Artificial intelligence (AI) has rapidly emerged as a transformative force in musculoskeletal imaging and interventional radiology. This article explores how AI-based methods—including machine learning (ML) and deep learning (DL)—streamline diagnostic processes, guide interventions, and improve patient outcomes. Key applications discussed include ultrasound-guided procedures for joints, nerves, and tumor-targeted interventions, along with CT-guided biopsies and ablations, and fluoroscopy-guided facet joint and nerve block injections. AI-powered segmentation algorithms, real-time feedback systems, and dose-optimization protocols collectively enable greater precision, operator consistency, and patient safety. In rehabilitation, AI-driven wearables and predictive models facilitate personalized exercise programs that can accelerate recovery and enhance long-term function. While challenges persist—such as data standardization, regulatory hurdles, and clinical adoption—ongoing interdisciplinary collaboration, federated learning models, and the integration of genomic and environmental data hold promise for expanding AI’s capabilities. As personalized medicine continues to advance, AI is poised to refine risk stratification, reduce radiation exposure, and support minimally invasive, patient-specific interventions, ultimately reshaping musculoskeletal care from early detection and diagnosis to individualized treatment and rehabilitation.

Objectives: Computed tomography scans of the kidney, ureters, and bladder (CT-KUB) are crucial in investigating urinary calculi but impart a substantial radiation doses. Radiation can be limited by minimising the scanning field to the necessary area (i.e. from the kidneys to urethra). Before auditing, the superior limit of CT-KUB scans had not been formally clarified at our trust. Consistently ensuring the upper limit of scans is at or below T10 has been shown to be a viable method of performing CT-KUB scans. This study aimed to assess the overscan length of CT-KUB investigations and modify practice accordingly to minimise it. There were two standards that were set for CT-KUB scanning. First, the mean percentage overscan length (i.e. percentage of the scan above the kidneys) should be 15% was present in 94.4% of scans. The mean percentage overscan length was 28.2%. The superior vertebral limit of 59% of scans was at T10 or below and a lower superior vertebral limit correlated with decreasing overscan. 99% of scans fully included both kidneys. In the second phase (3 months later), the mean overscan percentage reduced to 10.6% (standard deviation = 4.4%). Excessive overscan affected 35.2% of scans. The superior vertebral limit of 8% of scans was at T10 or below. 100% of scans fully included both kidneys. Conclusion: Excessive overscanning was due to inconsistent technique in capturing CT-KUB scans. Before this audit, the superior limit of CT-KUB scans had not been formally clarified at our trust. By successfully standardising the process with a reproducible method, the overscan target was comfortably met. Therefore, patient dose was minimised without compromising scan quality. Advances in knowledge: This audit has successfully shown a feasible standardised protocol for CT-KUB investigations which can be used to minimise overscanning of patients.

Primary malignant bone tumours can pose significant diagnostic and therapeutic challenges due to inter-tumour heterogeneity. While traditional imaging modalities such as radiography, MRI (magnetic resonance imaging), and CT (computed tomography) remain essential for initial evaluation and staging, emerging evidence underscores the evolving role of positron emission tomography (PET), particularly PET/CT with Fluorodeoxyglucose ([18F] FDG), in the comprehensive management of bone sarcomas. This narrative review aims to critically summarise the available literature on PET imaging’s utility in the management of primary bone tumours including osteosarcoma, chondrosarcoma, and Ewing sarcoma. Despite limitations like inconsistencies in standard uptake value (SUV) cutoffs and reduced pulmonary resolution, PET/CT is valuable for staging, assessing response to neoadjuvant chemotherapy, predicting histological outcomes, detecting recurrence, and guiding biopsy in metabolically active tumour sites. Further large-scale, prospective studies are warranted to standardise protocols and establish PET’s definitive role in sarcoma management.

Musculoskeletal image-guided interventional radiology plays a key role in diagnosing and treating a range of conditions. Recent advances have yielded a wide variety of procedures that can be applied selectively and enable the personalisation of patient care. This review aims to outline the indications, applications, and techniques of subspecialist musculoskeletal oncology interventional procedures that were used at our tertiary referral centre with a focus on how these may be used to personalise patient management. The applications of a range of diagnostic and therapeutic image-guided interventional procedures including different methods of bone and soft tissue sampling, ablation, and augmentation procedures across different types of patients and pathologies are reviewed. To supplement the reviewed literature, we included our own experience and radiology images retrospectively collected from our Picture Archiving and Communication System (PACS). We demonstrate how the range of musculoskeletal image-guided interventions provide flexibility in the diagnosis and management of different tumours across different patient populations. This study provides the musculoskeletal interventional radiologist with insight into how to appropriately utlilise different techniques to optimise the diagnosis, treatment and palliation of tumours.

Bone lesions encountered as part of radiology practice can bring diagnostic challenges, both when encountered incidentally or suspected as a primary bone lesion, and in patients at risk of metastases or marrow-based malignancies. Differentiating benign from malignant bone marrow lesions is critical, yet can be challenging due to overlapping imaging characteristics. One key imaging feature that can assist with diagnosis is the presence of fat within the lesion. Fat can be present either macroscopically (i.e., visible on radiographs, computed tomography (CT), and conventional magnetic resonance imaging (MRI)), or microscopically, detected through specialised MRI techniques such as chemical shift imaging (CSI). This comprehensive review explores the diagnostic significance of both macroscopic and microscopic fat in bone lesions and discusses how its presence can point towards benignity. We illustrate the spectrum of fat-containing bone lesions, encompassing both typical and atypical presentations, and provide practical imaging strategies to increase diagnostic accuracy by utilising radiographs, CT, and MRI in characterising these lesions. Specifically, CSI is highlighted as a non-invasive method for evaluating intralesional fat content, to distinguish benign marrow entities from malignant marrow-replacing conditions based on quantifiable signal drop-off. Furthermore, we detail imaging pitfalls with a focus on conditions that can mimic malignancy (such as aggressive haemangiomas) and collision lesions. Through a detailed discussion and illustrative examples, we aim to guide radiologists and clinicians in recognising reassuring imaging features while also identifying scenarios where further investigation may be warranted.

Bone oedema is a non-specific imaging finding associated with a wide range of pathologies, including trauma, infection, inflammation, and neoplasms