Artificial intelligence (AI) shows promise in streamlining MRI workflows by reducing radiologists’ workload and improving diagnostic accuracy. Despite MRI’s extensive clinical use, systematic evaluation of AI-driven productivity gains in MRI remains limited. This review addresses that gap by synthesizing evidence on how AI can shorten scanning and reading times, optimize worklist triage, and automate segmentation. On 15 November 2024, we searched PubMed, EMBASE, MEDLINE, Web of Science, Google Scholar, and Cochrane Library for English-language studies published between 2000 and 15 November 2024, focusing on AI applications in MRI. Additional searches of grey literature were conducted. After screening for relevance and full-text review, 66 studies met inclusion criteria. Extracted data included study design, AI techniques, and productivity-related outcomes such as time savings and diagnostic accuracy. The included studies were categorized into five themes: reducing scan times, automating segmentation, optimizing workflow, decreasing reading times, and general time-saving or workload reduction. Convolutional neural networks (CNNs), especially architectures like ResNet and U-Net, were commonly used for tasks ranging from segmentation to automated reporting. A few studies also explored machine learning-based automation software and, more recently, large language models. Although most demonstrated gains in efficiency and accuracy, limited external validation and dataset heterogeneity could reduce broader adoption. AI applications in MRI offer potential to enhance radiologist productivity, mainly through accelerated scans, automated segmentation, and streamlined workflows. Further research, including prospective validation and standardized metrics, is needed to enable safe, efficient, and equitable deployment of AI tools in clinical MRI practice.

Diagnostic imaging, particularly MRI, plays a key role in the evaluation of many spine pathologies. Recent progress in artificial intelligence and its subset, machine learning, has led to many applications within spine MRI, which we sought to examine in this review. A literature search of the major databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The search yielded 1226 results, of which 50 studies were selected for inclusion. Key data from these studies were extracted. Studies were categorized thematically into the following: Image Acquisition and Processing, Segmentation, Diagnosis and Treatment Planning, and Patient Selection and Prognostication. Gaps in the literature and the proposed areas of future research are discussed. Current research demonstrates the ability of artificial intelligence to improve various aspects of this field, from image acquisition to analysis and clinical care. We also acknowledge the limitations of current technology. Future work will require collaborative efforts in order to fully exploit new technologies while addressing the practical challenges of generalizability and implementation. In particular, the use of foundation models and large-language models in spine MRI is a promising area, warranting further research. Studies assessing model performance in real-world clinical settings will also help uncover unintended consequences and maximize the benefits for patient care.

In spinal oncology, integrating deep learning with computed tomography (CT) imaging has shown promise in enhancing diagnostic accuracy, treatment planning, and patient outcomes. This systematic review synthesizes evidence on artificial intelligence (AI) applications in CT imaging for spinal tumors. A PRISMA-guided search identified 33 studies: 12 (36.4%) focused on detecting spinal malignancies, 11 (33.3%) on classification, 6 (18.2%) on prognostication, 3 (9.1%) on treatment planning, and 1 (3.0%) on both detection and classification. Of the classification studies, 7 (21.2%) used machine learning to distinguish between benign and malignant lesions, 3 (9.1%) evaluated tumor stage or grade, and 2 (6.1%) employed radiomics for biomarker classification. Prognostic studies included three (9.1%) that predicted complications such as pathological fractures and three (9.1%) that predicted treatment outcomes. AI’s potential for improving workflow efficiency, aiding decision-making, and reducing complications is discussed, along with its limitations in generalizability, interpretability, and clinical integration. Future directions for AI in spinal oncology are also explored. In conclusion, while AI technologies in CT imaging are promising, further research is necessary to validate their clinical effectiveness and optimize their integration into routine practice.

