Zachary Elijah Stewart

Musculoskeletal radiology has transitioned to “musculoskeletal imaging and intervention,” encompassing both traditional diagnostic roles and specialized interventional roles shared with our interventional radiology colleagues. As part of the 30th year of publication of Seminars in Musculoskeletal Radiology, we are excited to present to readers what musculoskeletal interventions embody and how the field has progressed from past to present. We also specifically examine the future impact of artificial intelligence, robotics, and emerging technologies on procedural safety and effectiveness. Artificial intelligence is already optimizing scheduling and needle visualization while robotics and augmented reality are demonstrating high success rates in autonomous injections and biopsies. To envision the future of musculoskeletal intervention and the evolving roles of artificial intelligence and robotics, we must first understand where the field originated and where it stands today.

Background/Objectives: Fluoroscopically guided cervical nerve root corticosteroid injections are used for the treatment and diagnosis of radicular pain. Including a local anesthetic with the injected corticosteroid may decrease the pain associated with the procedure and add immediate diagnostic value. However, little is known about the safety of including a local anesthetic with a corticosteroid in these injections. Methods: A total of 299 consecutive cervical nerve root injections, performed between 2016 and 2024, were reviewed. Demographic and injection information (level/laterality and inclusion/exclusion of 1% preservative-free lidocaine with dexamethasone injectate) were documented. Charts were reviewed for major complications and increased pain post-procedure. Categorical data were compared between groups using Fisher’s exact test or Chi-square testing. Results: Injections were performed with 10 mg of dexamethasone only in 263 cases and with a mixture of 10 mg of dexamethasone and 1 mL of 1% lidocaine in 36 cases. There was no statistically significant difference in the incidence of major complications (p ≈ 1) or immediately increased pain post-procedure (p = 0.799). Conclusions: With proper technique, there is no evidence from this case–control study or in the available literature to suggest that including lidocaine with corticosteroid increases risks associated with cervical nerve root injections. However, serious adverse events are theoretically possible with injection of local anesthetic into a radicular artery, the vertebral artery, or subdural space. Given that such risks are not associated with the use of non-particulate steroids alone, large multi-institutional studies are needed to draw confident conclusions on the risks and benefits of the inclusion of local anesthetics with non-particulate corticosteroids for cervical transforaminal epidural steroid injection to inform clinical practice.

To predict cartilage tumor malignancy from radiographic images combined with readily available non-imaging information based on a vision-language foundation model. This single-institution study assembled a dataset of 3336 radiographs from 455 patients with enchondroma or chondrosarcoma that was assembled from two sources: (1) patients with histopathology-confirmed diagnoses of enchondroma or chondrosarcoma, and (2) patients with imaging-stable enchondroma without biopsy, confirmed through long-term imaging follow-up. An adapted vision-language foundation model based on the pre-trained CLIP (Contrastive Language-Image Pretraining) architecture was fine-tuned with our proposed Medical Knowledge Adapters and evaluated using 10-fold patient-level cross-validation to predict cartilage tumor malignancy from plain radiographs and demographic information. Using radiographs alone, the model achieved an Areas Under the receiver operating characteristic Curve (AUC) of 0.91 ± 0.04. Incorporating demographics improved the AUC to 0.94 ± 0.02. Subgroup analysis demonstrated robust generalizability across tumor grades with an AUC of 0.91 ± 0.07 in distinguishing atypical cartilaginous tumors (ACT) previously known as low grade chondrosarcomas, and 0.95 ± 0.02 in differentiating high-grade chondrosarcomas from enchondromas. Within the clinically challenging extremity subgroup (enchondroma vs ACT/LGCS), the model achieved an AUC of 0.79 ± 0.14, reflecting diagnostic difficulty observed in clinical practice. This foundation model-based approach demonstrates strong performance using accessible data sources, offering a non-invasive, cost-efficient, and scalable solution for cartilage tumor assessment in musculoskeletal oncology.

Minimally invasive ultrasound-guided techniques enable physicians to treat common musculoskeletal injuries of the knee. In addition to standard injectable anti-inflammatory treatments, other image-guided procedures are emerging, including injectable orthobiologics (i.e., platelet-rich plasma), needle tenotomy, and cyst fenestrations. Here, the rationale and technique for ultrasound-guided treatments for common knee ailments are reviewed.

Objective Describe the early non-arthrographic MRI appearance of the acetabular labrum after arthroscopic surgery for femoroacetabular impingement and labrum repair. Methods Eleven subjects (12 hips, 8 hips of females; mean age: 25.8 years, SD: 3.0) with a pre-operative MRI demonstrating a labrum tear and symptoms of femoroacetabular impingement were prospectively enrolled. Non-arthrographic images were obtained on a 3 T MRI scanner < 4 weeks after arthroscopic surgery for femoroacetabular impingement. Imaging features of the labrum, capsule, and cartilage were systematically assessed by two independent fellowship-trained musculoskeletal radiologists. Disagreements were resolved through consensus mediated by a musculoskeletal radiologist with 20 + years of experience and expertise in hip imaging. Results The appearance of a persistent labral tear and increased intrasubstance signal was observed in all hips. The labrum appeared shortened in 92% (11/12). The geographic distribution of abnormal labral signal corresponded to the same number of labrum quadrants treated surgically in 67% (8/12). There was an even distribution of hips showing abnormal signal across a smaller and larger portion of the labrum than was treated arthroscopically, seen in 17% (2/12), respectively. The appearance of a capsular defect was observed in 92% (11/12). Conclusion In the first 4 weeks after arthroscopic labrum repair surgery for femoroacetabular impingement, it is common for the labrum to appear shortened with a persistent appearance of a labrum tear and increased signal in the repaired segment. The capsule often appears discontinuous, even when capsular closure is performed.

Knee osteoarthritis is common and projected to increase in prevalence. When conservative treatments fail to improve pain and disability, the primary surgical option is total knee arthroplasty. Percutaneous image-guided ablation of the sensory articular nerve branches to the knee, also referred to as the genicular nerves, is a potential non-operative treatment. Here, we review the relevant anatomy, modes of denervation/neuromodulation, procedural techniques, and current controversies.