossifications are present independently from other signs of osteoarthritis in adult hips at all ages and should not be interpreted as a pathological finding. • The diagnosis of osteoarthritis or femoroacetabular impingement morphology should not be made based on the sole presence of ossifications at the acetabular rim.

Differentiation between benign and malignant vertebral compression fractures using qualitative and quantitative analysis of a single fast spin echo T2-weighted Dixon sequence.

OBJECTIVES: To determine and compare the qualitative and quantitative diagnostic performance of a single sagittal fast spin echo (FSE) T2-weighted Dixon sequence in differentiating benign and malignant vertebral compression fractures (VCF), using multiple readers and different quantitative methods. METHODS: From July 2014 to June 2020, 95 consecutive patients with spine MRI performed prior to cementoplasty for acute VCFs were retrospectively included. VCFs were categorized as benign (n = 63, mean age = 76 ± 12 years) or malignant (n = 32, mean age = 63 ± 12 years) with a best valuable comparator as a reference. Qualitative analysis was independently performed by four radiologists by categorizing each VCF as either benign or malignant using only the image sets provided by FSE T2-weighted Dixon sequences. Quantitative analysis was performed using two different regions of interest (ROI1-2) and three methods (signal drop, fat fraction (FF) from ROIs, FF maps). Diagnostic performance was compared using ROC curves analyses. Interobserver agreement was assessed using kappa statistics and intraclass correlation coefficients (ICC). RESULTS: The qualitative diagnostic performance ranged from area under the curve (AUC) = 0.97 (95% CI: 0.91-1.00) to AUC = 0.99 (95% CI: 0.95-1.0). The quantitative diagnostic performance ranged from AUC = 0.82 (95% CI: 0.73-0.89) to AUC = 0.97 (95% CI: 0.91-0.99). Pairwise comparisons showed no statistical difference in diagnostic performance (all p > 0.0013, Bonferroni-corrected p < 0.0011). All five cases with disagreement among the readers were correctly diagnosed at quantitative analysis using ROI2. Interobserver agreement was excellent for both qualitative and quantitative analyses. CONCLUSIONS: A single FSE T2-weighted Dixon sequence can be used to differentiate benign and malignant VCF with high diagnostic performance using both qualitative and quantitative analyses, which can provide complementary information. KEY POINTS: • Qualitative analysis of a single FSE T2-weighted Dixon sequence yields high diagnostic performance and excellent observer agreement for differentiating benign and malignant compression fractures. • The same FSE T2-weighted Dixon sequence allows quantitative assessment with high diagnostic performance. • Quantitative data can readily be extracted from the FSE T2-weighted Dixon sequence and may provide complementary information to the qualitative analysis, which may be useful in doubtful cases.

Interobserver reliability of the Tile classification system for pelvic fractures among radiologists and surgeons.

OBJECTIVES: To assess the interobserver reliability (IOR) of the Tile classification system, and its potential influence on outcomes, for the interpretation of CT images of pelvic fractures by radiologists and surgeons. METHODS: Retrospective data (1/2008-12/2016) from 238 patients with pelvic fractures were analyzed. Mean patient age was 44 years (SD 20); 66% were male. There were 54 Tile A, 82 Tile B, and 102 Tile C type injuries. The 30-day mortality rate was 15% (36/238). Six observers, three radiologists, and three surgeons with different levels of experience (attending/resident/intern) classified each fracture into one of the 26 second-order subcategories of the Tile classification. Weighted kappa coefficients were used to assess the IORs for the three main categories and nine first-order subcategories. RESULTS: The overall IORs of the Tile system for the main categories and first-order subcategories were moderate (kappa = 0.44) and fair (kappa = 0.31), respectively. IOR was fair to moderate among radiologists, but only fair among surgeons. By level of training, IOR was moderate between attendings and between residents, whereas it was only fair between interns. IOR was moderate to substantial (kappa = 0.56-0.70) between the radiology attending and resident. Association of the Tile fracture type with 30-day mortality was present based on two out of six observer ratings. CONCLUSIONS: The overall IOR of the Tile classification system is only fair to moderate, increases with the level of rater experience and is better among radiologists than surgeons. In the light of these findings, results from studies using this classification system must be interpreted cautiously. KEY POINTS: • The overall interobserver reliability of the Tile pelvic fracture classification is only fair to moderate. • Interobserver reliability increases with observer experience and radiologists have higher kappa coefficients than surgeons. • Interobserver reliability has an impact on the association of the Tile classification system with mortality in two out of six cases.

To buy or not to buy-evaluating commercial AI solutions in radiology (the ECLAIR guidelines).

Artificial intelligence (AI) has made impressive progress over the past few years, including many applications in medical imaging. Numerous commercial solutions based on AI techniques are now available for sale, forcing radiology practices to learn how to properly assess these tools. While several guidelines describing good practices for conducting and reporting AI-based research in medicine and radiology have been published, fewer efforts have focused on recommendations addressing the key questions to consider when critically assessing AI solutions before purchase. Commercial AI solutions are typically complicated software products, for the evaluation of which many factors are to be considered. In this work, authors from academia and industry have joined efforts to propose a practical framework that will help stakeholders evaluate commercial AI solutions in radiology (the ECLAIR guidelines) and reach an informed decision. Topics to consider in the evaluation include the relevance of the solution from the point of view of each stakeholder, issues regarding performance and validation, usability and integration, regulatory and legal aspects, and financial and support services. KEY POINTS: • Numerous commercial solutions based on artificial intelligence techniques are now available for sale, and radiology practices have to learn how to properly assess these tools. • We propose a framework focusing on practical points to consider when assessing an AI solution in medical imaging, allowing all stakeholders to conduct relevant discussions with manufacturers and reach an informed decision as to whether to purchase an AI commercial solution for imaging applications. • Topics to consider in the evaluation include the relevance of the solution from the point of view of each stakeholder, issues regarding performance and validation, usability and integration, regulatory and legal aspects, and financial and support services.