Background: Privacy-preserving large language models (PP-LLMs) hold potential for assisting clinicians with documentation. We evaluated a PP-LLM to improve the clinical information on radiology request forms for musculoskeletal magnetic resonance imaging (MRI) and to automate protocoling, which ensures that the most appropriate imaging is performed. Methods: The present retrospective study included musculoskeletal MRI radiology request forms that had been randomly collected from June to December 2023. Studies without electronic medical record (EMR) entries were excluded. An institutional PP-LLM (Claude Sonnet 3.5) augmented the original radiology request forms by mining EMRs, and, in combination with rule-based processing of the LLM outputs, suggested appropriate protocols using institutional guidelines. Clinical information on the original and PP-LLM radiology request forms were compared with use of the RI-RADS (Reason for exam Imaging Reporting and Data System) grading by 2 musculoskeletal (MSK) radiologists independently (MSK1, with 13 years of experience, and MSK2, with 11 years of experience). These radiologists established a consensus reference standard for protocoling, against which the PP-LLM and of 2 second-year board-certified radiologists (RAD1 and RAD2) were compared. Inter-rater reliability was assessed with use of the Gwet AC1, and the percentage agreement with the reference standard was calculated. Results: Overall, 500 musculoskeletal MRI radiology request forms were analyzed for 407 patients (202 women and 205 men with a mean age [and standard deviation] of 50.3 ± 19.5 years) across a range of anatomical regions, including the spine/pelvis (143 MRI scans; 28.6%), upper extremity (169 scans; 33.8%) and lower extremity (188 scans; 37.6%). Two hundred and twenty-two (44.4%) of the 500 MRI scans required contrast. The clinical information provided in the PP-LLM-augmented radiology request forms was rated as superior to that in the original requests. Only 0.4% to 0.6% of PP-LLM radiology request forms were rated as limited/deficient, compared with 12.4% to 22.6% of the original requests (p < 0.001). Almost-perfect inter-rater reliability was observed for LLM-enhanced requests (AC1 = 0.99; 95% confidence interval [CI], 0.99 to 1.0), compared with substantial agreement for the original forms (AC1 = 0.62; 95% CI, 0.56 to 0.67). For protocoling, MSK1 and MSK2 showed almost-perfect agreement on the region/coverage (AC1 = 0.96; 95% CI, 0.95 to 0.98) and contrast requirement (AC1 = 0.98; 95% CI, 0.97 to 0.99). Compared with the consensus reference standard, protocoling accuracy for the PP-LLM was 95.8% (95% CI, 94.0% to 97.6%), which was significantly higher than that for both RAD1 (88.6%; 95% CI, 85.8% to 91.4%) and RAD2 (88.2%; 95% CI, 85.4% to 91.0%) (p < 0.001 for both). Conclusions: Musculoskeletal MRI request form augmentation with an institutional LLM provided superior clinical information and improved protocoling accuracy compared with clinician requests and non-MSK-trained radiologists. Institutional adoption of such LLMs could enhance the appropriateness of MRI utilization and patient care. Level of Evidence: Diagnostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Background: Degenerative cervical spondylosis (DCS) is a common and potentially debilitating condition, with surgery indicated in selected patients. Deep learning models (DLMs) can improve consistency in grading DCS neural stenosis on magnetic resonance imaging (MRI), though existing models focus on axial images, and comparisons are mostly limited to radiologists. Methods: We developed an enhanced transformer-based DLM that trains on sagittal images and optimizes axial and foraminal classification using a maximized dataset. DLM training utilized 648 scans, with internal testing on 75 scans and external testing on an independent 75-scan dataset. Performance of the DLM, spine surgeons, and radiologists of varying subspecialities/seniority were compared against a consensus reference standard. Results: On internal testing, the DLM achieved high agreement for all-class classification: axial spinal canal κ = 0.80 (95%CI: 0.72–0.82), sagittal spinal canal κ = 0.83 (95%CI: 0.81–0.85), and neural foramina κ = 0.81 (95%CI: 0.77–0.84). In comparison, human readers demonstrated lower levels of agreement (κ = 0.60–0.80). External testing showed modestly degraded model performance (κ = 0.68–0.77). Conclusions: These results demonstrate the utility of transformer-based DLMs in multiplanar MRI interpretation, surpassing spine surgeons and radiologists on internal testing and highlighting its potential for real-world clinical adoption.