J Clin Med. 2025 Aug 20. pii: 5877. [Epub ahead of print]14(16):
Vivek Sanker,
Poorvikha Gowda,
Alexander Thaller,
Zhikai Li,
Philip Heesen,
Zekai Qiang,
Srinath Hariharan,
Emil O R Nordin,
Maria Jose Cavagnaro,
John Ratliff,
Atman Desai.
Background: Spinal metastasis is the third most common site for metastatic localization, following the lung and liver. Manual detection through imaging modalities such as CT, MRI, PET, and bone scintigraphy can be costly and inefficient. Preliminary artificial intelligence (AI) techniques and computer-aided detection (CAD) systems have attempted to improve lesion detection, segmentation, and treatment response in oncological imaging. The objective of this review is to evaluate the current applications of AI across multimodal imaging techniques in the diagnosis of spinal metastasis. Methods: Databases like PubMed, Scopus, Web of Science Advance, Cochrane, and Embase (Ovid) were searched using specific keywords like 'spine metastases', 'artificial intelligence', 'machine learning', 'deep learning', and 'diagnosis'. The screening of studies adhered to the PRISMA guidelines. Relevant variables were extracted from each of the included articles such as the primary tumor type, cohort size, and prediction model performance metrics: area under the receiver operating curve (AUC), accuracy, sensitivity, specificity, internal validation and external validation. A random-effects meta-analysis model was used to account for variability between the studies. Quality assessment was performed using the PROBAST tool. Results: This review included 39 studies published between 2007 and 2024, encompassing a total of 6267 patients. The three most common primary tumors were lung cancer (56.4%), breast cancer (51.3%), and prostate cancer (41.0%). Four studies reported AUC values for model training, 16 for internal validation, and five for external validation. The weighted average AUCs were 0.971 (training), 0.947 (internal validation), and 0.819 (external validation). The risk of bias was the highest in the analysis domain, with 22 studies (56%) rated high risk, primarily due to inadequate external validation and overfitting. Conclusions: AI-based approaches show promise for enhancing the detection, segmentation, and characterization of spinal metastatic lesions across multiple imaging modalities. Future research should focus on developing more generalizable models through larger and more diverse training datasets, integrating clinical and imaging data, and conducting prospective validation studies to demonstrate meaningful clinical impact.
Keywords: artificial intelligence (AI); convolutional neural networks (CNNs); deep learning; diagnostic imaging; machine learning; radiomics; spinal metastasis