Interdisciplinary consensus statements on imaging of scapholunate joint instability.

OBJECTIVES: The purpose of this agreement was to establish evidence-based consensus statements on imaging of scapholunate joint (SLJ) instability by an expert group using the Delphi technique. METHODS: Nineteen hand surgeons developed a preliminary list of questions on SLJ instability. Radiologists created statements based on the literature and the authors' clinical experience. Questions and statements were revised during three iterative Delphi rounds. Delphi panellists consisted of twenty-seven musculoskeletal radiologists. The panellists scored their degree of agreement to each statement on an eleven-item numeric scale. Scores of '0', '5' and '10' reflected complete disagreement, indeterminate agreement and complete agreement, respectively. Group consensus was defined as a score of '8' or higher for 80% or more of the panellists. RESULTS: Ten of fifteen statements achieved group consensus in the second Delphi round. The remaining five statements achieved group consensus in the third Delphi round. It was agreed that dorsopalmar and lateral radiographs should be acquired as routine imaging work-up in patients with suspected SLJ instability. Radiographic stress views and dynamic fluoroscopy allow accurate diagnosis of dynamic SLJ instability. MR arthrography and CT arthrography are accurate for detecting scapholunate interosseous ligament tears and articular cartilage defects. Ultrasonography and MRI can delineate most extrinsic carpal ligaments, although validated scientific evidence on accurate differentiation between partially or completely torn or incompetent ligaments is not available. CONCLUSIONS: Delphi-based agreements suggest that standardized radiographs, radiographic stress views, dynamic fluoroscopy, MR arthrography and CT arthrography are the most useful and accurate imaging techniques for the work-up of SLJ instability. KEY POINTS: • Dorsopalmar and lateral wrist radiographs remain the basic imaging modality for routine imaging work-up in patients with suspected scapholunate joint instability. • Radiographic stress views and dynamic fluoroscopy of the wrist allow accurate diagnosis of dynamic scapholunate joint instability. • Wrist MR arthrography and CT arthrography are accurate for determination of scapholunate interosseous ligament tears and cartilage defects.

A Registration Method for Three-Dimensional Analysis of Bone Mineral Density in the Proximal Tibia.

Although alterations in bone mineral density (BMD) at the proximal tibia have been suggested to play a role in various musculoskeletal conditions, their pathophysiological implications and their value as markers for diagnosis remain unclear. Improving our understanding of proximal tibial BMD requires novel tools for three-dimensional (3D) analysis of BMD distribution. Three-dimensional imaging is possible with computed tomography (CT), but computational anatomy algorithms are missing to standardize the quantification of 3D proximal tibial BMD, preventing distribution analyses. The objectives of this study were to develop and assess a registration method, suitable with routine knee CT scans, to allow the standardized quantification of 3D BMD distribution in the proximal tibia. Second, as an example of application, the study aimed to characterize the distribution of BMD below the tibial cartilages in healthy knees. A method was proposed to register both the surface (vertices) and the content (voxels) of proximal tibias. The method combines rigid transformations to account for differences in bone size and position in the scanner's field of view and to address inconsistencies in the portion of the tibial shaft included in routine CT scan, with a nonrigid transformation locally matching the proximal tibias. The method proved to be highly reproducible and provided a comprehensive description of the relationship between bone depth and BMD. Specifically it reported significantly higher BMD in the first 6 mm of bone than deeper in the proximal tibia. In conclusion, the proposed method offers promising possibilities to analyze BMD and other properties of the tibia in 3D.

Practical ultrasonographic technique to precisely identify and differentiate tendons and ligaments of the elbow at the level of the humeral epicondyles: anatomical study.

OBJECTIVES: To develop a practical step-by-step technique to precisely identify and differentiate tendons and ligaments attaching to the humeral epicondyles, to confirm through gross anatomical study the accurate structure identification provided by this technique and to determine the frequency at which each structure can be identified in healthy volunteers. MATERIALS AND METHODS: First, ten fresh frozen cadavers (6 men, age at death = 58-92 years) were examined by two musculoskeletal radiologists and a step-by-step technique for the identification of tendons and ligaments at the level of humeral epicondyles was developed. Second, the accurate identification of structures was confirmed through gross anatomical study including anatomical sections on five specimens and layer-by-layer dissection technique on five others. Finally, 12 healthy volunteers (6 men, average age = 36, range = 28-52) were scanned by two radiologists following the same technique. RESULTS: An ultrasonographic technique based on the recognition of bony landmarks and the use of ultrasonographic signs to differentiate overlapping structures was developed and validated through gross anatomical study. In healthy volunteers, most tendons and ligaments were identified and well-defined in ≥ 80% of cases, except for the extensor carpi radialis brevis and extensor digiti minimi tendons on the lateral epicondyle (having common attachments with the extensor digitorum communis) and the palmaris longus tendon on the medial epicondyle (absent, or common attachment with the flexor carpi radialis). CONCLUSION: A step-by-step approach to the ultrasonographic assessment of tendons and ligaments at the humeral epicondyles allowed accurate identification of and differentiation among these structures, in particular those relevant to pathological conditions.